Retrospective Study
Copyright ©The Author(s) 2025. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastrointest Oncol. May 15, 2025; 17(5): 102459
Published online May 15, 2025. doi: 10.4251/wjgo.v17.i5.102459
Development and validation of machine learning nomograms for predicting survival in stage IV pancreatic cancer: A retrospective study
Kun Huang, Zhu Chen, Xin-Zhu Yuan, Yun-Shen He, Xiang Lan, Chen-You Du
Kun Huang, Yun-Shen He, Department of General Surgery, Mianyang Hospital of Traditional Chinese Medicine, Mianyang 621000, Sichuan Province, China
Zhu Chen, Xiang Lan, Chen-You Du, Department of Hepatobiliary Surgery, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400000, China
Xin-Zhu Yuan, Department of Nephrology, The Second Clinical Medical Institution of North Sichuan Medical College (Nanchong Central Hospital) and Nanchong Key Laboratory of Basic Science & Clinical Research on Chronic Kidney Disease, Nanchong 637000, Sichuan Province, China
Co-first authors: Kun Huang and Zhu Chen.
Co-corresponding authors: Xiang Lan and Chen-You Du.
Author contributions: Huang K and Chen Z contributed equally to this work and share first authorship. Huang K and Chen Z designed the study, collected the data, and performed the primary data analysis. Yuan XZ and He YS assisted in data interpretation, statistical analysis, and manuscript drafting. All authors reviewed and approved the final manuscript and agreed to be accountable for all aspects of the research. Lan X ensured the accuracy and integrity of the work and also provided substantial input in refining the methodology and results. Du CY supervised the study and played a pivotal role in the conceptualization of the research. Du CY provided significant contributions to manuscript revisions and ensured that all research standards were adhered to during the study. Additionally, Du CY coordinated the overall project, reviewed critical data, and was responsible for the submission of the final version of the manuscript. Huang K and Chen Z made critical and indispensable contributions to the conception, design, and execution of the research, sharing the primary responsibility for data collection and analysis, which justifies their designation as co-first authors. Lan X and Du CY, as co-corresponding authors, both played an essential role in the conceptualization, data supervision, and final revisions of the manuscript, with Du CY specifically overseeing the study's overall progression and ensuring that the manuscript adhered to all academic and ethical standards.
Supported by Mianyang Health and Health Committee 2023 Scientific Research Project, No. 202309; Chengdu University of Traditional Chinese Medicine University-Hospital Joint Innovation Fund, No. LH202402010; and Mianyang Chinese Medicine Association 2024 Traditional Chinese Medicine Inheritance and Innovation Science and Technology Project, No. MYSZYYXH-202426.
Institutional review board statement: This study received ethical exemption from the Ethics Committee of Mianyang Hospital of Traditional Chinese Medicine, as it utilizes publicly available, de-identified patient data from the SEER database. The SEER database ensures patient anonymity and data protection, and therefore, informed consent was not required for this study. All analyses were conducted in strict accordance with SEER guidelines for ethical research use.
Informed consent statement: This study utilized data from the Surveillance, Epidemiology, and End Results (SEER) database, a publicly available resource that provides deidentified patient data. As all personal identifiers have been removed in the SEER database, there is no direct involvement with individual patients, and informed consent is not required for the use of this data
Conflict-of-interest statement: The authors declare that they have no conflicts of interest to disclose.
Data sharing statement: The data supporting the findings of this study are publicly available in the SEER database, maintained by the United States National Cancer Institute. Access to the SEER data is granted upon request to researchers who meet the criteria for access to confidential data, and the data can be obtained through SEER*Stat software version 8.3.9. Details on SEER data access are available at https://seer.cancer.gov/.
Open Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Xiang Lan, MD, Professor, Department of Hepatobiliary Surgery, The First Affiliated Hospital of Chongqing Medical University, No. 1 Youyi Road, Yuanjiagang, Yuzhong District, Chongqing 400000, China. lanxiangkeyan@163.com
Received: October 21, 2024
Revised: February 17, 2025
Accepted: March 10, 2025
Published online: May 15, 2025
Processing time: 207 Days and 16.5 Hours
Abstract
BACKGROUND

Stage IV pancreatic cancer (PC) has a poor prognosis and lacks individualized prognostic tools. Current survival prediction models are limited, and there is a need for more accurate, personalized methods. The Surveillance, Epidemiology, and End Results (SEER) database offers a valuable resource for studying large patient cohorts, yet machine learning-based nomograms for stage IV PC prognosis remain underexplored. This study hypothesizes that a machine learning-based nomogram can predict cancer-specific survival (CSS) and overall survival (OS) with high accuracy in stage IV PC patients.

AIM

To construct and validate a machine learning-based nomogram for predicting survival in stage IV PC patients using real-world data.

METHODS

Clinical data from stage IV PC patients diagnosed via pathology from 2000 to 2019 were extracted from the SEER database. Patients were randomly divided into a training set and a validation set in a 7:3 ratio. Multivariate Cox proportional hazards, Least Absolute Shrinkage and Selection Operator regression, and Random Survival Forest models were used to identify prognostic variables. A nomogram was constructed to predict CSS and OS at 6, 12, and 18 months. The C-index, receiver operating characteristic curves, and calibration curves were used to evaluate the model’s predictive performance.

RESULTS

A total of 1662 patients were included (1163 in the training set, 499 in the validation set). The median follow-up times were 4 months [interquartile range (IQR): 1-10 months] for the training set and 4 months (IQR: 1-11 months) for the validation set. Key independent prognostic factors identified included age, race, marital status, tumor location, N stage, grade, surgery, chemotherapy, and liver metastasis. The nomogram accurately predicted OS and CSS at 6, 12, and 18 months, with a C-index of 0.727 (OS) and 0.727 (CSS) in the training set, and 0.719 (OS) and 0.716 (CSS) in the validation set. Calibration curves demonstrated excellent model accuracy.

CONCLUSION

The nomogram developed using age, grade, chemotherapy, surgery, and liver metastasis as predictors can reliably estimate survival outcomes for stage IV PC patients and offers a potential tool for individualized clinical decision-making.

Keywords: Stage IV pancreatic ductal adenocarcinoma; Prognosis; Surveillance Epidemiology, and End Results Program; Machine learning; Cancer survival; Prognostic model

Core Tip: This study develops and validates a machine learning-based nomogram to predict survival in patients with stage IV pancreatic ductal adenocarcinoma. Using data from the Surveillance, Epidemiology, and End Results program, the model integrates prognostic factors and demonstrates high accuracy in predicting cancer-specific survival and overall survival at various time points. This nomogram offers a personalized approach to survival prediction, potentially guiding clinical decision-making and treatment strategies for advanced pancreatic cancer patients.