Copyright
©The Author(s) 2025. Published by Baishideng Publishing Group Inc. All rights reserved.
Preoperative prediction of textbook outcome in intrahepatic cholangiocarcinoma by interpretable machine learning: A multicenter cohort study
Ting-Feng Huang, Cong Luo, Luo-Bin Guo, Hong-Zhi Liu, Jiang-Tao Li, Qi-Zhu Lin, Rui-Lin Fan, Wei-Ping Zhou, Jing-Dong Li, Ke-Can Lin, Shi-Chuan Tang, Yong-Yi Zeng
Ting-Feng Huang, Hong-Zhi Liu, Qi-Zhu Lin, Rui-Lin Fan, Shi-Chuan Tang, Yong-Yi Zeng, Department of Hepatobiliary Surgery, Mengchao Hepatobiliary Hospital of Fujian Medical University, Fuzhou 350025, Fujian Province, China
Cong Luo, Department of Hepatopancreatobiliary Surgery, The People’s Hospital of Zizhong County, Neijiang 540045, Sichuan Province, China
Luo-Bin Guo, Ke-Can Lin, Department of Hepatopancreatobiliary Surgery, Mengchao Hepatobiliary Hospital of Fujian Medical University, Fuzhou 350025, Fujian Province, China
Jiang-Tao Li, Department of General Surgery, The Second Affiliated Hospital Zhejiang University School of Medicine, Hangzhou 310009, Zhejiang Province, China
Wei-Ping Zhou, Department of the 3rd Liver Surgery, Eastern Hepatobiliary Surgery Hospital, The Second Military Medical University, Shanghai 200438, China
Jing-Dong Li, The Affiliated Hospital of North Sichuan Medical College, Nanchong 637000, Sichuan Province, China
Co-first authors: Ting-Feng Huang and Cong Luo.
Co-corresponding authors: Shi-Chuan Tang and Yong-Yi Zeng.
Author contributions: Zeng YY, Huang TF and Tang SC conceptualized and designed the research; Li JT, Li JD Zhou WP and Zeng YY screened patients and acquired clinical data; Guo LB, Lin QZ, Fan RL, Lin KC and Liu HZ performed Data analysis; Huang TF wrote the paper; All the authors have read and approved the final manuscript. Huang TF proposed, designed and analysis the date, performed data analysis and prepared the first draft of the manuscript. Luo C was responsible for patient screening, enrollment, collection of clinical data. Both authors have made crucial and indispensable contributions towards the completion of the project and thus qualified as the co-first authors of the paper. Both Zeng YY and Tang SC have played important and indispensable roles in the experimental design, data interpretation and manuscript preparation as the co-corresponding authors. Zeng YY applied for and obtained the funds for this research project. Tang SC conceptualized, designed, and supervised the whole process of the project. He searched the literature, revised and submitted the early version of the manuscript with the focus on the interpretability of machine learning algorithms. Zeng YY was instrumental and responsible for data re-analysis and re-interpretation, figure plotting, comprehensive literature search, preparation and submission of the current version of the manuscript with a new focus on interpretability and external validation of machine learning. This collaboration between Zeng YY and Tang SC is crucial for the publication of this manuscript and other manuscripts still in preparation.
Supported by National Key Research and Development Program, No. 2022YFC2407304; Major Research Project for Middle-Aged and Young Scientists of Fujian Provincial Health Commission, No. 2021ZQNZD013; The National Natural Science Foundation of China, No. 62275050; Fujian Province Science and Technology Innovation Joint Fund Project, No. 2019Y9108; and Major Science and Technology Projects of Fujian Province, No. 2021YZ036017.
Institutional review board statement: The study was reviewed and approved by the Ethics Committee of the Mengchao Hepatobiliary Hospital of Fujian Medical University, and exempts the requirement of written informed consent. All procedures were performed in accordance with World Medical Association Declaration of Helsinki, (Approval No. 2024_041_01).
Informed consent statement: The need for patient consent was waived due to the retrospective nature of the study.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
STROBE statement: The authors have read the STROBE Statement—checklist of items, and the manuscript was prepared and revised according to the STROBE Statement—checklist of items.
Data sharing statement: The data where our results derived from were from Mengchao Hepatobiliary Hospital of Fujian Medical University. The original data were not publicly available and could only be shared with the permission of the ethics committee of Mengchao Hospital.
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: Yong-Yi Zeng, MD, PhD, Professor, Department of Hepatobiliary Surgery, Mengchao Hepatobiliary Hospital of Fujian Medical University, No. 312 Xihong Road, Fuzhou 350025, Fujian Province, China.
lamp197311@126.com
Received: August 30, 2024
Revised: January 10, 2025
Accepted: February 13, 2025
Published online: March 21, 2025
Processing time: 195 Days and 8.1 Hours
BACKGROUND
To investigate the preoperative factors influencing textbook outcomes (TO) in Intrahepatic cholangiocarcinoma (ICC) patients and evaluate the feasibility of an interpretable machine learning model for preoperative prediction of TO, we developed a machine learning model for preoperative prediction of TO and used the SHapley Additive exPlanations (SHAP) technique to illustrate the prediction process.
AIM
To analyze the factors influencing textbook outcomes before surgery and to establish interpretable machine learning models for preoperative prediction.
METHODS
A total of 376 patients diagnosed with ICC were retrospectively collected from four major medical institutions in China, covering the period from 2011 to 2017. Logistic regression analysis was conducted to identify preoperative variables associated with achieving TO. Based on these variables, an EXtreme Gradient Boosting (XGBoost) machine learning prediction model was constructed using the XGBoost package. The SHAP (package: Shapviz) algorithm was employed to visualize each variable's contribution to the model's predictions. Kaplan-Meier survival analysis was performed to compare the prognostic differences between the TO-achieving and non-TO-achieving groups.
RESULTS
Among 376 patients, 287 were included in the training group and 89 in the validation group. Logistic regression identified the following preoperative variables influencing TO: Child-Pugh classification, Eastern Cooperative Oncology Group (ECOG) score, hepatitis B, and tumor size. The XGBoost prediction model demonstrated high accuracy in internal validation (AUC = 0.8825) and external validation (AUC = 0.8346). Survival analysis revealed that the disease-free survival rates for patients achieving TO at 1, 2, and 3 years were 64.2%, 56.8%, and 43.4%, respectively.
CONCLUSION
Child-Pugh classification, ECOG score, hepatitis B, and tumor size are preoperative predictors of TO. In both the training group and the validation group, the machine learning model had certain effectiveness in predicting TO before surgery. The SHAP algorithm provided intuitive visualization of the machine learning prediction process, enhancing its interpretability.
Core Tip: This study developed a machine learning model to preoperatively predict the Textbook outcome (TO), a measure of surgical quality and short-term prognosis, and utilized the SHapley Additive exPlanations technique to enhance model transparency. Based on the analysis of 376 intrahepatic cholangiocarcinoma patients from four Chinese medical institutions, logistic regression identified key preoperative factors, including Child-Pugh classification, Eastern Cooperative Oncology Group score, hepatitis B status, and tumor size. The EXtreme Gradient Boosting algorithm was used to construct the prediction model, while SHAP visualized its decision-making process. The model effectively stratified recurrence-free survival, demonstrating its utility in preoperative TO prediction.
