The current research focused on extraction optimization of bioactive compounds from Strychnos potatorum seeds (SPs) using an eco-friendly glycerol-sodium acetate based deep eutectic solvent (DES). The optimization was accomplished using response surface methodology (RSM) and artificial neural networking (ANN). The independent variables included shaking time (A), temperature (B), and solvent-to-feed ratio (C), and the responses were the extraction yield, total phenolic content (TPC), total flavonoid content (TFC), antioxidant activity (DPPH), and antidiabetic activity (α-amylase inhibitory activity). The SPs extracts obtained under optimal conditions (29 min, 40 °C and 30 mL/g of A, B, and C parameters, respectively) had 30.43 mg gallic acid equivalents (GAE)/g of dry weight (DW) TPC, 10.99 mg rutin equivalents (RE)/g DW TFC, 26.16 % antioxidant activity and 46.95 % α-amylase inhibitory activity. For all the outputs, the ANN percentage error was less than the RSM percentage error for the predicted values against the experimentally measured values. The results were further supported by the %AAD (% absolute average deviation) and R2 values obtained from RSM and ANN methods. The %AAD for TPC, TFC, DPPH, and α-amylase inhibitory activity by RSM was 7.31, 4.80, 4.03, and 4.36, while by ANN, it was 1.18, 3.90, 1.99, and 2.97, respectively. It is worth noting that despite no statistical difference between the two predictive models, ANN gave closer results to the experimental values. Correlation among various response types showed that TPC and TFC were strongly correlated. This research highlights the efficiency of glycerol-sodium acetate DES as an extractant.

The self-compacting concrete (SCC) mixes were developed using lightweight expandable clay aggregate (LECA) as a partial substitute for coarse aggregate, ground granulated blast-furnace slag (GGBS) as a partial replacement for cement, and combusted bio-medical waste ash (BMWA) as a partial replacement for fine aggregate. The substitution levels for LECA, GGBS, and BMWA were set at 10%, 20%, and 30% of coarse aggregate, cement, and fine aggregate, respectively. M30-grade SCC mixes were designed with two different water-to-binder ratios-0.40 and 0.45-and their compressive strength (CS) was experimentally evaluated. The data entries from the above mix designs and experiments were collected in this research which deals with evaluating the impact of lightweight expandable clay aggregate, metallurgical slag, and combusted bio-medical waste ash on self-compacting concrete. An extensive literature search was used in this project and this produced a global representative database collected from literature. The collected 384 records were divided into training set (300 records = 80%) and validation set (84 records = 20%) in line with the requirements of a more reliable data partitioning. Six advanced machine learning methods such as the Artificial Neural Network (ANN), Support Vector Regression (SVR), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGB), Random Forest (RF), and Adaptive Boosting (AdaBoost) were used to model the concrete behavior. All models were created using "Orange Data Mining" software version 3.36. A combination of error metrics, efficiency metrics and determination/correlation metrics were used to test the models performance and accuracy. Also, the Hoffman and Gardener's method was used to evaluate the sensitivity analysis of the model variables. At the end of the model work, AdaBoost and KNN excel in predictive accuracy with 97.5%, reducing the margin of error and ensuring precise mix designs for SCC. SVR, XGB, and RF also exhibit strong accuracy (96.5-97%), supporting reliable material selection and proportions. AdaBoost and KNN demonstrate the lowest errors (MAE: 0.65 MPa, RMSE: 0.75 MPa), indicating precise performance, minimizing overdesign or underperformance risks, and optimizing material usage. The Hoffman/Gardener's sensitivity analysis produced produced GGBS of 31% and Dens of 26% as the highest impact and this is followed by LECA of 21% and BMWA of 20%. This research enables the optimization of self-compacting concrete mix designs using machine learning, reducing experimental trials, enhancing material efficiency, lowering environmental impact, and promoting sustainable construction through the effective reuse of industrial by-products.

This study examines existing automatic screening methods for developmental language disorder (DLD), a neurodevelopmental language deficit without known biomedical etiologies, focusing on languages, data sets, extracted features, performance metrics, and classification methods. Additionally, it summarizes the strengths and weaknesses of current systems and explores future research opportunities and challenges.

We conducted a systematic review, searching PubMed, Web of Science, Scopus, and PsycINFO for articles published in English before March 2024. We included studies that developed automated screening systems to classify DLD cases among children.

A total of 23 studies were thoroughly reviewed. We found that automatic screening models for DLD focused on five languages, namely, Czech, Italian, Mandarin, Spanish, and English, with various data sets employed. Most studies identified and used acoustic, textural, and combination of speech features and nonspeech features for model development. Traditional machine learning, artificial neural networks, convolutional neural networks, long short-term memory, and non-machine-learning classification methods were employed in model training. The need for larger, multilingual data sets and improved system sensitivity is noted. Future research opportunities include exploring the integration of combined features and algorithms; implementing new algorithms; and considering variations in age, gender, severity, and comorbidity differences in DLD.

This systematic review of existing automatic screening methods for DLD highlights significant advancements and suggests potential areas in future research on automatic DLD screening.

Determining worker's body posture during load handling activities is the first step toward assessing and managing occupational risk of musculoskeletal injuries. Traditional approaches for the measurement of body posture are impractical in real work settings due to the required laboratory setups and occlusion issues. This study aims to develop artificial neural networks (ANNs) to predict full-body 3D continuous posture during load-reaching and load-leaving phases of lifting and lowering activities thus complementing our previous posture prediction ANNs for the load-moving phase (i.e., the lifting activity between load-reaching and load-leaving phases). Using an existing whole-body motion dataset from twenty healthy young novice subjects during 204 load-reaching and load-leaving tasks, four ANNs were developed to estimate body continuous coordinates and segment/joint angles based on task- and subject-specific parameters as inputs. Results indicated that the developed ANNs achieved root-mean-square-errors of <3 cm and <10° for load-reaching and <4 cm and <15° for load-leaving tasks for the whole-body under random hold-out validation. The maximum posture prediction errors were observed at the left side of the body and the prediction errors were larger during the second half of the activities. Compared to prior static posture prediction models, our approach enabled continuous, phase-specific posture prediction thereby improving relevance for ergonomic and biomechanical applications. Although further investigations are required across diverse demographics (e.g., for female, elderly, experienced individuals), the present ANNs represent a step toward more accessible posture prediction tools in occupational settings, potentially reducing data collection demands for ergonomic assessments.

Present new bioactive compounds, created by De novo Drug Design and artificial intelligence (AI), as possible inhibitors of C. auris polymerase.

MolAICal's AI module was configured to identify FDA-approved molecular fragments with therapeutic effectiveness against C. auris polymerase, where the model with optimized synthetic accessibility and structural complexity was subjected to docking and molecular dynamics simulations and pharmacokinetic prediction.

Among 1,722 new forms, the Hit-960 compound stood out for its high bioaffinity and stability, with a binding energy of -9.12 kcal/mol and 75% synthetic accessibility.

Clinical studies are recommended to test its efficacy, contributing to the development of new treatments for C. auris infections.

Cell-penetrating peptides (CPP) have gained rapid attention over the last 25 years; this is attributed to their versatility, customisation, and 'Trojan horse' delivery that evades the immune system. However, the current CPP rational design process is limited, as it requires several rounds of peptide synthesis, prediction and wet-lab validation, which is expensive, time-consuming and requires extensive knowledge in peptide chemistry. Artificial intelligence (AI) has emerged as a promising alternative which can augment the design process, for example by determining physiochemical characteristics, secondary structure, solvent accessibility, disorder and flexibility, as well as predicting in vivo behaviour such as toxicity and peptidase degradation. Other more recent tools utilise supervised machine learning (ML) to predict the penetrative ability of an amino acid sequence. The use of AI in the CPP design process has the potential to reduce development costs and increase the chances of success with respect to delivery. This review provides a survey of in silico tools and AI platforms which can be utilised in the design process, and the key features that should be taken into consideration when designing next generation CPPs.

This study systematically analyzes the land use changes in Changsha City from 2000 to 2023. Three classification models-Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and Artificial Neural Network (ANN) were employed to evaluate the accuracy of land use classification. The RF model, with an accuracy of 95.78%, outperformed the others, demonstrating its robustness and generalization ability in handling complex land use classification tasks. The study further conducted a spatiotemporal analysis of urban construction land expansion, identified key driving forces behind urbanization in Changsha. Results indicate that the construction land area expanded nearly threefold, from 563.82 km² in 2000 to 1628.20 km² in 2023, with the most significant growth occurring between 2010 and 2015. This rapid expansion was largely driven by China's "New Urbanization" policy and population growth. Additionally, 12 key factors influencing land use change in Changsha was analyzed, including slope, soil salinity, annual mean temperature, leaf area index, soil moisture, aerosols, aspect, nighttime light index (X8), DEM, population density (X10), vegetation cover, and annual precipitation. Univariate and interaction detection analyses revealed that the nighttime light index (X8) and population density (X10) were the most significant drivers of construction land expansion, consistently exhibiting high q-values across all years. In contrast, natural factors, such as slope (X1) and aerosols (X6), had a lesser impact on land use change, although their influence has gradually increased over time. This is particularly evident in the growing role of annual precipitation (X12) and leaf area index (X4) in influencing ecosystem and vegetation recovery. The study also simulated construction land expansion trends for 2030 under three different scenarios. In the natural development scenario, construction land area is projected to expand to 1920.65 km², reflecting unregulated expansion of urbanization. Under the farmland protection scenario, the area will grow to 1826.32 km², indicating the effectiveness of policy interventions in preserving agricultural land. The ecological control scenario, however, predicts a limited expansion to 1702.66 km², underscoring the importance of ecological protection policies in curbing uncontrolled urban sprawl. This research provides a comprehensive understanding of the driving mechanisms and evolutionary patterns of construction land use change in Changsha. It highlights the significant pressure that urbanization, particularly anthropogenic factors, has placed on land resources. It also demonstrates that policy regulation, particularly through ecological protection measures, can effectively mitigate this expansion trend. The findings offer valuable insights for land use planning and policy formulation in Changsha, underscoring the importance of balancing economic development with ecological preservation to achieve sustainable urban growth.

The study is based on applying Artificial Neural Network (ANN) based machine learning and Response Surface Methodology (RSM) as simultaneous bivariate approaches in developing controlled-release rivaroxaban (RVX) osmotic tablets. The influence of different types of polyethylene oxide, osmotic agents, coating membrane thickness, and orifice diameter on RVX release profiles was investigated. After obtaining the trial formulation data sets from Central Composite Design (CCD), an ANN-based model was trained to get the optimized formulations. The Physiological-based Pharmacokinetic (PBPK) modeling of the predicted formulation was performed by GastroPlus™ to simulate in vivo plasma profiles under fasting and fed conditions. In vitro release tests showed zero-order RVX release for up to 12 h. Using graphical and numerical methods, the predicted formulation generated by the prediction profiler was cross-validated by the CCD-based optimized formulation. Analysis of Variance (ANOVA) findings revealed no significant difference between the predicted and optimized formulations and these formulations have a shelf life of 22.47 and 17.87 months, respectively. The PBPK modeling of RVX push-pull osmotic pump (PPOP) tablets suggested enhanced bioavailability in the fasted (up to 82%) and fed (up to 98.5%) state compared to immediate-release tablets. The results indicated that ANN can be effectively used for osmotic systems due to their complex nature and nonlinear interactions between dependent and independent variables.

Current research on the association between demographic variables and dietary patterns with atherosclerotic cardiovascular disease (ASCVD) is limited in breadth and depth. This study aimed to construct a machine learning (ML) algorithm that can accurately and transparently establish correlations between demographic variables, dietary habits, and ASCVD. The dataset used in this research originates from the United States National Health and Nutrition Examination Survey (U.S. NHANES) spanning 1999-2018. Five ML models were developed to predict ASCVD, and the best-performing model was selected for further analysis. The study included 40,298 participants. Using 20 population characteristics, the eXtreme Gradient Boosting (XGBoost) model demonstrated high performance, achieving an area under the curve value of 0.8143 and an accuracy of 88.4%. The model showed a positive correlation between male sex and ASCVD risk, while age and smoking also exhibited positive associations with ASCVD risk. Dairy product intake exhibited a negative correlation, while a lower intake of refined grains did not reduce the risk of ASCVD. Additionally, the poverty income ratio and calorie intake exhibited non-linear associations with the disease. The XGBoost model demonstrated significant efficacy, and precision in determining the relationship between the demographic characteristics and dietary intake of participants in the U.S. NHANES 1999-2018 dataset and ASCVD.

Rivers are vital for sustaining human life as they foster social development, provide drinking water, maintain aquatic ecosystems, and offer recreational spaces. However, most rivers are being increasingly contaminated by pollutants from non-point sources, urbanization, and other sources. Consequently, real-time river water quality modeling is essential for managing and protecting rivers from contamination, and its significance is growing across various sectors, including public health, agriculture, and water treatment systems. Therefore, a real-time river water quality simulation toolbox was developed using machine learning (ML) and an application program interface (API). To create the toolbox, models that simulated water quality parameters such as chlorophyll a (Chl-a), dissolved oxygen (DO), total nitrogen (TN), total organic carbon (TOC), and total phosphorus (TP) at each point in the Nakdong River were constructed. The models were constructed using Artificial neural network (ANN), Random Forest (RF), support vector machines (SVM), and data from API. Subsequently, hyperparameter optimization was conducted to enhance the model's performance. During training, the models' performances were evaluated and compared based on the data sampling method and ML algorithms. Models trained with random sampling data outperformed those trained with time-series data. Among the algorithm models that used random sampling data, the RF exhibited the best performance. The average coefficient of determination (R2) values for each water quality simulation with randomly sampled data using RF for DO, TN, TP, Chl-a, and TOC were 0.79, 0.65, 0.74, 0.45, and 0.48, respectively. For ANN, they were 0.7, 0.51, 0.64, 0.35, and 0.35, respectively, and for SVM, they were 0.73, 0.51, 0.59, 0.21, and 0.3, respectively. The Chl-a and TOC models exhibited relatively poor performance, whereas the DO, TN, and TP models demonstrated superior performance. Diversifying the input data variables is necessary to improve the performance of the Chl-a and TOC models. Sensitivity and uncertainty analyses were conducted to evaluate and enhance the models' understanding. Furthermore, using a graphic user interface (GUI) toolbox, user convenience was maximized.

Feature extraction in ML plays a crucial role in transforming raw data into a more meaningful and interpretable representation. In this study, we thoroughly examined a range of feature extraction techniques and assessed their impact on the binary classification models for medical images, utilizing a diverse and rich set of medical imaging modalities. Using H&E-stained, chest X-ray, and retina OCT images, we applied methods to extract statistical, radiomics, and deep features. These features were then used to develop PCA-LDA models as the employed classifier. We evaluated the models based on two decisive metrics: latency and performance. Latency measured the time taken for feature extraction and prediction, while mean sensitivity (balanced accuracy) characterizes the model performance. Our comparative study revealed that statistical and radiomics features were less effective for medical image classification, as they showed high latency and lower performance scores. In contrast, pre-trained DL networks performed efficiently, with high sensitivity and low latency. For H&E-stained images, the statistical feature extraction took about an hour and achieved 90.8 % sensitivity, while ResNet50 reduced processing time fourfold and increased sensitivity to 96.9 %. For chest X-rays, radiomics features were time-intensive with 92.2 % sensitivity, while ResNet50 improved sensitivity to 96 % with faster extraction time. For retina OCT images, radiomics yielded a sensitivity of 91 %, while DenseNet121 achieved 98.6 % sensitivity in 15 min. These findings underscore the superior performance of DL techniques over the statistical and radiomics features, highlighting their potential for real-world applications where accurate and rapid diagnostic decisions are essential.

Crop maturity status recognition is a key component of automated harvesting. Traditional manual detection methods are inefficient and costly, presenting a significant challenge for the agricultural industry.

To improve crop maturity detection, we propose enhancements to the Real-Time DEtection TRansformer (RT-DETR) method. The original model's Backbone structure is refined by: HG Block Enhancement: Replacing conventional convolution with the Rep Block during feature extraction, incorporating multiple branches to improve model accuracy. Partial Convolution (PConv): Replacing traditional convolution in the Rep Block with PConv, which applies convolution to only a portion of the input channels, reducing computational redundancy. Efficient Multi-Scale Attention (EMA): Introducing EMA to ensure a uniform distribution of spatial semantic features within feature groups, improving model performance and efficiency.

The refined model significantly enhances detection accuracy. Compared to the original model, the average accuracy (mAP@0.5) improves by 2.9%, while model size is reduced by 5.5% and computational complexity decreases by 9.6%. Further experiments comparing the RT-DETR model, YOLOv8, and our improved model on plant pest detection datasets show that our model outperforms others in general scenarios.

The experimental results validate the efficacy of the enhanced RT-DETR model in crop maturity detection. The improvements not only enhance detection accuracy but also reduce model size and computational complexity, making it a promising solution for automated crop maturity detection.

A new metaheuristic optimizer combined with artificial neural networks is proposed for streamflow prediction. Hence, the study aimed to forecast monthly streamflow of the main rivers in Urmia, Iran, by considering data shortage and using artificial neural network (ANN) models. By combining three variables: temperature, precipitation, and streamflow, we formulated five patterns, where 70% of the data were used for model training, and 30% for model testing. To improve the performance of ANN, we evaluated a new optimization algorithm, reptile search algorithm (RSA), and compared the results with combinations of ANN, particle swarm optimization algorithm (PSO), and whale optimization algorithm (WOA) models. The results of the ANN + RSA were promising at most stations and patterns. At Band station streamflow simulation testing gave RMSE, MAE, and NSE of 1.65, 1.21 MCM/month, and 0.80, respectively. At Babaroud station they were 4.01, 3.0 MCM/month and 0.68, respectively, at Nazlo station 5.62, 3.79 MCM/month, and 0.69, respectively, and at Tapik station 5.69, 3.82 MCM/month, and 0.59, respectively. However, the results of the ANN + PSO hybrid model were better than ANN + RSA. The impact of different parameters on the accuracy of streamflow prediction varied depending on model and streamflow station, indicating that the models do not perform consistently across different locations, times, and conditions. The inclusion of lagged monthly streamflow in the model was an influential input parameter. The results demonstrated that the new algorithm consistently improved predictions, enhancing the performance of traditional algorithms. The findings of this study highlight advantage of the ANN + RSA hybrid model for specific areas, suggesting its potential application in other similar hydrological problems for further validation.

Laver (Pyropia spp.) is a major seaweed that is cultivated and consumed globally. Although quality standards for laver products have been established, traditional physicochemical analyses and sensory evaluations have notable drawbacks regarding rapid-quality inspection. Not all relevant physicochemical quality indices, such as texture, are typically evaluated. Therefore, in this study, we investigated the use of hyperspectral imaging to rapidly, accurately, and objectively determine the quality of dried laver. Hyperspectral images of 25 dried laver samples were captured in the short-wave infrared range from 980 to 2576 nm to assess their moisture, protein content, cutting stress, and other key quality indicators. Spectral signatures were analyzed using partial least-squares discriminant analysis (PLS-DA) to correlate the spectral data with three primary quality index values. The performance of PLS-DA was compared with that of the variable importance in projection score and nonlinear regression analysis methods. The comprehensive quality grading model demonstrated accuracies ranging from 96 to 100%, R2 values from 75 to 92%, and root-mean-square errors from 0.14 to 0.25. These results suggest that the PLS-DA regression model shows great potential for the multivariate analysis of hyperspectral images, serving as an effective quality grading system for dried laver.

Lipid-based formulations are essential for enhancing drug solubility and bioavailability, yet selecting optimal lipid excipients for specific drugs remains challenging. This study introduces Sol_ME, a machine learning-based model designed to predict drug solubility in lipidic environments, thereby streamlining the formulation process. The Sol_ME model uses PubChem® fingerprints, focusing on solubility correlations with lipid excipients, minimizing reliance on traditional parameters like LogP and molecular weight. The model was trained on a dataset of 1,379 drug-solvent entries and applied to the formulation of Apalutamide, a BCS Class II drug. Experimental validation was performed with 35 drug-solvent combinations to assess the accuracy of predicted solubilities. Sol_ME achieved a high predictive accuracy with a correlation coefficient of 0.998. The model successfully identified Cinnamon oil as the optimal excipient for Apalutamide, further refining the formulation with Vanillin. This reduced formulation volume by 75%, enabling the development of a single-unit 240 mg soft gelatin capsule. Experimental validation showed 80% alignment between predicted and actual solubilities. The Sol_ME model demonstrates significant potential to optimize lipid-based drug formulation, offering a data-driven approach that enhances efficiency. The success of Apalutamide formulation highlights its practical utility. Future work will expand the dataset and extend the model to solid lipid systems, broadening its application in drug delivery technologies.

Our fingers are the most dexterous and complicated parts of our body and play a significant role in our daily activities. Non-invasive techniques, such as Electroencephalography (EEG) and Electromyography (EMG) can be used to collect neural and muscular signals related to finger movements. In this study, we combined an 8-channel EMG and a 31-channel EEG while the human subject moved one of the five fingers on the right hand. To identify the best EEG frequency features that encode distinct finger movements, we systematically examined the decoding accuracies of the slow-cortical potentials and three types of sensorimotor rhythms, namely the Mu, beta, and gamma oscillations. For both EMG and EEG, we came up with a simple and unified root mean square or power approach that avoided the complex signal features used by previous studies. The signal features were then fed into a feedforward artificial-neural-network (ANN) classifier. We found that the low-gamma oscillation provided the best decoding performance over the other frequency bands, ranging from 65.0 % to 89.0 %, which was comparable to the EMG performance. Combining EMG and low gamma into a single ANN can further improve the outcome for subjects who had showed suboptimal performances with EMG or EEG alone. This study provided a simple and efficient algorithm for prosthetics that assist patients with sensorimotor impairments.

Interfacial tension (IFTC-B) between CO2 and brine depends on chemical components in multiphase systems, intricately evolving with a change in temperature. In this study, we developed a convolutional neural network with a multibranch structure (MBCNN), which, in combination with a compiled data set containing measurement data of 1716 samples from 13 available literature sources at wide temperature and pressure ranges (273.15-473.15 K and 0-70 MPa), was used to quantitatively explore the correlation of various chemical components with IFTC-B at varying temperature, aiming to achieve accurate predictions of IFTC-B under complex conditions. Our multibranch neural network analysis yielded some important insights: (1) Leveraging the convolutional and multibranch structure, MBCNN effectively mitigates the adverse effects of sparse matrices resulting from the absence of certain basic components, exhibiting higher prediction accuracy particularly for low IFTC-B scenarios (MAE = 0.47, and R2 = 0.9921) than other AI models. (2) The multibranch structure allows MBCNN to additionally capture the interattribute relationship between temperature and each chemical component. Such interattribute relationships are quantitatively correlated with IFTC-B, demonstrating that varying temperature significantly influences the dependence of IFTC-B on chemical components in gas and brine by causing the variation in their solubility. Specifically, the ratio of IFTC-B to the molality of monovalent cations (Na+ and K+) and bivalent cations (Ca2+ and Mg2+) in brine, as well as to the mole fraction of non-CO2 components (CH4 and N2) in the gas phase, varies with increasing temperature, approximately following a quadratic function. (3) By formulating the effect of each attribute on IFTC-B and quantifying their respective weight, we derived a new piecewise function for predicting IFTC-B at three temperature intervals (T ≤ 293.15 K, 293.15 K < T ≤ 324.4 K, and T > 324.4 K), with high prediction performance (MAE = 2.3672, R2 = 0.9263) across a wide temperature range in saline aquifers.

Osteoarthritis (OA), characterized by progressive degeneration of cartilage and reactive proliferation of subchondral bone, stands as a prevalent condition in orthopedic clinics. However, the precise mechanisms underlying OA pathogenesis remain inadequately explored.

In this study, Random Forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), and Support Vector Machine-Recursive Feature Elimination (SVM-RFE) machine learning techniques were employed to identify hub genes. Based on these hub genes, an Artificial Neural Network (ANN) diagnostic model was constructed. The Drug Signatures Database (DSigDB) was utilized to screen small-molecule drugs targeting these hub genes, and molecular docking analyses and molecular dynamics simulations were employed to explore and validate the binding interactions between proteins and small-molecule drugs. Expression changes of the hub genes under inflammatory conditions were validated through in vitro experiments, including RT-qPCR and Western blotting, and the therapeutic effects of the identified small-molecule drug on chondrocytes under inflammatory conditions were further verified in vitro. Lastly, Mendelian randomization analysis was conducted to examine the causal association between progesterone levels and various OA phenotypes.

In this study, we identified three hub genes: interleukin 1 receptor-associated kinase 3 (IRAK3), integrin subunit beta-like 1 (ITGBL1), and Ras homolog family member U (RHOU). An Artificial Neural Network (ANN) diagnostic model constructed based on these hub genes demonstrated excellent performance in both training and validation phases. Screening with the Drug Signatures Database (DSigDB) identified progesterone as a small-molecule drug targeting these key proteins. Molecular docking analysis using AutoDock Vina revealed that progesterone exhibited binding energies of ≤ -7 kcal/mol with each of the key proteins, indicating strong binding affinity. Furthermore, molecular dynamics simulations validated the stability and strength of these interactions. RT-qPCR and Western blotting confirmed the downregulation of the hub genes in IL-1β-treated chondrocytes. Western blotting also demonstrated the potential therapeutic effects of progesterone on IL-1β-treated chondrocytes. Finally, Mendelian randomization analysis established a significant association between progesterone levels and multiple OA phenotypes.

In our study, IRAK3, ITGBL1, and RHOU were identified as potential novel diagnostic and therapeutic targets for OA. Progesterone was preliminarily validated as a small-molecule drug with potential effects on OA. Further research is crucial to elucidate the pathogenesis of OA and the specific therapeutic mechanisms involved.

This study presents a novel methodology for optimizing the number of Raman spectra required per sample for human bone compositional analysis. The methodology integrates Artificial Neural Network (ANN) and Monte Carlo Simulation (MCS). We demonstrate the robustness of ANN in enabling prediction of Raman spectroscopy-based bone quality properties even with limited spectral inputs. The ANN algorithms tailored to individual sex and age groups, which enhance the specificity and accuracy of predictions in bone quality properties. In addition, ANN guided MCS systematically explores the variability and uncertainty inherent in different sample sizes and spectral datasets, leading to the identification of an optimal number of spectra per sample for characterizing human bone tissues. The findings suggest that as low as 2 spectra are sufficient for biochemical analysis of bone, with R2 values between real and predicted values of v1/PO4/Amide I and ∼I1670/I1640 ratios, ranging from 0.60 to 0.89. Our results also suggest that up to 8 spectra could be optimal when balancing other factors. This optimized approach streamlines experimental workflows, reduces data and acquisition costs. Additionally, our study highlights the potential for advancing Raman spectroscopy in bone research through the innovative integration of ANN-guided probabilistic modeling techniques. This research could significantly contribute to the broader landscape of bone quality analyses by establishing a precedent for optimizing the number of Raman spectra with sophisticated computational tools. It also sets a novel platform for future optimization studies in Raman spectroscopy applications in biomedical field.

Artificial neural network (ANN) models have been used in the past to model surface roughness in manufacturing processes. Specifically, different parameters influence surface roughness in fused filament fabrication (FFF) processes. In addition, the characteristics of the networks have a direct impact on the performance of the models. In this work, a study about the use of ANN to model surface roughness in FFF processes is presented. The main objective of the paper is discovering how key ANN parameters (specifically, the number of neurons, the training algorithm, and the percentage of training and validation datasets) affect the accuracy of surface roughness predictions. To address this question, 125 3D printing experiments were conducted changing orientation angle, layer height and printing temperature, and measuring average roughness Ra as response. A multilayer perceptron neural network model with backpropagation algorithm was used. The study evaluates the effect of three ANN parameters: (1) number of neurons in the hidden layer (4, 5, 6 or 7), (2) training algorithm (Levenberg-Marquardt, Resilient Backpropagation or Scaled Conjugate Gradient), and (3) data splitting ratios (70%-15%-15% vs. 55%-15%-30%). Mean Absolute Error (MAE) was used as the performance metric. The Resilient Backpropagation algorithm, 7 neurons, and using 55% of training data yielded the best predictive performance, minimizing the MAE. Additionally, the impact of the dataset size on prediction accuracy was analysed. It was observed that the performance of the ANN gets worse as the number of datasets is reduced, emphasizing the importance of having sufficient data. This study will help to select appropriate values for the printing parameters in FFF processes, as well as to define the characteristics of the ANN to be used to model surface roughness.

This study proposes a novel non-linear modelling approach to predict the dissolution profiles of extended-release tablets, by combining a full-factorial design, curve fitting to the dissolution profiles, and artificial neural networks (ANN), with linear regression methods, partial least squares (PLS) and multiple linear regression (MLR) as benchmarks. Hydroxypropylmethylcellulose (HPMC) and carboxymethylcellulose (CMC) grades, active pharmaceutical ingredient (API) lubrication, and compression force were chosen as DoE factors. The resulting batches were tested to obtain their corresponding dissolution profile, and a first-order dissolution equation was fitted to each profile. ANN, PLS and MLR were used to model and predict the tablet-specific constant k which then served to simulate dissolution profiles. This study demonstrates how non-linear methods, specifically ANN, outperform traditional linear models in predicting the complex interactions affecting drug release from extended-release formulations.

In this work, artificial neural network coupled with multi-objective genetic algorithm (ANN-NSGA-II) has been used to develop a model and optimize the conditions for the extracting of the Mentha longifolia (L.) L. plant. Input parameters were extraction temperature (40-70 °C), extraction time (4-10 h), and extract concentration (0.25-2 mg/mL) while total antioxidant status (TAS) and total oxidant status (TOS) values of extracts were output parameters. The mean absolute percentage error (MAPE) of selected ANN model was determined as 1.434% and 0.464% for TAS and TOS, respectively. The results showed that the optimum extraction conditions were as follows: extraction temperature of 54.260 °C, extraction time of 7.854 h, and extract concentration of 0.810 mg/mL. The biological activities and phenolic contents of the extract obtained under determined optimum extract conditions were determined. TAS and TOS values of extract were determined as 6.094 ± 0.033 mmol/L and 14.050 ± 0.063 µmol/L, respectively. Oxidative stress index (OSI) as 0.231 ± 0.002, total phenolic content (TPC) as 123.05 ± 1.70 mg/g and total flavonoid content (TFC) as 181.84 ± 1.97 mg/g. Anti- acetylcholinesterase value and anti-butyrylcholinesterase value of the extract was determined as 42.97 ± 0.87 and 60.52 ± 0.80 µg/mL, respectively. In addition, 11 phenolic compounds, namely acetohydroxamic acid, gallic acid, catechin hydrate, 4-hydroxybenzoic acid, caffeic acid, vanillic acid, syringic acid, 2-hydoxycinamic acid, quercetin, luteolin and kaempferol, were determined. It was observed that the extract of M. longifolia produced under optimum conditions exhibited strong biological activities. These results indicate that ANN coupled NSGA-II was an effective method for the optimization extraction conditions of M. longifolia.

The rapid development of urbanization has led to a continuous rise in number of elevators. This has led to elevator failures from time to time. At present, although there are some studies on elevator fault diagnosis, they are more or less limited by the lack of data to make the research more superficial. For such complex special equipment as elevator, it is difficult to obtain reliable and sufficient data to train the fault diagnosis model. To address this issue, this paper first establishes a numerical model of vertical vibration for elevators with three degrees of freedom. The obtained motion equations are then used as constraints to acquire simulated vibration data through PINNs. Next, the proposed e-RGCN is employed for elevator fault diagnosis. Finally, experimental validation shows that the fault diagnosis accuracy with the participation of digital twins exceeds 90%, and the accuracy of the proposed model reaches 96.61%, significantly higher than that of other comparative models.

One of the prominent challenges in breast cancer (BC) treatment is human epidermal growth factor receptor (EGFR) overexpression, which facilitates tumor proliferation and presents a viable target for anticancer therapies. This study integrates multiomics data to pinpoint promising therapeutic compounds and employs a machine learning (ML)-based similarity search to identify effective alternatives. We used BC cell line data from the Cancer Cell Line Encyclopedia (CCLE) and Genomics of Drug Sensitivity in Cancer (GDSC) databases and single-cell RNA sequencing (scRNA-seq) information that established afatinib as an efficacious candidate demonstrating superior IC50 values. Next, ML models, including support vector machine (SVM), artificial neural networks (ANN), and random forest (RF), were trained on ChEMBL data to classify compounds with similar activity to the reference drug as active or inactive. The promising candidates underwent computational structural biology assessments for their molecular interactions and conformational dynamics. Our findings indicate that compounds ChEMBL233324, ChEMBL233325, ChEMBL234580, and ChEMBL372692 exhibit potent repressive action against EGFR, underscoring their potential as active antibreast cancer agents.

Daphne genkwa (D. genkwa) is the dried flower buds of a Chinese medicinal plant with multiple biological activities. Response surface methodology (RSM) combined with artificial neural network (ANN) techniques were utilized to optimize ultrasound-assisted extraction conditions for D. genkwa. Antioxidant activity and anti-inflammatory and analgesic properties of total flavonoids from D. genkwa (TFDG) were assessed. Optimal conditions involving ultrasonic power of 225 W, 30 min extraction time, 30 mL/g liquid-solid ratio, 60 °C extraction temperature, and 70% ethanol concentration yielded a maximum total flavonoids content (TFC) of 5.41 mg/g. After microporous resin purification, four specific flavonoids in D. genkwa were identified and quantified using high-performance liquid chromatography (HPLC). The TFDG demonstrated potent antioxidant activity, with a 94% rate of scavenging the 2, 2-diphenyl-1-picrylhydrazyl (DPPH). Furthermore, TFDG exhibited pain-alleviating properties in hot plate and acetic acid-induced writhing tests and noteworthy inhibitory effects on xylene-induced ear swelling in mice. The total flavonoids extracted by ultrasound had excellent biological activity. This establishes a foundation for further investigation into the potential medical value of D. genkwa.

Psychiatric disorders present diagnostic challenges due to individuals concealing their genuine emotions, and traditional methods relying on neurophysiological signals have limitations. Our study proposes an improved EEG-based diagnostic model employing Deep Learning (DL) techniques to address this. By experimenting with DL models on EEG data, we aimed to enhance psychiatric disorder diagnosis, offering promising implications for medical advancements. We utilized a dataset of 945 individuals, including 850 patients and 95 healthy subjects, focusing on six main and nine specific disorders. Quantitative EEG data were analyzed during resting states, featuring power spectral density (PSD) and functional connectivity (FC) across various frequency bands. Employing artificial neural networks (ANN), K nearest neighbors (KNN), Long short-term memory (LSTM), bidirectional Long short-term memory (Bi LSTM), and a hybrid CNN-LSTM model, we performed binary classification. Remarkably, all proposed models outperformed previous approaches, with the ANN achieving 96.83 % accuracy for obsessive-compulsive disorder using entire band features. CNN-LSTM attained the same accuracy for adjustment disorder, while KNN and LSTM achieved 98.94 % accuracy for acute stress disorder using specific feature sets. Notably, KNN and Bi-LSTM models reached 97.88 % accuracy for predicting obsessive-compulsive disorder. These findings underscore the potential of EEG as a cost-effective and accessible diagnostic tool for psychiatric disorders, complementing traditional methods like MRI. Our study's advanced DL models show promise in enhancing psychiatric disorder detection and monitoring, with significant implications for clinical application, inspiring hope for improved patient care and outcomes. The potential of EEG as a diagnostic tool for psychiatric disorders is substantial, as it can lead to improved patient care and outcomes in the field of psychiatry.

To explore the differences and associations of hypoxic parameters among distinct types of respiratory events in patients with obstructive sleep apnea (OSA) and to construct prediction models for the types of respiratory events based on hypoxic parameters.

A retrospective analysis was conducted on a cohort of 67 patients with polysomnography (PSG). All overnight recorded respiratory events with pulse oxygen saturation (SpO2) desaturation were categorized into four categories: hypopnea (Hyp, 3409 events), obstructive apnea (OA, 5561 events), central apnea (CA, 1110 events) and mixed apnea (MA, 1372 events). All event recordings were exported separately from the PSG software as comma-separated variable (.csv) files, which were imported into custom-built MATLAB software for analysis. Based on 13 hypoxic parameters, artificial neural network (ANN) and binary logistic regression (BLR) were separately used for construction of Hyp, OA, CA and MA models. Receiver operating characteristic (ROC) curves were employed to compare the various predictive indicators of the two models for different respiratory event types, respectively.

Both ANN and BLR models suggested that 13 hypoxic parameters significantly influenced the classification of respiratory event types; The area under the ROC curves of the ANN models surpassed those of traditional BLR models respiratory event types.

The ANN models constructed based on the 13 hypoxic parameters exhibited superior predictive capabilities for distinct types of respiratory events, providing a feasible new tool for automatic identification of respiratory event types using sleep SpO2.

Stroke is a significant global health concern, ranking as the second leading cause of death and placing a substantial financial burden on healthcare systems, particularly in low- and middle-income countries. Timely evaluation of stroke severity is crucial for predicting clinical outcomes, with standard assessment tools being the Rapid Arterial Occlusion Evaluation (RACE) and the National Institutes of Health Stroke Scale (NIHSS). This study aims to utilize Machine Learning (ML) algorithms to predict stroke severity using these two distinct scales.

We conducted this study using two datasets collected from hospitals in Urmia, Iran, corresponding to stroke severity assessments based on RACE and NIHSS. Seven ML algorithms were applied, including K-Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), Adaptive Boosting (AdaBoost), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), and Artificial Neural Network (ANN). Hyperparameter tuning was performed using grid search to optimize model performance, and SHapley Additive Explanations (SHAP) were used to interpret the contribution of individual features.

Among the models, the RF achieved the highest performance, with accuracies of 92.68% for the RACE dataset and 91.19% for the NIHSS dataset. The Area Under the Curve (AUC) was 92.02% and 97.86% for the RACE and NIHSS datasets, respectively. The SHAP analysis identified triglyceride levels, length of hospital stay, and age as critical predictors of stroke severity.

This study is the first to apply ML models to the RACE and NIHSS scales for predicting stroke severity. The use of SHAP enhances the interpretability of the models, increasing clinicians' trust in these ML algorithms. The best-performing ML model can be a valuable tool for assisting medical professionals in predicting stroke severity in clinical settings.

The cast in-situ pile is a widely used type of deep foundations which its execution in civil projects is increasing daily. The use of ordinary concrete in this type of piles causes technical and executive problems, a decrease in the compressive strength (CS) of concrete, and an increase in the permeability under the ground level. But use of the self-compacting concrete in the cast in-situ piles while increasing the CS of concrete ensures proper compaction, increase in the execution speed, and easy placing of concrete. In this article, utilizing the data obtained from the laboratory results and also the application of soft computing techniques, predicting the degree of CS of self-compacting concrete (SCC) in concrete piles was investigated. To estimate the CS of SCC, a total number of 7 inputs were implemented. Then, using gene expression programming (GEP) a model was presented for estimating the CS of SCC in the cast in-situ piles. The results of the neural network showed a precision of 99.98% which exhibits the high accuracy of the model. The use of this model could greatly help persons, companies, and research centers in the preparation and construction of self-compacting concrete with the desired CS.

Spinal cord injury (SCI) often leads to central neuropathic pain, a condition associated with significant morbidity and is challenging in terms of the clinical management. Despite extensive efforts, identifying effective biomarkers for neuropathic pain remains elusive. Here we propose a novel approach combining matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) with artificial neural networks (ANNs) to discriminate between mass spectral profiles associated with chronic neuropathic pain induced by SCI in female mice. Functional evaluations revealed persistent chronic neuropathic pain following mild SCI as well as minor locomotor disruptions, confirming the value of collecting serum samples. Mass spectra analysis revealed distinct profiles between chronic SCI and sham controls. On applying ANNs, 100% success was achieved in distinguishing between the two groups through the intensities of m/z peaks. Additionally, the ANNs also successfully discriminated between chronic and acute SCI phases. When reflexive pain response data was integrated with mass spectra, there was no improvement in the classification. These findings offer insights into neuropathic pain pathophysiology and underscore the potential of MALDI-TOF MS coupled with ANNs as a diagnostic tool for chronic neuropathic pain, potentially guiding attempts to discover biomarkers and develop treatments.

In the realm of dynamic system analysis, the Kalman filter and the alpha-beta filter are widely recognized for their tracking and prediction capabilities. However, their performance is often limited by static parameters that cannot adapt to changing conditions. Addressing this limitation, this paper introduces innovative neural network-based prediction models that enhance the adaptability and accuracy of these conventional filters. Our approach involves the integration of neural networks within the filtering algorithms, enabling the dynamic augmentation of parameters in response to performance feedback. We present two modified filters: a neural network-based Kalman filter and an alpha-beta filter, each augmented to incorporate neural network-driven parameter tuning. The alpha-beta filter is enhanced with neural network outputs for its α and β parameters, while the Kalman filter employs a neural network to optimize its internal parameter R and noise factor F. We assess these advanced models using the root mean square error (RMSE) metric, where our neural network-based alpha-beta filter demonstrates a significant 38.2% improvement in prediction accuracy, and the neural network-based Kalman filter achieves a 53.4% enhancement. Hence, our novel approach of integrating neural networks into filtering algorithms stands out as an effective strategy to significantly enhance their performance in dynamic environments.

Deep eutectic solvents (DESs) are popular green media used for various industrial, pharmaceutical, and biomedical applications. However, the possible compositions of eutectic systems are so numerous that it is impossible to study all of them experimentally. To remedy this limitation, the solubility landscape of selected active pharmaceutical ingredients (APIs) in choline chloride- and betaine-based deep eutectic solvents was explored using theoretical models based on machine learning. The available solubility data for the selected APIs, comprising a total of 8014 data points, were collected for the available neat solvents, binary solvent mixtures, and DESs. This set was augmented with new measurements for the popular sulfa drugs in dry DESs. The descriptors used in the machine learning protocol were obtained from the σ-profiles of the considered molecules computed within the COSMO-RS framework. A combination of six sets of descriptors and 36 regressors were tested. Taking into account both accuracy and generalization, it was concluded that the best regressor is nuSVR regressor-based predictive models trained using the relative intermolecular interactions and a twelve-step averaged simplification of the relative σ-profiles.

Simultaneous determination of atenolol (ATN), losartan potassium (LOS), and hydrochlorothiazide (HCZ) in presence of HCZ impurity B was conducted by chemometric approaches and radial basis function network (RBFN) using UV-spectrophotometry without preliminary separation. Three chemometric models namely, classical least-squares (CLS), principal component regression (PCR), and partial least-squares (PLS) along with RBFN were utilized using the ternary mixtures of the three drugs. The multivariate calibrations were obtained by measuring the zero-order absorbance of the mixtures from 250 to 270 nm at the interval of 0.2 nm. The models were built covering the concentration range of (4.0 to 20.0), (3.8 to 20.2), and (0.9 to 50.1) μg mL-1 for ATN, LOS, and HCZ, respectively. The regression coefficient was calculated between the actual and predicted concentrations of the 3 drugs using CLS, PCR, PLS and RBFN. The accuracy of the developed models was evaluated using the root mean square error of prediction (RMSEP) giving satisfactory results. The proposed methods were simple, accurate, precise and were applied efficiently for the quantitation of the three components in laboratory-prepared mixtures, and in dosage form showing good recovery values. In addition, the obtained results were compared statistically with each other using ANOVA test showing non-significant difference between them.

Chronic obstructive pulmonary disease (COPD) is a severe condition affecting millions worldwide, leading to numerous annual deaths. The absence of significant symptoms in its early stages promotes high underdiagnosis rates for the affected people. Besides pulmonary function failure, another harmful problem of COPD is the systemic effects, e.g., heart failure or voice distortion. However, the systemic effects of COPD might provide valuable information for early detection. In other words, symptoms caused by systemic effects could be helpful to detect the condition in its early stages.

The proposed study aims to explore whether the voice features extracted from the vowel "a" utterance carry any information that can be predictive of COPD by employing Machine Learning (ML) on a newly collected voice dataset.

Forty-eight participants were recruited from the pool of research clinic visitors at Blekinge Institute of Technology (BTH) in Sweden between January 2022 and May 2023. A dataset consisting of 1246 recordings from 48 participants was gathered. The collection of voice recordings containing the vowel "a" utterance commenced following an information and consent meeting with each participant using the VoiceDiagnostic application. The collected voice data was subjected to silence segment removal, feature extraction of baseline acoustic features, and Mel Frequency Cepstrum Coefficients (MFCC). Sociodemographic data was also collected from the participants. Three ML models were investigated for the binary classification of COPD and healthy controls: Random Forest (RF), Support Vector Machine (SVM), and CatBoost (CB). A nested k-fold cross-validation approach was employed. Additionally, the hyperparameters were optimized using grid-search on each ML model. For best performance assessment, accuracy, F1-score, precision, and recall metrics were computed. Afterward, we further examined the best classifier by utilizing the Area Under the Curve (AUC), Average Precision (AP), and SHapley Additive exPlanations (SHAP) feature-importance measures.

The classifiers RF, SVM, and CB achieved a maximum accuracy of 77 %, 69 %, and 78 % on the test set and 93 %, 78 % and 97 % on the validation set, respectively. The CB classifier outperformed RF and SVM. After further investigation of the best-performing classifier, CB demonstrated the highest performance, producing an AUC of 82 % and AP of 76 %. In addition to age and gender, the mean values of baseline acoustic and MFCC features demonstrate high importance and deterministic characteristics for classification performance in both test and validation sets, though in varied order.

This study concludes that the utterance of vowel "a" recordings contain information that can be captured by the CatBoost classifier with high accuracy for the classification of COPD. Additionally, baseline acoustic and MFCC features, in conjunction with age and gender information, can be employed for classification purposes and benefit healthcare for decision support in COPD diagnosis.

NCT05897944.

This study systematically reviews the integration of artificial intelligence (AI) and remote sensing technologies to address the issue of crop water stress caused by rising global temperatures and climate change; in particular, it evaluates the effectiveness of various non-destructive remote sensing platforms (RGB, thermal imaging, and hyperspectral imaging) and AI techniques (machine learning, deep learning, ensemble methods, GAN, and XAI) in monitoring and predicting crop water stress. The analysis focuses on variability in precipitation due to climate change and explores how these technologies can be strategically combined under data-limited conditions to enhance agricultural productivity. Furthermore, this study is expected to contribute to improving sustainable agricultural practices and mitigating the negative impacts of climate change on crop yield and quality.

Climate change is a major concern for a range of environmental issues including water resources especially groundwater. Recent studies have reported significant impact of various climatic factors such as change in temperature, precipitation, evapotranspiration, etc. on different groundwater variables. For this, a range of tools and techniques are widely used in the literature including advanced machine learning (ML) and artificial intelligence (AI) approaches. To the best of the authors' knowledge, this review is one of the novel studies that offers an in-depth exploration of ML/AI models for evaluating climate change impact on groundwater variables. The study primarily focuses on the efficacy of various ML/AI models in forecasting critical groundwater parameters such as levels, discharge, storage, and quality under various climatic pressures like temperature and precipitation that influence these variables. A total of 65 research papers were selected for review from the year 2017-2023, providing an up-to-date exploration of the advancements in ML/AI methods for assessing the impact of climate change on various groundwater variables. It should be noted that the ML/AI model performance depends on the data attributes like data types, geospatial resolution, temporal scale etc. Moreover, depending on the research aim and objectives of the different studies along with the data availability, various sets of historical/observation data have been used in the reviewed studies Therefore, the reviewed studies considered these attributes for evaluating different ML/AI models. The results of the study highlight the exceptional ability of neural networks, random forest (RF), decision tree (DT), support vector machines (SVM) to perform exceptionally accurate in predicting water resource changes and identifying key determinants of groundwater level fluctuations. Additionally, the review emphasizes on the enhanced accuracy achieved through hybrid and ensemble ML approaches. In terms of Irish context, the study reveals significant climate change risks posing threats to groundwater quantity and quality along with limited research conducted in this avenue. Therefore, the findings of this review can be helpful for understanding the interplay between climate change and groundwater variables along with the details of the various tools and techniques including ML/AI approaches for assessing the impacts of climate changes on groundwater.

Recent studies have primarily focused on introducing novel frameworks to enhance the predictive power of toxicity prediction models by refining molecular representation methods and algorithms. However, these methods are inherently complex and often pose challenges in understanding and explaining, leading to barriers in their regulatory adoption and validation. Therefore, it is necessary to select the optimal model, considering not only model performance but also interpretability. This study aimed to identify the optimal combination of molecular fingerprints (pattern-based versus algorithm-based) and machine learning algorithms (simple versus complex) for developing explainable toxicity prediction models through an comprehensive investigation of the ToxCast/Tox21 bioassay data set. For 1092 ToxCast/Tox21 assays, five molecular fingerprints (MACCS, Morgan, RDKit, Layered, and Patterned) and six algorithms (MLP, GBT, Random Forest, kNN, Logistic Regression, and Naïve Bayes) were used to train the models. Results showed that 35 models revealed acceptable performance (F1 score or accuracy is 0.8 or higher). Among the combinations, either MACCS or Morgan, paired with Random Forest, demonstrated robust performance compared with other molecular fingerprints and algorithms. MACCS and Random Forest are valuable, even when prioritizing interpretability. Consequently, the MACCS-Random Forest combination model based on four assays, targeting G protein-coupled receptor and kinase, were identified and they can be used to discern specific structural features or patterns in chemical compounds, offering explainable insights into toxicity-related chemical structures. This study indicates the importance of not disregarding the utilization of simple models when assessing both predictivity and interpretability within the context of chemical feature-based Tox21 data analysis.

In the era of the blue bio-economy, which promotes the sustainable utilization and exploitation of marine resources for economic growth and development, the fisheries and aquaculture industries still face huge sustainability issues. One of the major challenges of these industries is associated with the generation and management of wastes, which pose a serious threat to human health and the environment if not properly treated. In the best-case scenario, fishery and aquaculture waste is processed into low-value commodities such as fishmeal and fish oil. However, this renewable organic biomass contains a number of highly valuable bioproducts, including enzymes, bioactive peptides, as well as functional proteins and polysaccharides. Marine-derived enzymes are known to have unique physical, chemical and catalytic characteristics and are reported to be superior to those from plant and animal origins. Moreover, it has been established that enzymes from marine species possess cold-adapted properties, which makes them interesting from technological, economic and sustainability points of view. Therefore, this review centers around enzymes from fishery and aquaculture waste, with a special focus on proteases, lipases, carbohydrases, chitinases and transglutaminases. Additionally, the use of fishery and aquaculture waste as a substrate for the production of industrially relevant microbial enzymes is discussed. The application of emerging technologies (i.e., artificial intelligence and machine learning) in microbial enzyme production is also presented.

Recent studies reveal that around 1.9 million stillbirths occur annually worldwide, with Sub-Saharan Africa having among the highest cases. Some Sub-Saharan African countries, including Ghana, failed to meet Millennium Development Goal 5 (MDG5) by 2015 and may struggle to meet Sustainable Development Goal 3 (SDG3) despite maternal healthcare interventions. Concerns arise about Ghana's ability to achieve the World Health Organization's neonatal mortality goal of 12 per 1000 live births by 2030. This study aims to identify key factors influencing childbirth outcomes and create a predictive method for high-risk pregnancies.

We compared four machine learning classifiers (Extreme Gradient Boosting, Random Forest, Logistic Regression, and Artificial Neural Network) in predicting childbirth outcomes using data from a tertiary health facility in Ghana. To address class imbalance, we employed the Synthetic Minority Over-sampling Technique (SMOTE).

Our findings show that fetal heartbeat, gestation age at birth are the most influential factors on birth outcome (stillbirth or live birth), while there is no significant association with maternal age, number of babies, and type of delivery method. Among the machine learning models considered, Random Forest emerged as the optimal model achieving an accuracy, F1-score, and AUC values of approximately 0.98, 0.99, and 0.90 respectively.

Our study identifies key factors affecting childbirth outcomes and highlights the potential of machine learning for early high-risk pregnancy detection in clinical settings. These findings are crucial for Ghana and other Sub-Saharan African countries striving to meet maternal and neonatal healthcare goals. Further research and policy initiatives can use these results to improve healthcare in the region and work toward the World Health Organization's objectives by 2030.

A prediction model based on XGBoost is proposed for ultrasonic degradation of micropollutants' kinetic constants. After parameter optimization through iteration, the model achieves Evaluation metrics with R2 and SMAPE reaching 0.99 and 2.06%, respectively. The impact of design parameters on predicting kinetic constants for ultrasound degradation of trace pollutants was assessed using Shapley additive explanations (SHAP). Results indicate that power density and frequency significantly impact the predictive performance. The database was sorted based on power density and frequency values. Subsequently, 800 raw data were split into small databases of 200 each. After confirming that reducing the database size doesn't affect prediction accuracy, ultrasound degradation experiments were conducted for five pollutants, yielding experimental data. A small database with experimental conditions within the numerical range was selected. Data meeting both feature conditions were filtered, resulting in an optimized 60-data group. After incorporating experimental data, a model was trained for prediction. Degradation kinetic constants for experiments (kE) were compared with predicted constants (for 800 data-based model: kP-800 and for 60 data-based model: kP-60). Results showed ibuprofen, bisphenol A, carbamazepine, and 17β-Estradiol performed better on the 60-data group (kP-60/kE: 1.00, 0.99, 1.00, 1.00), while caffeine suited the model trained on the 800-data group (kP-800/kE: 1.02).

In recent years, the emergence of numerous applications of artificial intelligence (AI) has sparked a new technological revolution. These applications include facial recognition, autonomous driving, intelligent robotics, and image restoration. However, the data processing and storage procedures in the conventional von Neumann architecture are discrete, which leads to the "memory wall" problem. As a result, such architecture is incompatible with AI requirements for efficient and sustainable processing. Exploring new computing architectures and material bases is therefore imperative. Inspired by neurobiological systems, in-memory and in-sensor computing techniques provide a new means of overcoming the limitations inherent in the von Neumann architecture. The basis of neural morphological computation is a crossbar array of high-density, high-efficiency non-volatile memory devices. Among the numerous candidate memory devices, ferroelectric memory devices with non-volatile polarization states, low power consumption and strong endurance are expected to be ideal candidates for neuromorphic computing. Further research on the complementary metal-oxide-semiconductor (CMOS) compatibility for these devices is underway and has yielded favorable results. Herein, we first introduce the development of ferroelectric materials as well as their mechanisms of polarization reversal and detail the applications of ferroelectric synaptic devices in artificial neural networks. Subsequently, we introduce the latest developments in ferroelectrics-based in-memory and in-sensor computing. Finally, we review recent works on hafnium-based ferroelectric memory devices with CMOS process compatibility and give a perspective for future developments.

Currently, artificial intelligence (AI), machine learning (ML), and deep learning (DL) are gaining increased interest in many fields, particularly in pharmaceutical research and development, where they assist in decision-making in complex situations. Numerous research studies and advancements have demonstrated how these computational technologies are used in various pharmaceutical research and development aspects, including drug discovery, personalized medicine, drug formulation, optimization, predictions, drug interactions, pharmacokinetics/ pharmacodynamics, quality control/quality assurance, and manufacturing processes. Using advanced modeling techniques, these computational technologies can enhance efficiency and accuracy, handle complex data, and facilitate novel discoveries within minutes. Furthermore, these technologies offer several advantages over conventional statistics. They allow for pattern recognition from complex datasets, and the models, typically developed from data-driven algorithms, can predict a given outcome (model output) from a set of features (model inputs). Additionally, this review discusses emerging trends and provides perspectives on the application of AI with quality by design (QbD) and the future role of AI in this field. Ethical and regulatory considerations associated with integrating AI into pharmaceutical technology were also examined. This review aims to offer insights to researchers, professionals, and others on the current state of AI applications in pharmaceutical research and development and their potential role in the future of research and the era of pharmaceutical Industry 4.0 and 5.0.

Accurately predicting the Modulus of Resilience (MR) of subgrade soils, which exhibit non-linear stress-strain behaviors, is crucial for effective soil assessment. Traditional laboratory techniques for determining MR are often costly and time-consuming. This study explores the efficacy of Genetic Programming (GEP), Multi-Expression Programming (MEP), and Artificial Neural Networks (ANN) in forecasting MR using 2813 data records while considering six key parameters. Several Statistical assessments were utilized to evaluate model accuracy. The results indicate that the GEP model consistently outperforms MEP and ANN models, demonstrating the lowest error metrics and highest correlation indices (R2). During training, the GEP model achieved an R2 value of 0.996, surpassing the MEP (R2 = 0.97) and ANN (R2 = 0.95) models. Sensitivity and SHAP (SHapley Additive exPlanations) analysis were also performed to gain insights into input parameter significance. Sensitivity analysis revealed that confining stress (21.6%) and dry density (26.89%) are the most influential parameters in predicting MR. SHAP analysis corroborated these findings, highlighting the critical impact of these parameters on model predictions. This study underscores the reliability of GEP as a robust tool for precise MR prediction in subgrade soil applications, providing valuable insights into model performance and parameter significance across various machine-learning (ML) approaches.

Survival analysis is an integral part of medical statistics that is extensively utilized to establish prognostic indices for mortality or disease recurrence, assess treatment efficacy, and tailor effective treatment plans. The identification of prognostic biomarkers capable of predicting patient survival is a primary objective in the field of cancer research. With the recent integration of digital histology images into routine clinical practice, a plethora of Artificial Intelligence (AI)-based methods for digital pathology has emerged in scholarly literature, facilitating patient survival prediction. These methods have demonstrated remarkable proficiency in analyzing and interpreting whole slide images, yielding results comparable to those of expert pathologists. The complexity of AI-driven techniques is magnified by the distinctive characteristics of digital histology images, including their gigapixel size and diverse tissue appearances. Consequently, advanced patch-based methods are employed to effectively extract features that correlate with patient survival. These computational methods significantly enhance survival prediction accuracy and augment prognostic capabilities in cancer patients. The review discusses the methodologies employed in the literature, their performance metrics, ongoing challenges, and potential solutions for future advancements. This paper explains survival analysis and feature extraction methods for analyzing cancer patients. It also compiles essential acronyms related to cancer precision medicine. Furthermore, it is noteworthy that this is the inaugural review paper in the field. The target audience for this interdisciplinary review comprises AI practitioners, medical statisticians, and progressive oncologists who are enthusiastic about translating AI-driven solutions into clinical practice. We expect this comprehensive review article to guide future research directions in the field of cancer research.

In this work, neutron spectra are unfolded using artificial neural networks (ANNs). The neutron response of the NE213 scintillator detector, characterized by the pulse height distribution, is calculated to obtain the necessary data for unfolding the energy spectrum. This is achieved using both analytical response functions and response functions generated by the MCNPX-PHOTRACK code. In this query, the Levenberg-Marquardt method (LMM), which has a high computational speed in the learning method, is used to train the network. The performance of the ANN for unfolding the neutron energy spectrum of the NE213 scintillation detector was evaluated by comparing its results to the established Gravel method. The ANN method consistently produced spectra with a single peak closely matching the incident energy, while the Gravel method showed additional peaks and distortions. Quantitative analysis revealed a lower relative energy peak difference (indicating higher accuracy) for the ANN method compared to Gravel, particularly when noise was introduced into the data. These results suggest that ANNs offer a more robust and accurate approach for neutron spectrum unfolding.

This study aims to optimize and evaluate drug release kinetics of Modified-Release (MR) solid dosage form of Quetiapine Fumarate MR tablets by using the Artificial Neural Networks (ANNs). In training the neural network, the drug contents of Quetiapine Fumarate MR tablet such as Sodium Citrate, Eudragit® L100 55, Eudragit® L30 D55, Lactose Monohydrate, Dicalcium Phosphate (DCP), and Glyceryl Behenate were used as variable input data and Drug Substance Quetiapine Fumarate, Triethyl Citrate, and Magnesium Stearate were used as constant input data for the formulation of the tablet. The in-vitro dissolution profiles of Quetiapine Fumarate MR tablets at ten different time points were used as a target data. Several layers together build the neural network by connecting the input data with the output data via weights, these weights show importance of input nodes. The training process optimises the weights of the drug product excipients to achieve the desired drug release through the simulation process in MATLAB software. The percentage drug release of predicted formulation matched with the manufactured formulation using the similarity factor (f2), which evaluates network efficiency. The ANNs have enormous potential for rapidly optimizing pharmaceutical formulations with desirable performance characteristics.

Analysis of the change in groundwater used as a drinking and irrigation water source is of critical importance in terms of monitoring aquifers, planning water resources, energy production, combating climate change, and agricultural production. Therefore, it is necessary to model groundwater level (GWL) fluctuations to monitor and predict groundwater storage. Artificial intelligence-based models in water resource management have become prevalent due to their proven success in hydrological studies. This study proposed a hybrid model that combines the artificial neural network (ANN) and the artificial bee colony optimization (ABC) algorithm, along with the ensemble empirical mode decomposition (EEMD) and the local mean decomposition (LMD) techniques, to model groundwater levels in Erzurum province, Türkiye. GWL estimation results were evaluated with mean square error (MSE), coefficient of determination (R2), and residual sum of squares (RSS) and visually with violin, scatter, and time series plot. The study results indicated that the EEMD-ABC-ANN hybrid model was superior to other models in estimating GWL, with R2 values ranging from 0.91 to 0.99 and MSE values ranging from 0.004 to 0.07. It has also been revealed that promising GWL predictions can be made with previous GWL data.

As artificial intelligence technology gains widespread adoption in biomedicine, the exploration of integrating biofluidic Raman spectroscopy for enhanced disease diagnosis opens up new prospects for the practical application of Raman spectroscopy in clinical settings. However, for systemic lupus erythematosus (SLE), origin Raman spectral data (ORS) have relatively weak signals, making it challenging to obtain ideal classification results. Although the surface enhancement technique can enhance the scattering signal of Raman spectroscopic data, the sensitivity of the SERS substrate to airborne impurities and the inhomogeneous distribution of hotspots degrade part of the signal. To fully utilize both kinds of data, this paper proposes a two-branch residual-attention network (DBRAN) fusion technique, which allows the ORS to complement the degraded portion and thus improve the model's classification accuracy. The features are extracted using the residual module, which retains the original features while extracting the deep features. At the same time, the study incorporates the attention module in both the upper and lower branches to handle the weight allocation of the two modal features more efficiently. The experimental results demonstrate that both the low-level fusion method and the intermediate-level fusion method can significantly improve the diagnostic accuracy of SLE disease classification compared with a single modality, in which the intermediate-level fusion of DBRAN achieves 100% classification accuracy, sensitivity, and specificity. The accuracy is improved by 10% and 7% compared with the ORS unimodal and the SERS unimodal modalities, respectively. The experiment, by fusing the multimodal spectral, realized rapid diagnosis of SLE disease by fusing multimodal spectral data, which provides a reference idea in the field of Raman spectroscopy and can be further promoted to clinical practical applications in the future.

This study presents a method employing artificial neural networks (ANN) for automated interpretation and depth profiling of organic multilayers using a limited set of time-of-flight secondary ion mass spectrometry (ToF-SIMS) spectra. To overcome the challenges of acquiring massive data sets for OLEDs, training data was generated by combining existing ToF-SIMS data sets with mathematically generated spectra. The classification model achieved an impressive 99.9% accuracy in identifying the mixed layers of the OLED dyes. The study demonstrates the synergy of ToF-SIMS and ANN analysis for effective classification and depth profiling of the OLED layers, providing valuable insights for the development and optimization of organic electronic devices.