Predicting Neoplastic Polyp in Patients With Gallbladder Polyps Using Interpretable Machine Learning Models: Retrospective Cohort Study

ABSTRACT Objective Gallbladder polyps (GBPs) are increasingly prevalent, with the majority being benign; however, neoplastic polyps carry a risk of malignant transformation, highlighting the importance of accurate differentiation. This study aimed to develop and validate interpretable machine learni...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhaobin He, Shengbiao Yang, Jianqiang Cao, Huijie Gao, Cheng Peng
Format: Article
Language:English
Published: Wiley 2025-03-01
Series:Cancer Medicine
Subjects:
Online Access:https://doi.org/10.1002/cam4.70739
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850030782424285184
author Zhaobin He
Shengbiao Yang
Jianqiang Cao
Huijie Gao
Cheng Peng
author_facet Zhaobin He
Shengbiao Yang
Jianqiang Cao
Huijie Gao
Cheng Peng
author_sort Zhaobin He
collection DOAJ
description ABSTRACT Objective Gallbladder polyps (GBPs) are increasingly prevalent, with the majority being benign; however, neoplastic polyps carry a risk of malignant transformation, highlighting the importance of accurate differentiation. This study aimed to develop and validate interpretable machine learning (ML) models to accurately predict neoplastic GBPs in a retrospective cohort, identifying key features and providing model explanations using the Shapley additive explanations (SHAP) method. Methods A total of 924 patients with GBPs who underwent cholecystectomy between January 2013 and December 2023 at Qilu Hospital of Shandong University were included. The patient characteristics, laboratory results, preoperative ultrasound findings, and postoperative pathological results were collected. The dataset was randomly split, with 80% used for model training and the remaining 20% used for model testing. This study employed nine ML algorithms to construct predictive models. Subsequently, model performance was evaluated and compared using several metrics, including the area under the receiver operating characteristic curve (AUC). Feature importance was ranked, and model interpretability was enhanced by the SHAP method. Results K‐nearest neighbors, C5.0 decision tree algorithm, and gradient boosting machine models showed the highest performance, with the highest predictive efficacy for neoplastic polyps. The SHAP method revealed the top five predictors of neoplastic polyps according to the importance ranking. The polyp size was recognized as the most important predictor variable, indicating that lesions ≥ 18 mm should prompt heightened clinical surveillance and timely intervention. Conclusions Our interpretable ML models accurately predict neoplastic polyps in GBP patients, providing guidance for treatment planning and resource allocation. The model's transparency fosters trust and understanding, empowering physicians to confidently use its predictions for improved patient care.
format Article
id doaj-art-5f9dad7d581349788e60a4e3d28535bb
institution DOAJ
issn 2045-7634
language English
publishDate 2025-03-01
publisher Wiley
record_format Article
series Cancer Medicine
spelling doaj-art-5f9dad7d581349788e60a4e3d28535bb2025-08-20T02:59:07ZengWileyCancer Medicine2045-76342025-03-01145n/an/a10.1002/cam4.70739Predicting Neoplastic Polyp in Patients With Gallbladder Polyps Using Interpretable Machine Learning Models: Retrospective Cohort StudyZhaobin He0Shengbiao Yang1Jianqiang Cao2Huijie Gao3Cheng Peng4Department of Hepatobiliary Surgery, General Surgery Qilu Hospital, Shandong University Jinan Shandong P.R. ChinaDepartment of Hepatobiliary Surgery, General Surgery Qilu Hospital, Shandong University Jinan Shandong P.R. ChinaDepartment of Hepatobiliary Surgery, General Surgery Qilu Hospital, Shandong University Jinan Shandong P.R. ChinaDepartment of Hepatobiliary Surgery, General Surgery Qilu Hospital, Shandong University Jinan Shandong P.R. ChinaDepartment of Hepatobiliary Surgery, General Surgery Qilu Hospital, Shandong University Jinan Shandong P.R. ChinaABSTRACT Objective Gallbladder polyps (GBPs) are increasingly prevalent, with the majority being benign; however, neoplastic polyps carry a risk of malignant transformation, highlighting the importance of accurate differentiation. This study aimed to develop and validate interpretable machine learning (ML) models to accurately predict neoplastic GBPs in a retrospective cohort, identifying key features and providing model explanations using the Shapley additive explanations (SHAP) method. Methods A total of 924 patients with GBPs who underwent cholecystectomy between January 2013 and December 2023 at Qilu Hospital of Shandong University were included. The patient characteristics, laboratory results, preoperative ultrasound findings, and postoperative pathological results were collected. The dataset was randomly split, with 80% used for model training and the remaining 20% used for model testing. This study employed nine ML algorithms to construct predictive models. Subsequently, model performance was evaluated and compared using several metrics, including the area under the receiver operating characteristic curve (AUC). Feature importance was ranked, and model interpretability was enhanced by the SHAP method. Results K‐nearest neighbors, C5.0 decision tree algorithm, and gradient boosting machine models showed the highest performance, with the highest predictive efficacy for neoplastic polyps. The SHAP method revealed the top five predictors of neoplastic polyps according to the importance ranking. The polyp size was recognized as the most important predictor variable, indicating that lesions ≥ 18 mm should prompt heightened clinical surveillance and timely intervention. Conclusions Our interpretable ML models accurately predict neoplastic polyps in GBP patients, providing guidance for treatment planning and resource allocation. The model's transparency fosters trust and understanding, empowering physicians to confidently use its predictions for improved patient care.https://doi.org/10.1002/cam4.70739gallbladder polypsinterpretable machine learningneoplastic polypSHAP
spellingShingle Zhaobin He
Shengbiao Yang
Jianqiang Cao
Huijie Gao
Cheng Peng
Predicting Neoplastic Polyp in Patients With Gallbladder Polyps Using Interpretable Machine Learning Models: Retrospective Cohort Study
Cancer Medicine
gallbladder polyps
interpretable machine learning
neoplastic polyp
SHAP
title Predicting Neoplastic Polyp in Patients With Gallbladder Polyps Using Interpretable Machine Learning Models: Retrospective Cohort Study
title_full Predicting Neoplastic Polyp in Patients With Gallbladder Polyps Using Interpretable Machine Learning Models: Retrospective Cohort Study
title_fullStr Predicting Neoplastic Polyp in Patients With Gallbladder Polyps Using Interpretable Machine Learning Models: Retrospective Cohort Study
title_full_unstemmed Predicting Neoplastic Polyp in Patients With Gallbladder Polyps Using Interpretable Machine Learning Models: Retrospective Cohort Study
title_short Predicting Neoplastic Polyp in Patients With Gallbladder Polyps Using Interpretable Machine Learning Models: Retrospective Cohort Study
title_sort predicting neoplastic polyp in patients with gallbladder polyps using interpretable machine learning models retrospective cohort study
topic gallbladder polyps
interpretable machine learning
neoplastic polyp
SHAP
url https://doi.org/10.1002/cam4.70739
work_keys_str_mv AT zhaobinhe predictingneoplasticpolypinpatientswithgallbladderpolypsusinginterpretablemachinelearningmodelsretrospectivecohortstudy
AT shengbiaoyang predictingneoplasticpolypinpatientswithgallbladderpolypsusinginterpretablemachinelearningmodelsretrospectivecohortstudy
AT jianqiangcao predictingneoplasticpolypinpatientswithgallbladderpolypsusinginterpretablemachinelearningmodelsretrospectivecohortstudy
AT huijiegao predictingneoplasticpolypinpatientswithgallbladderpolypsusinginterpretablemachinelearningmodelsretrospectivecohortstudy
AT chengpeng predictingneoplasticpolypinpatientswithgallbladderpolypsusinginterpretablemachinelearningmodelsretrospectivecohortstudy