Pancreatic ductal adenocarcinoma (PDAC) is recognized as one of the most lethal malignancies, characterized by late-stage diagnosis and limited therapeutic options. Risk stratification has traditionally been performed using epidemiological studies and genetic analyses, through which key risk factors, including smoking, diabetes, chronic pancreatitis, and inherited predispositions, have been identified. However, the multifactorial nature of PDAC has often been insufficiently addressed by these methods, leading to limited precision in individualized risk assessments. Advances in artificial intelligence (AI) have been proposed as a transformative approach, allowing the integration of diverse datasets-spanning genetic, clinical, lifestyle, and imaging data into dynamic models capable of uncovering novel interactions and risk profiles. In this review, the evolution of PDAC risk stratification is explored, with classical epidemiological frameworks compared to AI-driven methodologies. Genetic insights, including genome-wide association studies and polygenic risk scores, are discussed, alongside AI models such as machine learning, radiomics, and deep learning. Strengths and limitations of these approaches are evaluated, with challenges in clinical translation, such as data scarcity, model interpretability, and external validation, addressed. Finally, future directions are proposed for combining classical and AI-driven methodologies to develop scalable, personalized predictive tools for PDAC, with the goal of improving early detection and patient outcomes.

Pancreatic ductal adenocarcinoma (PDAC) is frequently diagnosed in its late stages when treatment options are limited. Unlike other common cancers, there are no population-wide screening programmes for PDAC. Thus, early disease detection, although urgently needed, remains elusive. Individuals in certain high-risk groups are, however, offered screening or surveillance. Here we explore advances in understanding high-risk groups for PDAC and efforts to implement biomarker-driven detection of PDAC in these groups. We review current approaches to early detection biomarker development and the use of artificial intelligence as applied to electronic health records (EHRs) and social media. Finally, we address the cost-effectiveness of applying biomarker strategies for early detection of PDAC.

Accurate and fully automated pancreas segmentation is critical for advancing imaging biomarkers in early pancreatic cancer detection and for biomarker discovery in endocrine and exocrine pancreatic diseases. We developed and evaluated a deep learning (DL)-based convolutional neural network (CNN) for automated pancreas segmentation using the largest single-institution dataset to date (n = 3031 CTs). Ground truth segmentations were performed by radiologists, which were used to train a 3D nnU-Net model through five-fold cross-validation, generating an ensemble of top-performing models. To assess generalizability, the model was externally validated on the multi-institutional AbdomenCT-1K dataset (n = 585), for which volumetric segmentations were newly generated by expert radiologists and will be made publicly available. In the test subset (n = 452), the CNN achieved a mean Dice Similarity Coefficient (DSC) of 0.94 (SD 0.05), demonstrating high spatial concordance with radiologist-annotated volumes (Concordance Correlation Coefficient [CCC]: 0.95). On the AbdomenCT-1K dataset, the model achieved a DSC of 0.96 (SD 0.04) and a CCC of 0.98, confirming its robustness across diverse imaging conditions. The proposed DL model establishes new performance benchmarks for fully automated pancreas segmentation, offering a scalable and generalizable solution for large-scale imaging biomarker research and clinical translation.

The risk of pancreatic ductal adenocarcinoma (PDAC) is increased in patients with diabetes mellitus (DM), particularly in new-onset diabetes (NOD). This study aimed to analyze the effect of NOD on the outcomes of patients with PDAC after R0 resection.

PDAC patients from six centers in China undergoing R0 resection from 2015 to 2022 were included. Patients were categorized as long-term diabetes (LTD), NOD, or non-diabetes mellitus (non-DM) based on the timing of diagnosis relative to pancreatic resection. We compared the effects of diabetes status on perioperative and oncological outcomes of PDAC.

Of 1211 patients, 602 (49.7%), 127 (10.5%), and 482 (39.8%) were in the non-DM, LTD, and NOD groups, respectively. Patients with NOD suffered from higher rates of fatty pancreas and postoperative pancreatic fistula (POPF) (both P < 0.05). When compared with the non-DM group, the NOD group had worse median overall survival (OS) (24.6 vs. 29.4 months, P < 0.001) and recurrence-free survival (RFS) (13.3 vs. 15.8 months, P < 0.001); and the LTD group also had worse median OS (25.2 vs. 29.4 months, P = 0.041) and RFS (13.8 vs. 15.8 months, P = 0.007) compared with non-DM group. However, there were no significant differences in survival between the NOD and the LTD groups. Multivariate analysis indicated that NOD, LTD, largest tumor size, and poor tumor differentiation were independently associated with worse OS and RFS (all P < 0.05).

Patients with PDAC undergoing R0 resection experienced a higher probability of POPF in the presence of concurrent NOD. Long-term survival prognosis was worse in NOD or LTD patients than in non-DM patients.

New-Onset Diabetes Mellitus (NODM) is often an early manifestation of pancreatic cancer (Pancreatic Ductal Adenocarcinoma, PDAC). However, there is limited information about (1) the duration prior to PDAC diagnosis when the annual incidence of NODM starts significantly exceeding that in age-matched controls, (2) the percentage of PDAC patients diagnosed with NODM in the years preceding, and (3) the risk of PDAC following NODM in time when the PDAC risk is significantly higher than in controls.

Using the nationwide VA database, we evaluated the annual incidence of NODM for 15 years preceding the PDAC diagnosis and in the age- and sex-matched controls (1:5 matching). In the second part, we evaluated the long-term risk and predictors of PDAC in NODM patients and controls.

The case-control study comprised 8198 PDAC patients and 40,992 matched controls. The higher annual incidence of NODM in PDAC patients was statistically significant up to 15 years before PDAC diagnosis. 69.2% of PDAC patients had NODM in the preceding 15 years versus 38.0% of controls. PDAC risk in the 15 years following NODM was 0.60% compared to 0.13% in the controls (aHR 3.83, 95% CI 3.68-3.98, p < 0.001). The risk of PDAC is more pronounced in the 1 year following NODM (aHR 9.07, 95% CI 8.33-9.87) than the subsequent 5 years (aHR 2.98, 95% CI 2.82-3.15).

NODM pre-dates PDAC diagnosis in most patients with PDAC. Further evaluation of NODM patients for PDAC has the potential to become a feasible strategy for diagnosing more early-stage resectable PDACs.

Recent research suggests that new-onset diabetes mellitus (NODM) often results from pancreatic cancer (PC) rather than causing it. Determining if NODM is type 2 diabetes mellitus (T2DM) or PC-related NODM (NODM-PC) aids in the early diagnosis of PC. We developed a NODM-PC risk prediction model to stratify PC risk in patients with NODM.

This study utilized data from the UK Biobank, including 238 NODM-PC cases and 14,825 cancer-free T2DM controls. Polygenic risk scores (PRSs) for PC and T2DM were constructed using previously reported single nucleotide polymorphisms (SNPs) separately, while the NODM-PC PRS was developed by combining SNPs from both. Non-genetic factors were selected as candidate predictors based on prior NODM-PC prediction models. We developed three Cox models to estimate the risk of PC diagnosis within 3 years in the NODM population and evaluated them by internal-external cross-validation.

Elevated NODM-PC PRS and PC PRS scores positively correlated with NODM-PC risk, while T2DM PRS showed an inverse correlation. The NODM-PC PRS achieved the highest AUC at 0.719. Three Cox models were developed: Model 1 included age at T2DM diagnosis, smoking status, HbA1c, PC PRS, and T2DM PRS; Model 2 replaced PC and T2DM PRS with NODM-PC PRS; Model 3 included only non-genetic factors. Model 2 had the highest discrimination (Harrell's C-index 0.823 (95% CI: 0.806-0.840)), demonstrated the best clinical utility with good calibration, and showed significant classification improvement (continuous net reclassification index: 26.89% and 31.93% for cases, 28.51% and 30.90% for controls, compared to Models 1 and 3). The positive predictive value for the top 1% predicted risk in Model 2 was 13.25%.

This NODM-PC PRS enhances NODM-PC risk prediction, efficiently identifies individuals at high risk for PC screening, and improves PC screening efficiency at the population level among NODM individuals.

Pancreatic cancer (PC) is among the deadliest types of cancer globally. While early detection helps avert adverse outcomes, screening is only recommended for individuals at high risk, specifically those with familial and/or genetic predispositions. The objectives of this study are to systematically review primary studies on the cost-effectiveness of PC screening and to identify the critical factors that influence cost-effectiveness.

This systematic review was performed using PRISMA guidelines. Economic evaluation studies on PC screening were identified from searches on the SCOPUS and PubMed databases. The quality of reporting of the selected articles was assessed according to CHEERS 2022. Using predefined inclusion and exclusion criteria, two reviewers conducted the title-abstract review, full-text review, and data extraction to select relevant articles. The authors' consensus was used to settle disagreements. The primary outcome was the incremental cost-effectiveness ratio, measured by cost per quality-adjusted life year and cost per life year saved.

Nine studies were selected for the final review. Most studies demonstrated that one-time screening for PC among high-risk individuals was cost-effective compared with no screening, while others found annual screening to also be cost-effective. High-risk was generally defined as having a >5% lifetime risk of PC and included individuals with either familial pancreatic cancer (FPC) or genetic susceptibility syndromes such as Peutz-Jeghers Syndrome, hereditary pancreatitis, hereditary non-polypoid colorectal cancer syndrome, familial adenomatous polyposis, and BRCA2 mutations. Individuals with new-onset diabetes (NOD) were also considered high-risk. Screening using mainly endoscopic ultrasound was cost-effective among FPC individuals and those with genetic syndromes. Risk-based screening was also cost-effective among patients with NOD.

Screening for PC is cost-effective among selected high-risk individuals. However, cost-effectiveness depends on epidemiological factors, cost, the diagnostic performance of screening tools, and the overall design of studies.

Early detection of pancreatic cancer (PC) remains challenging largely due to the low population incidence and few known risk factors. However, screening in at-risk populations and detection of early cancer has the potential to significantly alter survival. In this study, we aim to develop a predictive model to identify patients at risk for developing new-onset PC at two and a half to three year time frame. We used the Electronic Health Records (EHR) of a large medical system from 2000 to 2021 (N = 537,410). The EHR data analyzed in this work consists of patients' demographic information, diagnosis records, and lab values, which are used to identify patients who were diagnosed with pancreatic cancer and the risk factors used in the machine learning algorithm for prediction. We identified 73 risk factors of pancreatic cancer with the Phenome-wide Association Study (PheWAS) on a matched case-control cohort. Based on them, we built a large-scale machine learning algorithm based on EHR. A temporally stratified validation based on patients not included in any stage of the training of the model was performed. This model showed an AUROC at 0.742 [0.727, 0.757] which was similar in both the general population and in a subset of the population who has had prior cross-sectional imaging. The rate of diagnosis of pancreatic cancer in those in the top 1 percentile of the risk score was 6 folds higher than the general population. Our model leverages data extracted from a 6-month window of time in the electronic health record to identify patients at nearly sixfold higher than baseline risk of developing pancreatic cancer 2.5-3 years from evaluation. This approach offers an opportunity to define an enriched population entirely based on static data, where current screening may be recommended.

Diabetic ketoacidosis (DKA), typically linked to type 1 diabetes or acute illness in type 2 diabetes, can rarely be triggered by pancreatic adenocarcinoma (PA). Though 80% of PA patients have glucose intolerance, DKA is exceptionally uncommon, with fewer than 20 documented cases. A 52-year-old woman with new-onset type 2 diabetes presented with altered mental status, abdominal pain, and 23 kg weight loss over 2 months. Labs confirmed DKA (glucose: 439 mg/dL, pH 7.1, ketonuria). Elevated tumor markers (CA19-9: >10,000 U/mL, CEA: 365 ng/mL) and imaging revealed a 4 cm pancreatic mass with metastases, biopsy-proven as PA. This case underscores PA as a rare but critical DKA precipitant in new-onset diabetes. Unexplained hyperglycemia, rapid weight loss, and markedly elevated tumor markers should prompt malignancy screening. Early multidisciplinary intervention may improve outcomes in this aggressive cancer. Clinicians must maintain high suspicion for occult PA in atypical DKA presentations.

Unexplained weight loss alongside newly-identified type 2 DM warrants thorough evaluation for occult malignancy. Elevated CA19-9 and CEA in the context of new-onset diabetes should raise suspicion for pancreatic malignancy. DKA may rarely serve as the initial manifestation of pancreatic cancer in newly-identified type 2 DM cases, necessitating a high index of clinical suspicion.

Pancreatic cancer is one of the most lethal neoplasms. Despite considerable research conducted in recent decades, not much has been achieved to improve its survival rate. That may stem from the lack of effective screening strategies in increased pancreatic cancer risk groups. One population that may be appropriate for screening is new-onset diabetes (NOD) patients. Such a conclusion stems from the fact that pancreatic cancer can cause diabetes several months before diagnosis. The most widely used screening tool for this population, the ENDPAC (Enriching New-Onset Diabetes for Pancreatic Cancer) model, has not achieved satisfactory results in validation trials. This provoked the first attempts at using artificial intelligence (AI) to create larger, multi-parameter models that could better identify the at-risk population, which would be suitable for screening. The results shown by the authors of these trials seem promising. Nonetheless, the number of publications is limited, and the downfalls of using AI are not well highlighted. This narrative review presents a summary of previous publications, recent advancements and feasible solutions for effective screening of patients with NOD for pancreatic cancer.

Patients with type 2 diabetes mellitus (T2DM) have higher pancreatic cancer (PC) risk. While aspirin has chemopreventive effects on digestive cancers, its effect on PC among patients with T2DM is unclear.

This retrospective cohort study identified newly diagnosed adult patients with T2DM in Hong Kong between 2001 and 2015 from a territory-wide healthcare registry. Exclusion criteria were history of PC, pancreatic cyst, IgG4 disease, or pancreatectomy. To address reverse causality between PC and T2DM, we excluded patients with PC diagnosed within 1 year of T2DM. We also excluded patients with less than 1 year of observation. Primary outcome was PC, and secondary outcomes were PC-related and all-cause mortality. Aspirin use was treated as time-varying variable (≥180 day-use/year) to address immortal-time bias, and multivariable Cox regression model was employed to derive adjusted HR (aHR). Propensity-score (PS) matching was used as secondary analysis.

Among 343 966 newly diagnosed patients with T2DM (median follow-up: 10.5 years; IQR: 7.7-14.5 years), 1224 (0.36%) developed PC. There were 51 151 (14.9%) deaths from any cause, and 787 (0.2%) died from PC. Aspirin use was associated with lower PC risk in both time-dependent (aHR: 0.58; 95% CI 0.49 to 0.69) and PS matching analysis (aHR: 0.61; 95% CI 0.48 to 0.77). An inverse relationship was observed with increasing dose and duration of aspirin use (P trend<0.001). Aspirin was also associated with a lower risk of PC-related mortality (aHR: 0.43; 95% CI 0.34 to 0.53) and all-cause mortality (aHR: 0.78; 95% CI 0.76 to 0.80).

Aspirin use may be an oncopreventive strategy to reduce PC risk in patients with T2DM. Further studies are warranted to validate the study findings.

Recurrent acute pancreatitis (RAP) is a complex syndrome that presents variably, with many cases remaining idiopathic after thorough diagnostics. For evaluating structural etiologies, endoscopic ultrasound and MR cholangiopancreatography are preferred over endoscopic retrograde cholangiopancreatography (ERCP) given their more favorable risk profile and sensitivity. The diagnostic work-up remains paramount since treatment should focus on addressing underlying causes such as early cholecystectomy for gallstone pancreatitis. As more etiologic factors are uncovered, such as genetic susceptibility, causality becomes more nuanced. Earlier enthusiasm for endoscopic sphincterotomy as a treatment for idiopathic RAP has been tempered by less favorable studies in recent years.

Pancreatic cancer, often diagnosed at advanced stages, has poor survival rates. Effective screening aims to detect the disease early, improving outcomes. Current guidelines recommend screening high-risk groups, including those with a family history or genetic predispositions, using methods like endoscopic ultrasound and MRI. The American Gastroenterological Association and other organizations advise annual surveillance for high-risk individuals, typically starting at the age of 50 or 10 years younger than the youngest affected relative. For certain genetic syndromes, such as Peutz-Jeghers syndrome or hereditary pancreatitis, screening may begin as early as the age of 35 to 40 years.

One percent of pancreatic adenocarcinoma (PDAC) patients are diagnosed with new onset diabetes (NOD) over the age of 50 years within 3 years. Therefore, NOD is a major factor for early diagnosis of PDAC. Research has focused on understanding the differences between NOD and type 2 diabetes, particularly in relation to PDAC. However, conflicting data exists regarding their impact on survival outcomes in PDAC patients. We performed this multi-center study to assess the prevalence and influence of NOD on clinical outcomes in patients with PDAC within a community-based hospital system.

We conducted a retrospective cohort study of 138 patients with biopsy-proven PDAC with localized/borderline disease (n=70), and metastatic disease (n=68) at three institutions from 2014 to 2021. NOD group consisted of pts diagnosed with diabetes [hemoglobin A1c (HbA1c) >6.5%] or pre-diabetes (HbA1c 5.7-6.4%) within the 3 years prior to PDAC diagnosis. Primary aim of the study was to determine the impact of NOD on clinical outcomes.

A total of 138 patients were included in the study, from which 30 met the criteria for NOD. No significant differences were noted in the demographic and clinical characteristics comparing patients based on NOD history. Comparing survival outcomes, NOD group was associated with worse overall survival (OS) in both the metastatic cohort [n=68, progression-free survival (PFS) 4.6 vs. 7.1 months, P=0.07; OS 7.1 vs. 13.2 months, P=0.01) and the resected cohort (n=40, PFS 8.4 vs. 19.3 months, P=0.04; OS 24.5 vs. 42.3 months, P=0.04). In multivariate analysis, the impact of NOD remained significant for OS and PFS in the resected cohort. Identifying common features amongst the NOD group, we found the entire cohort had a significant reduction in individual body mass index (BMI) 1 year prior to the NOD diagnosis (P=0.006).

NOD is associated with worse survival outcomes in patients with metastatic and resected PDAC. Reduction of BMI prior to diagnosis of NOD, warrants further investigation to be incorporated into the PDAC screening paradigm.

Pancreatic cancer (PC) is a leading cause of cancer mortality, often diagnosed at advanced stages. Acute pancreatitis (AP), particularly idiopathic cases, may serve as an early indicator of PC.

This multicenter cohort study investigated the incidence of PC before and after an AP episode, focusing on idiopathic AP and the role of pseudocysts as potential early markers for PC development.

We analyzed data from 2356 AP patients across 25 centers, with a median follow-up of 4.1 years (IQR: 1.6-6.8 years). Patients were categorized into 'PC before AP' and 'PC after AP' groups, and relative risk (RR) and adjusted odds ratios (OR) were calculated for idiopathic AP cases to quantify PC risk.

Among all cases, 69 patients (2.9 %) developed PC: 1.4 % (n = 34) before and 1.5 % (n = 35) after AP. Idiopathic AP cases had a fourfold higher risk of PC (OR = 4.46, [2.25-8.85]). Notably, pseudocysts were five times more prevalent in the PC group (14 %) compared to controls (3 %) (RR = 5.66; p < 0.01), often located at the tumor site. PC developed in 3 % of idiopathic AP cases versus 1.0 % in non-idiopathic cases. The median time to PC diagnosis post-AP was 373 days.

Idiopathic AP and pseudocyst formation significantly elevate the risk of PC, particularly within two years. These findings underscore the need for structured follow-up and early screening in idiopathic AP cases to improve PC detection and survival outcomes.

The integration of Artificial Intelligence (AI) in endoscopic ultrasound (EUS) represents a transformative advancement in the early detection and management of biliopancreatic lesions. This review highlights the current state of AI-enhanced EUS (AI-EUS) for diagnosing solid and cystic pancreatic lesions, as well as biliary diseases. AI-driven models, including machine learning (ML) and deep learning (DL), have shown significant improvements in diagnostic accuracy, particularly in distinguishing pancreatic ductal adenocarcinoma (PDAC) from benign conditions and in the characterization of pancreatic cystic neoplasms. Advanced algorithms, such as convolutional neural networks (CNNs), enable precise image analysis, real-time lesion classification, and integration with clinical and genomic data for personalized care. In biliary diseases, AI-assisted systems enhance bile duct visualization and streamline diagnostic workflows, minimizing operator dependency. Emerging applications, such as AI-guided EUS fine-needle aspiration (FNA) and biopsy (FNB), improve diagnostic yields while reducing errors. Despite these advancements, challenges remain, including data standardization, model interpretability, and ethical concerns regarding data privacy. Future developments aim to integrate multimodal imaging, real-time procedural support, and predictive analytics to further refine the diagnostic and therapeutic potential of AI-EUS. AI-driven innovation in EUS stands poised to revolutionize pancreatico-biliary diagnostics, facilitating earlier detection, enhancing precision, and paving the way for personalized medicine in gastrointestinal oncology and beyond.

Pancreatic Ductal Adenocarcinoma (PDAC) is a highly aggressive malignancy with limited survival due to late stage diagnosis and scarce therapeutic options. Emerging evidence highlights the role of the "exposome," which encompasses environmental, lifestyle, and metabolic exposures, as a crucial determinant in PDAC risk and a potential avenue for early detection. This review synthesizes findings on modifiable risk factors, including smoking, obesity, diabetes, diet, and alcohol consumption, and their interplay with genetic and metabolic profiles in PDAC development. Additionally, we explore cutting-edge approaches in exposomic research, such as biobanking, electronic health record analysis, and AI-driven predictive models, to identify early biomarkers and stratify high-risk populations. This integrated framework aims to inform prevention strategies and improve early detection of PDAC.

The lifetime risk of pancreatic cancer in women with a germline mutation in BRCA1 and BRCA2 is not well established. In an international prospective cohort of female carriers of BRCA1 and BRCA2 mutations, the cumulative incidence of pancreatic cancer from age 40 until 80 years was estimated.

A total of 8295 women with a BRCA1 or BRCA2 mutation were followed for new cases of pancreatic cancer. Subjects were followed from the date of baseline questionnaire or age 40 years (whichever came last) until a new diagnosis of pancreatic cancer, death from another cause, or date of last follow-up.

Thirty-four incident pancreatic cancer cases were identified in the cohort. The annual risk of pancreatic cancer between age 40 and 80 years was 0.04% for BRCA1 carriers and 0.09% for BRCA2 carriers. Via the Kaplan-Meier method, the cumulative incidence from age 40 to 80 years was 2.2% (95% CI, 1.1%-4.3%) for BRCA1 carriers and 2.7% (95% CI, 1.3%-5.4%) for BRCA2 carriers. Only two of the 34 cases reported a first-degree relative with pancreatic cancer (hazard ratio, 4.75; 95% CI, 1.13-19.9; p = .03). Risk factors for pancreatic cancer included alcohol intake and a history of diabetes. The 5-year survival rate for the 34 cases was 8.8%.

The lifetime risk of pancreatic cancer is approximately 2% in women with a BRCA1 mutation and 3% for women with a BRCA2 mutation. The poor survival in hereditary pancreatic cancer underscores the need for novel antitumoral strategies.

Pancreatic cancer is a highly aggressive malignancy with a profoundly poor prognosis. Clinically, the condition most frequently manifests with symptoms including painless jaundice, abdominal discomfort, and back pain. Early diagnosis and the implementation of effective therapeutic strategies are critical for improving patient survival outcomes. However, merely 10-20% of patients are diagnosed at an early stage, with the majority presenting at advanced stages, often with metastasis. Consequently, early detection and intervention are crucial for enhancing prognosis. The widespread adoption of endoscopic ultrasonography (EUS) technology in recent years has significantly enhanced the diagnostic accuracy for pancreatic space-occupying lesions. EUS is increasingly recognized for its pivotal role in alleviating malignant biliary obstruction (MBO), gastric outlet obstruction (GOO), and refractory pain in advanced pancreatic cancer. This article aims to provide an overall review of the current applications of EUS in the diagnosis and treatment of pancreatic cancer, exploring its advantages and limitations in early screening, diagnosis, and palliative care. Furthermore, this review explores potential future directions in the field, aiming to provide valuable insights to inform and enhance the clinical management of pancreatic cancer.

Pancreatic ductal adenocarcinoma (PDAC) is the third leading cause of cancer-related deaths in the United States, largely due to its poor five-year survival rate and frequent late-stage diagnosis. A significant barrier to early detection even in high-risk cohorts is that the pancreas often appears morphologically normal during the pre-diagnostic phase. Yet, the disease can progress rapidly from subclinical stages to widespread metastasis, undermining the effectiveness of screening. Recently, artificial intelligence (AI) applied to cross-sectional imaging has shown significant potential in identifying subtle, early-stage changes in pancreatic tissue that are often imperceptible to the human eye. Moreover, AI-driven imaging also aids in the discovery of prognostic and predictive biomarkers, essential for personalized treatment planning. This article uniquely integrates a critical discussion on AI's role in detecting visually occult PDAC on pre-diagnostic imaging, addresses challenges of model generalizability, and emphasizes solutions like standardized datasets and clinical workflows. By focusing on both technical advancements and practical implementation, this article provides a forward-thinking conceptual framework that bridges current gaps in AI-driven PDAC research.

Pancreatic cancer (PC) is a prevalent gastrointestinal tumour known for its high degree of malignancy, resulting in a mere 10% five-year survival rate for most patients. Over the past decade, a growing body of research has shed light on the intricate bidirectional association between PC and Type 2 diabetes (T2DM). The collection of PC- and T2DM-related articles is derived from two comprehensive databases, namely WOS (Web of Science Core Collection) and CNKI (China National Knowledge Infrastructure). This article discusses the last 10 years of research trends in PC and T2DM and explores their potential regulatory relationship as well as related medications.

Several studies suggest that new-onset diabetes mellitus is an early manifestation of pancreatic ductal adenocarcinoma (PDAC). Therefore, the International Cancer of the Pancreas Screening Consortium recommends glucose and hemoglobin A1c (HbA1c) monitoring in high-risk individuals (HRIs) undergoing surveillance. However, evidence that such monitoring improves PDAC detection is lacking. Our aim was to investigate the association between serum glucose and HbA1c values and the development of PDAC in HRIs undergoing surveillance.

Participants were recruited from the familial pancreatic cancer surveillance cohort, which follows hereditary predisposed HRIs yearly by magnetic resonance imaging and/or endoscopic ultrasound and blood sampling. Those who underwent fasting glucose and/or HbA1c monitoring at least once were eligible candidates.

Four hundred four HRIs met the inclusion criteria. During a median follow-up of 41 months (range 14-120), 9 individuals developed PDAC and 4 (without PDAC) were diagnosed with new-onset diabetes mellitus. Glucose levels ranged from 3.4 to 10.7 mmol/L (mean 5.6 ± 0.7) and HbA1c levels from 25 to 68 mmol/mol (mean 37.7 ± 4.1). The mean values did not differ significantly between PDAC cases and controls. The percentage of individuals with at least one elevated value were comparable between PDAC cases and controls for glucose (33% and 27%, P = 0.707) and HbA1c (22% and 14%, P = 0.623). No consistent glucose or HbA1c trends over time suggested a correlation with PDAC development.

In this HRI surveillance cohort, measuring glucose and HbA1c values did not contribute to PDAC detection. Larger and longer-term studies are needed to determine the final role of glucose and HbA1c monitoring in PDAC surveillance.

Pancreatic ductal adenocarcinoma (PDAC) is a highly lethal disease that is challenging to detect at an early stage. Biomarkers are needed that can detect PDAC early in the course of disease when interventions lead to the best outcomes. We highlight study design and statistical considerations that inform pancreatic cancer early detection biomarker evaluation.

We describe experimental design strategies in this setting useful for streamlining biomarker evaluation at each Early Detection Research Network (EDRN) phase of biomarker development. We break the early EDRN phases into sub-phases, proposing objectives, study design strategies, and biomarker performance benchmarks.

The goal of early detection in populations at high-risk of PDAC is described. Evaluating biomarker behavior in patients under surveillance without disease can winnow candidate biomarkers. Potential resources for biomarker validation studies are described.

Multisite and multidisciplinary collaboration can facilitate study design strategies in this lethal but low incidence disease and streamline the path from biomarker discovery to clinical use. Improvements in analytical and experimental design methods could help accelerate biomarker evaluation through the phases of biomarker development.

Pancreatic cancer (PC), a highly malignant cancer with a poor diagnosis, may be influenced by diet-related inflammation. This study examined the association between dietary inflammatory index (DII) scores and the incidence and prognosis of PC in Korea.

A total of 55 patients with PC were matched with 280 healthy controls (HCs) by age and sex. We also analyzed the combined effects of DII scores and fasting blood glucose (FBG) levels or smoking status on the risk of PC and performed a survival analysis using the Cox proportional hazards method.

The DII scores were higher in the patients with PC than those in HCs (odds ratio [OR] = 3.36, confidence interval [CI] = 1.16-9.73, p = 0.03), and the effect was larger in women (OR = 6.13, CI = 1.11-33.82, p = 0.04). A high DII score was jointly associated with FBG ≥ 126 mg/dL in raising PC risk [OR = 32.5, relative excess risk due to interaction/synergy (RERI/S) index = 24.2/4.34, p-interaction = 0.04], indicating a multiplicative interaction. A high DII score combined with ex/current smoker status increased PC risk through an additive interaction (RERI/S = 1.01/1.54, p-interaction = 0.76). However, DII scores did not influence disease-free survival.

The consumption of an anti-inflammatory diet, coupled with maintaining normal FBG levels and abstaining from smoking, may help reduce the risk of PC by mitigating pancreatic inflammation.

Disturbances in carbohydrate metabolism are suggested to be the early symptoms of pancreatic ductal adenocarcinoma (PDAC). The accumulated data suggests that endocrine function-related biomarkers may represent a breakthrough in the early detection of PDAC. Factors which may predispose one to the development of PDAC are insulin resistance and hyperinsulinemia. Elevated insulin levels induce the onset of carcinogenesis by altering the differentiation and function of islet cells through stimulating growth factors, including insulin-like growth factors (IGFs). Impaired β cell function, along with the impact of PDAC-released factors (e.g., adrenomedullin (ADM), IGF-1, and macrophage inhibitory factor (MIF) on pancreatic islets, may contribute to the induction of diabetes associated with PDAC. Recently, exosomes have attracted worldwide attention due to their role in varied features of cell function, particularly in cancer progression. Exosomes comprise of small extracellular vesicles produced by almost all cells. These vesicles contain a vast array of biomolecules, including proteins and microRNAs. Exosomes participate in cancer growth and promote angiogenesis. They promote tumorigenesis and metastasis, and are associated with the acquisition of cancer cells resistant to chemotherapy. Data have been accumulating recently on the role of exosomes in the rapid recognition, prognosis and potential therapy of pancreatic cancer.

A rise in blood glucose is an early warning sign of underlying pancreatic cancer (PC) and may be an indicator of genetic events in PC progression. However, there is still a lack of mechanistic research on pancreatic cancer-associated new-onset diabetes (PCAND). In the present study, we identified a gene SRI, which possesses a SNP with the potential to distinguish PCAND and Type 2 diabetes mellitus (T2DM), by machine learning on the basis of the UK Biobank database. In vitro and in vivo, sorcin overexpression induced pancreatic β-cell dysfunction. Sorcin can form a positive feedback loop with STAT3 to increase the transcription of serpin E1 and CCL5, which may directly induce β-cell dysfunction. In 88 biopsies, the expression of sorcin was elevated in PC tissues, especially in PCAND samples. Furthermore, plasma serpin E1 levels are higher in peripheral blood samples from PCAND patients than in those from T2DM patients. In conclusion, sorcin may be the key driver in PCAND, and further study on the sorcin-STAT3-serpin E1/CCL5 signaling axis may help us better understand the pathogenesis of PCAND and identify potential biomarkers.

A blood test that enables surveillance for early-stage pancreatic ductal adenocarcinoma (PDAC) is an urgent need. Independent laboratories have reported PDAC biomarkers that could improve biomarker performance over CA19-9 alone, but the performance of the previously reported biomarkers in combination is not known. Therefore, we conducted a coordinated case/control study across multiple laboratories using common sets of blinded training and validation samples (132 and 295 plasma samples, respectively) from PDAC patients and non-PDAC control subjects representing conditions under which surveillance occurs. We analyzed the training set to identify candidate biomarker combination panels using biomarkers across laboratories, and we applied the fixed panels to the validation set. The panels identified in the training set, CA19-9 with CA199.STRA, LRG1, TIMP-1, TGM2, THSP2, ANG, and MUC16.STRA, achieved consistent performance in the validation set. The panel of CA19-9 with the glycan biomarker CA199.STRA improved sensitivity from 0.44 with 0.98 specificity for CA19-9 alone to 0.71 with 0.98 specificity (p < 0.001, 1000-fold bootstrap). Similarly, CA19-9 combined with the protein biomarker LRG1 and CA199.STRA improved specificity from 0.16 with 0.94 sensitivity for CA19-9 to 0.65 with 0.89 sensitivity (p < 0.001, 1000-fold bootstrap). We further validated significantly improved performance using biomarker panels that did not include CA19-9. This study establishes the effectiveness of a coordinated study of previously discovered biomarkers and identified panels of those biomarkers that significantly increased the sensitivity and specificity of early-stage PDAC detection in a rigorous validation trial.

Individuals who develop new-onset diabetes have been identified as a high-risk cohort for pancreatic cancer (PC), exhibiting an incidence rate nearly 8 times higher than the general population. Hence, the targeted screening of this specific cohort presents a promising opportunity for early pancreatic cancer detection. We aimed to develop and validate a novel model capable of identifying high-risk individuals among those with new-onset diabetes.

Employing the UK Biobank cohort, we focused on those developing new-onset diabetes during follow-up. Genetic and clinical characteristics available at registration were considered as candidate predictors. We conducted univariate regression analysis to identify potential indicators and used a 5-fold cross-validation method to select optimal predictors for model development. Five machine learning algorithms were used for model development.

Among 12,735 patients with new-onset diabetes, 100 (0.8%) were diagnosed with PC within 2 years. The final model (area under the curve, 0.897; 95% confidence interval, 0.865-0.929) included 5 clinical predictors and 24 single nucleotide polymorphisms. Two threshold cut-offs were established: 1.28% and 5.26%. The recommended 1.28% cut-off, based on model performance, reduces definitive testing to 13% of the total population while capturing 76% of PC cases. The high-risk threshold is 5.26%. Utilizing this threshold, only 2% of the population needs definitive testing, capturing nearly half of PC cases.

We, for the first time, combined clinical and genetic data to develop and validate a model to determine the risk of pancreatic cancer in patients with new-onset diabetes using machine learning algorithms. By reducing the number of unnecessary tests while ensuring that a substantial proportion of high-risk patients are identified, this tool has the potential to improve patient outcomes and optimize healthcare sources.

The Enriching New-Onset Diabetes for Pancreatic Cancer (ENDPAC) model relies primarily on fasting glucose values. Health systems have increasingly shifted practice towards use of glycated hemoglobin (HbA1c) measurement. We modified the ENDPAC model using patients with new onset hyperglycemia.

Four cohorts of patients 50-84 years of age with HbA1c results ≥6.2-6.5 % in 2011-2018 were identified. A combine cohort was formed. A widened eligibility criterion was applied to form additional four individual cohorts and one combined cohort. The primary outcome was the diagnosis of pancreatic cancer within 3 years after the first elevated HbA1c testing. The performance of the modified ENDPAC model was evaluated by AUC, sensitivity, positive predictive value, cases detected, and total number of patients screened.

The individual and combined cohorts consisted of 39,001-79,060 and 69,334-92,818 patients, respectively (mean age 63.5-65.0 years). The three-year PC incidence rates were 0.47%-0.54 %. The AUC measures were in the range of 0.75-0.77 for the individual cohorts and 0.75 for the combined cohorts. When the four individual cohorts were combined, more PC cases can be identified (149 by the combined vs. 113-116 by individual cohorts when risk score was 5+). Performance measures were compromised in nonwhites. Asian and Pacific islanders had lower sensitivity compared to other racial and ethnic groups (29 % vs. 50-60 %) when risk score was 5+.

The modified ENDPAC model targets a broader population and thus identifies more high-risk patients for cancer screening. The differential performance needs to be considered when the model is applied to non-white population.

The incidence of pancreatic cancer is increasing, although globally it represents less than 3% of all cancers. Despite advances in medical and surgical management, survival rates have not significantly improved in recent years. Consequently, pancreatic cancer, though relatively uncommon, is the third leading cause of cancer-related deaths. This is primarily due to the disease´s late detection. Symptoms appear late and are nonspecific, and over 80% of cases are diagnosed at an advanced stage and unsuitable for curative surgery, resulting in a five-year survival rate below 10%. However, the exceptional cases that are diagnosed early show five-year survival rates exceeding 80%. Therefore, one of the keys to improving pancreatic cancer prognosis lies in early detection, making screening in high-risk individuals a potentially crucial strategy.

Pancreatic ductal adenocarcinoma (PDAC) continues to remain one of the leading causes of cancer-related death. Unlike other malignancies where universal screening is recommended, the same cannot be said for PDAC. The purpose of this study is to review which patients are at high risk of developing PDAC and therefore candidates for screening, methods/frequency of screening, and risk for these groups of patients.

Pancreatic ductal adenocarcinoma (PDAC) is a lethal malignancy characterised by late diagnosis and poor prognosis. Despite advancements, current diagnostic and prognostic strategies remain limited. Liquid biopsy techniques, including circulating tumour DNA (ctDNA), circulating tumour cells (CTCs), circulating tumour exosomes, and proteomics, offer potential solutions to improve PDAC diagnosis, prognostication, and management. A systematic search of Ovid MEDLINE identified studies published between 2019 and 2024, focusing on liquid biopsy biomarkers for PDAC. A total of 49 articles were included. ctDNA research shows some promise in diagnosing and prognosticating PDAC, especially through detecting mutant KRAS in minimal residual disease assays. CTC analyses had low sensitivity for early-stage PDAC and inconsistent prognostic results across subpopulations. Exosomal studies revealed diverse biomarkers with some diagnostic and prognostic potential. Proteomics, although relatively novel, has demonstrated superior accuracy in PDAC diagnosis, including early detection, and notable prognostic capacity. Proteomics combined with CA19-9 analysis has shown the most promising results to date. An update on multi-cancer early detection testing, given its significance for population screening, is also briefly discussed. Liquid biopsy techniques offer promising avenues for improving PDAC diagnosis, prognostication, and management. In particular, proteomics shows considerable potential, yet further research is needed to validate existing findings and comprehensively explore the proteome using an unbiased approach.

Changes in body composition and metabolic factors may serve as biomarkers for the early detection of pancreatic ductal adenocarcinoma (PDAC). The aim of this study was to capture the longitudinal changes in body composition and metabolic factors before diagnosis of PDAC.

We performed a retrospective cohort study in which all patients (≥18 years) diagnosed with PDAC from 2002 to 2021 were identified. We collected all abdominal computed tomography scans and 10 different blood-based biomarkers up to 36 months before diagnosis. We applied a fully automated abdominal segmentation algorithm previously developed by our group for 3-dimensional quantification of body composition on computed tomography scans. Longitudinal trends of body composition and blood-based biomarkers before PDAC diagnosis were estimated using linear mixed models, compared across different time windows, and visualized using spline regression.

We included 1690 patients in body composition analysis, of whom 516 (30.5%) had ≥2 prediagnostic computed tomography scans. For analysis of longitudinal trends of blood-based biomarkers, 3332 individuals were included. As an early manifestation of PDAC, we observed a significant decrease in visceral and subcutaneous adipose tissue (β = -1.94 [95% confidence interval (CI), -2.39 to -1.48] and β = -2.59 [95% CI, -3.17 to -2.02]) in area (cm2)/height (m2) per 6 months closer to diagnosis, accompanied by a decrease in serum lipids (eg, low-density lipoprotein [β = -2.83; 95% CI, -3.31 to -2.34], total cholesterol [β = -2.69; 95% CI, -3.18 to -2.20], and triglycerides [β = -1.86; 95% CI, -2.61 to -1.11]), and an increase in blood glucose levels. Loss of muscle tissue and bone volume was predominantly observed in the last 6 months before diagnosis.

This study identified significant alterations in a variety of soft tissue and metabolic markers that occur in the development of PDAC. Early recognition of these metabolic changes may provide an opportunity for early detection.