Explainable machine learning for predicting lung metastasis of colorectal cancer

Abstract Patients with lung metastasis of colorectal cancer typically have a poor prognosis. Therefore, establishing an effective screening and diagnosis model is paramount. Our study seeks to construct and verify a predictive model utilizing machine learning (ML) that can evaluate the risk of lung...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhentian Guo, Zongming Zhang, Limin Liu, Yue Zhao, Zhuo Liu, Chong Zhang, Hui Qi, Jinqiu Feng, Peijie Yao
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-98188-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849699445708423168
author Zhentian Guo
Zongming Zhang
Limin Liu
Yue Zhao
Zhuo Liu
Chong Zhang
Hui Qi
Jinqiu Feng
Peijie Yao
author_facet Zhentian Guo
Zongming Zhang
Limin Liu
Yue Zhao
Zhuo Liu
Chong Zhang
Hui Qi
Jinqiu Feng
Peijie Yao
author_sort Zhentian Guo
collection DOAJ
description Abstract Patients with lung metastasis of colorectal cancer typically have a poor prognosis. Therefore, establishing an effective screening and diagnosis model is paramount. Our study seeks to construct and verify a predictive model utilizing machine learning (ML) that can evaluate the risk of lung metastasis with newly diagnosed colorectal cancer (CRC) using Shapley Additive exPlanations (SHAP). Using the Surveillance, Epidemiology, and End Results database, 39,674 were extracted for model development, all of whom had been pathologically diagnosed with CRC. The data spans from 2010 to 2015. Our study has constructed seven ML algorithms based on the data mentioned above, including Random Forest (RF), Decision Tree, Support Vector Machine, Naive Bayes, K-Nearest Neighbor, eXtreme Gradient Boosting, and Gradient Boosting Machine. We selected the best algorithm and visualized it using SHAP. We conducted a validation of the model utilizing data from a Chinese hospital to assess its practicality. Based on this, we have constructed an open web calculator. 39,674 patient data were included in our study, among whom 1369 (3.5%) presented with distant lung metastasis. The Random Forest (RF) algorithm demonstrated the highest predictive capability within the internal test set (AUC of 0.980, AUPR of 0.941). Furthermore, the random forest algorithm also exhibited excellent performance in external validation sets. Meanwhile, we have also established a web calculator ( http://121.43.117.60:8003/ ). The RF algorithm has demonstrated excellent predictive performance. It can assist clinicians in devising more personalized treatment plans.
format Article
id doaj-art-a4c82a33f8864be0a2e558d70ba835fa
institution DOAJ
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-a4c82a33f8864be0a2e558d70ba835fa2025-08-20T03:18:34ZengNature PortfolioScientific Reports2045-23222025-04-0115111210.1038/s41598-025-98188-5Explainable machine learning for predicting lung metastasis of colorectal cancerZhentian Guo0Zongming Zhang1Limin Liu2Yue Zhao3Zhuo Liu4Chong Zhang5Hui Qi6Jinqiu Feng7Peijie Yao8Department of General Surgery, Beijing Electric Power Hospital, State Grid Corporation of China, Capital Medical UniversityDepartment of General Surgery, Beijing Electric Power Hospital, State Grid Corporation of China, Capital Medical UniversityDepartment of General Surgery, Beijing Electric Power Hospital, State Grid Corporation of China, Capital Medical UniversityDepartment of General Surgery, Beijing Electric Power Hospital, State Grid Corporation of China, Capital Medical UniversityDepartment of General Surgery, Beijing Electric Power Hospital, State Grid Corporation of China, Capital Medical UniversityDepartment of General Surgery, Beijing Electric Power Hospital, State Grid Corporation of China, Capital Medical UniversityDepartment of General Surgery, Beijing Electric Power Hospital, State Grid Corporation of China, Capital Medical UniversityChina Clinical Medical Research Center for Hepatobiliary Diseases in General Surgery, China General Technology GroupChina Clinical Medical Research Center for Hepatobiliary Diseases in General Surgery, China General Technology GroupAbstract Patients with lung metastasis of colorectal cancer typically have a poor prognosis. Therefore, establishing an effective screening and diagnosis model is paramount. Our study seeks to construct and verify a predictive model utilizing machine learning (ML) that can evaluate the risk of lung metastasis with newly diagnosed colorectal cancer (CRC) using Shapley Additive exPlanations (SHAP). Using the Surveillance, Epidemiology, and End Results database, 39,674 were extracted for model development, all of whom had been pathologically diagnosed with CRC. The data spans from 2010 to 2015. Our study has constructed seven ML algorithms based on the data mentioned above, including Random Forest (RF), Decision Tree, Support Vector Machine, Naive Bayes, K-Nearest Neighbor, eXtreme Gradient Boosting, and Gradient Boosting Machine. We selected the best algorithm and visualized it using SHAP. We conducted a validation of the model utilizing data from a Chinese hospital to assess its practicality. Based on this, we have constructed an open web calculator. 39,674 patient data were included in our study, among whom 1369 (3.5%) presented with distant lung metastasis. The Random Forest (RF) algorithm demonstrated the highest predictive capability within the internal test set (AUC of 0.980, AUPR of 0.941). Furthermore, the random forest algorithm also exhibited excellent performance in external validation sets. Meanwhile, we have also established a web calculator ( http://121.43.117.60:8003/ ). The RF algorithm has demonstrated excellent predictive performance. It can assist clinicians in devising more personalized treatment plans.https://doi.org/10.1038/s41598-025-98188-5SEERColorectal cancerRandom forestLung metastasisSHapley additive exPlanations
spellingShingle Zhentian Guo
Zongming Zhang
Limin Liu
Yue Zhao
Zhuo Liu
Chong Zhang
Hui Qi
Jinqiu Feng
Peijie Yao
Explainable machine learning for predicting lung metastasis of colorectal cancer
Scientific Reports
SEER
Colorectal cancer
Random forest
Lung metastasis
SHapley additive exPlanations
title Explainable machine learning for predicting lung metastasis of colorectal cancer
title_full Explainable machine learning for predicting lung metastasis of colorectal cancer
title_fullStr Explainable machine learning for predicting lung metastasis of colorectal cancer
title_full_unstemmed Explainable machine learning for predicting lung metastasis of colorectal cancer
title_short Explainable machine learning for predicting lung metastasis of colorectal cancer
title_sort explainable machine learning for predicting lung metastasis of colorectal cancer
topic SEER
Colorectal cancer
Random forest
Lung metastasis
SHapley additive exPlanations
url https://doi.org/10.1038/s41598-025-98188-5
work_keys_str_mv AT zhentianguo explainablemachinelearningforpredictinglungmetastasisofcolorectalcancer
AT zongmingzhang explainablemachinelearningforpredictinglungmetastasisofcolorectalcancer
AT liminliu explainablemachinelearningforpredictinglungmetastasisofcolorectalcancer
AT yuezhao explainablemachinelearningforpredictinglungmetastasisofcolorectalcancer
AT zhuoliu explainablemachinelearningforpredictinglungmetastasisofcolorectalcancer
AT chongzhang explainablemachinelearningforpredictinglungmetastasisofcolorectalcancer
AT huiqi explainablemachinelearningforpredictinglungmetastasisofcolorectalcancer
AT jinqiufeng explainablemachinelearningforpredictinglungmetastasisofcolorectalcancer
AT peijieyao explainablemachinelearningforpredictinglungmetastasisofcolorectalcancer