Liver cancer is one of the most prevalent malignant tumors worldwide, and its early detection and treatment are crucial for enhancing patient survival rates and quality of life. However, the early symptoms of liver cancer are often not obvious, resulting in a late-stage diagnosis in many patients, which significantly reduces the effectiveness of treatment. Developing a highly targeted, widely applicable, and practical risk prediction model for liver cancer is crucial for enhancing the early diagnosis and long-term survival rates among affected individuals.

To develop a liver cancer risk prediction model by employing machine learning techniques, and subsequently assess its performance.

In this study, a total of 550 patients were enrolled, with 190 hepatocellular carcinoma (HCC) and 195 cirrhosis patients serving as the training cohort, and 83 HCC and 82 cirrhosis patients forming the validation cohort. Logistic regression (LR), support vector machine (SVM), random forest (RF), and least absolute shrinkage and selection operator (LASSO) regression models were developed in the training cohort. Model performance was assessed in the validation cohort. Additionally, this study conducted a comparative evaluation of the diagnostic efficacy between the ASAP model and the model developed in this study using receiver operating characteristic curve, calibration curve, and decision curve analysis (DCA) to determine the optimal predictive model for assessing liver cancer risk.

Six variables including age, white blood cell, red blood cell, platelet counts, alpha-fetoprotein and protein induced by vitamin K absence or antagonist II levels were used to develop LR, SVM, RF, and LASSO regression models. The RF model exhibited superior discrimination, and the area under curve of the training and validation sets was 0.969 and 0.858, respectively. These values significantly surpassed those of the LR (0.850 and 0.827), SVM (0.860 and 0.803), LASSO regression (0.845 and 0.831), and ASAP (0.866 and 0.813) models. Furthermore, calibration and DCA indicated that the RF model exhibited robust calibration and clinical validity.

The RF model demonstrated excellent prediction capabilities for HCC and can facilitate early diagnosis of HCC in clinical practice.

Although methods in diagnosis and therapy of hepatocellular carcinoma (HCC) have made significant progress in the past decades, the overall survival (OS) of liver cancer is still disappointing. Machine learning models have several advantages over traditional cox models in prognostic prediction. This study aimed at designing an optimal panel and constructing an optimal machine learning model in predicting prognosis for HCC. A total of 941 HCC patients with completed survival data and preoperative clinical chemistry and immunology indicators from two medical centers were included. The OCC panel was designed by univariate and multivariate cox regression analysis. Subsequently, cox model and machine-learning models were established and assessed for predicting OS and PFS in discovery cohort and internal validation cohort. The best OCC model was validated in the external validation cohort and analyzed in different subgroups. In discovery, internal and external validation cohort, C-indexes of our optimal OCC model were 0.871 (95% CI, 0.863-0.878), 0.692 (95% CI, 0.667-0.717) and 0.648 (95% CI, 0.630-0.667), respectively; the 2-year AUCs of OCC model were 0.939 (95% CI, 0.920-0.959), 0.738 (95% CI, 0.667-0.809) and 0.725 (95% CI, 0.643-0.808), respectively. For subgroup analysis of HCC patients with HBV, aged less than 65, cirrhosis or resection as first therapy, C-indexes of our optimal OCC model were 0.772 (95% CI, 0.752-0.792), 0.769 (95% CI, 0.750-0.789), 0.855 (95% CI, 0.846-0.864) and 0.760 (95% CI, 0.741-0.778), respectively. In general, the optimal OCC model based on RSF algorithm shows prognostic guidance value in HCC patients undergoing individualized treatment.

Accurate prognosis is crucial for improving hepatocellular carcinoma (HCC) patients, clinical management, and outcomes post-liver resection. However, the lack of reliable prognostic indicators poses a significant challenge. This study aimed to develop a user-friendly nomogram to predict HCC patients' post-resection prognosis.

We retrospectively analyzed the data from 1091 HCC patients, randomly split into training (n=767) and validation (n=324) cohorts. Receiver operating characteristic (ROC) curves determined the optimal cut-off value for alpha1-microglobulin (α1MG) and Beta2-microglobulin (β2MG). Kaplan-Meier analysis assessed microglobulin's impact on survival, followed by Cox regression to identify prognostic factors and construct a nomogram. The predictive accuracy and discriminative ability of the nomogram were measured by the concordance index (C-index), calibration curves, area under the ROC curve (AUC), and decision curve analysis (DCA), and were compared with the BCLC staging system, Edmondson grade, or BCLC stage plus Edmondson grade.

Patients with high β2MG (≥2.395mg/L) had worse overall survival (OS). The nomogram integrated β2MG, BCLC stage, Edmondson grade, microvascular invasion (MVI), and serum carbohydrate antigen 199 (CA199) levels. C-index for training and validation cohorts (0.712 and 0.709) outperformed the BCLC stage (0.660 and 0.657), Edmondson grade (0.579 and 0.564), and the combination of BCLC stage with Edmondson grade (0.681 and 0.668), improving prognosis prediction. Calibration curves demonstrated good agreement between predicted and observed survival. AUC values exceeded 0.700 over time, highlighting the nomogram's discriminative ability. DCA revealed superior overall net income compared to other systems, emphasizing its clinical utility.

Our β2MG-based nomogram accurately predicts HCC patients' post-resection prognosis, aiding intervention and follow-up planning. Significantly, our nomogram surpasses existing prognostic indicators, including BCLC stage, Edmondson grade, and the combination of BCLC stage with Edmondson grade, by demonstrating superior predictive performance.

Dynamic changes in circulating immune-inflammatory cells have been regarded as simple and convenient prognostic biomarkers in various cancers. However, studies on the prognostic values of their ratios in oral squamous cell carcinoma (OSCC) remain limited.

A total of 493 OSCC patients were included in the present study. Here, we investigated the prognostic values of the neutrophil-to-lymphocyte ratio (NLR), lymphocyte-to-monocyte ratio (LMR), neutrophil-to-white blood cell ratio (NWR), and lymphocyte-to-white blood cell ratio (LWR) in OSCC. The correlations of the NLR, LMR, NWR, and LWR with clinicopathological characteristics were statistically analyzed using the Chi-square test, Kaplan-Meier curves, and univariate and multivariate Cox regression models.

Kaplan-Meier analyses revealed that OSCC patients with a high LMR and low NWR had prolonged overall survival (OS, P<0.001) and disease-free survival (DFS, P<0.001 and P=0.003, respectively), but there were no significant differences in metastasis-free survival (MFS, P=0.053 and P=0.052, respectively). In contrary, a high NLR and low LWR were associated with poor OS (P<0.001 and P=0.0016, respectively), DFS (P=0.0014 and 0.0012, respectively) and MFS (P=0.021 and 0.008, respectively). Additionally, Cox multivariate analyses showed that the LMR was an independent prognostic factor for both OS (P=0.007) and DFS (P=0.017), while the LWR was an independent prognostic factor for MFS (P=0.009).

Preoperative NLR, LMR, NWR, and LWR in the peripheral blood are significant prognostic factors for OSCC and might be helpful in predicting OSCC progression.