Clinical significance of risk factor analysis in pancreatic cancer by using supervised model of machine learning

Q: What is the main purpose of the study?

To identify clinically relevant predictors of pancreatic cancer using a supervised machine learning approach and to develop a risk stratification tool with diagnostic capabilities.

Q: How was the study designed and what data were used?

It used a retrospective matched case-control design from Tongji University’s Tenth People’s Hospital (2017–2023) with 353 cases and 370 matched controls. Demographic and hematological data were extracted from medical records.

Q: Which predictors were retained in the final model?

The final logistic regression model retained HbA1c, ALP, CA19-9, CEA, and BMI as independent predictors.

Sep 17, 2026

Uploaded by Clementine

Pancreatic cancer remains a major global health challenge because of aggressive biology, late-stage diagnosis, and persistently high mortality. This study used a supervised machine learning framework to identify clinically relevant predictors and to construct a risk stratification tool with diagnostic capability. A retrospective matched case-control design (2017–2023) included 353 cases and 370 matched controls. Key retained predictors were HbA1c, ALP, CA19-9, CEA, and BMI, and the model showed strong internal diagnostic performance (AUC 0.969).

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Introduction

Methods

Results

Conclusion

Keywords

TYPE Original Research PUBLISHED 26 May 2025 DOI 10.3389/fmed.2025.1551926 OPEN ACCESS EDITED BY Pengpeng Zhang, Nanjing Medical University, China REVIEWED BY Shuai Ren, Afﬁliated Hospital of Nanjing University of Chinese Medicine, China Vinod Kumar Yata, Malla Reddy University, India *CORRESPONDENCE Maoquan Li [cjr.limaoquan@vip.163.com](cjr.limaoquan@vip.163.com) RECEIVED 26 December 2024 ACCEPTED 22 April 2025 PUBLISHED 26 May 2025 CITATION Sherchan A, Jin F, Sherchan B, Mandal SK, Upadhaya Regmi B, Ghising R, Upadhaya SR, Gautam B, Pathak D and Li M (2025) Clinical signiﬁcance of risk factor analysis in pancreatic cancer by using supervised model of machine learning. Front. Med. 12:1551926 . doi: 10.3389/fmed.2025.1551926 COPYRIGHT © 2025 Sherchan, Jin, Sherchan, Mandal, Upadhaya Regmi, Ghising, Upadhaya, Gautam, Pathak and Li. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Clinical signiﬁcance of risk factor analysis in pancreatic cancer by using supervised model of machine learning Amir Sherchan1 , Feng Jin1 , Bhakti Sherchan2 , Sujit Kumar Mandal3 , Binit Upadhaya Regmi4 , Ranita Ghising2 , Sandesh Raj Upadhaya5 , Bishnu Gautam6 , Dipendra Pathak7 and Maoquan Li1* 1 Department of Interventional and Vascular Surgery, Shanghai Tenth People’s Hospital, School of Medicine, Tongji University, Shanghai, China, 2 Department of General Surgery, Scheer Memorial Adventist Hospital, Kavre, Nepal, 3 District Hospital, Doti, Nepal, 4 Patan Hospital, Patan Academy of Health Sciences, Kathmandu, Nepal, 5Trishuli Hospital, Nuwakot, Nepal, 6 Department of Radiology, Buddha International Hospital, Dang, Nepal, 7 Department of Radiology, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, China Introduction: Pancreatic cancer (PC) poses a signiﬁcant global health challenge due to its aggressive nature, late-stage diagnosis, and high mortality despite advancements in treatment. Early detection remains crucial for timely intervention. This study aimed to identify clinically relevant predictors of pancreatic cancer using a supervised machine learning approach and to develop a risk stratiﬁcation tool with diagnostic capabilities. Methods: A matched case-control study was conducted retrospectively atthe Tenth People’s Hospital of Tongji University (2017–2023), involving 353 cases and 370 matched controls. Demographic and hematological data were extracted from medical records. Variables were pre-selected using cluster dendrograms and subsequently reﬁned using logistic regression with backward elimination and Support Vector Machine (SVM) models. A ﬁnal risk scoring model was developed based on the best-performing model and internally validated. Results: Key predictors retained in the ﬁnal logistic regression model included Hemoglobin A1c (HbA1c) (OR 1.28; 95% CI: 1.08–1.52), Alkaline Phosphatase (ALP) (OR 1.02; 95% CI: 1.01–1.03), CA19-9 (OR 1.01; 95% CI: 1.01–1.01), Carcinoembryonic Antigen (CEA) (OR 1.41; 95% CI: 1.20–1.66), and Body Mass Index (BMI) (OR 0 . 88; 95% CI: 0 .81–0.97) . The ﬁnal model demonstrated excellent diagnostic performance (AUC = 0 .969, p < 0.001), with high accuracy, sensitivity, and speciﬁcity. A nomogram was constructed to facilitate individualized PC risk assessment. Conclusion: HbA1c, ALP, CA19-9, CEA, and BMI were independently associated with pancreatic cancer. The machine learning-derived risk scoring model demonstrated high predictive accuracy and may serve as a valuable clinical tool for early detection and screening of pancreati

FAQs

What is the main purpose of the study?

To identify clinically relevant predictors of pancreatic cancer using a supervised machine learning approach and to develop a risk stratification tool with diagnostic capabilities.

How was the study designed and what data were used?

It used a retrospective matched case-control design from Tongji University’s Tenth People’s Hospital (2017–2023) with 353 cases and 370 matched controls. Demographic and hematological data were extracted from medical records.

Which predictors were retained in the final model?

The final logistic regression model retained HbA1c, ALP, CA19-9, CEA, and BMI as independent predictors.

Sep 17, 2026

Uploaded by Clementine