Clinical prediction of pathological complete response in breast cancer: a machine learning study

Abstract Background This study aimed to develop and validate machine learning models to predict pathological complete response (pCR) after neoadjuvant therapy in patients with breast cancer patients. Methods Clinical and pathological data from 1143 patients were analyzed, encompassing variables such...

Full description

Saved in:
Bibliographic Details
Main Authors: Chongwu He, Tenghua Yu, Liu Yang, Longbo He, Jin Zhu, Jing Chen
Format: Article
Language:English
Published: BMC 2025-05-01
Series:BMC Cancer
Subjects:
Online Access:https://doi.org/10.1186/s12885-025-14335-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849325874687508480
author Chongwu He
Tenghua Yu
Liu Yang
Longbo He
Jin Zhu
Jing Chen
author_facet Chongwu He
Tenghua Yu
Liu Yang
Longbo He
Jin Zhu
Jing Chen
author_sort Chongwu He
collection DOAJ
description Abstract Background This study aimed to develop and validate machine learning models to predict pathological complete response (pCR) after neoadjuvant therapy in patients with breast cancer patients. Methods Clinical and pathological data from 1143 patients were analyzed, encompassing variables such as age, gender, marital status, histologic grade, T stage, N stage, months from diagnosis to treatment, molecular subtype, and response to neoadjuvant therapy. Seven machine learning models were trained and validated using both internal and external datasets. Model performance was evaluated using multiple metrics, and interpretability analysis was conducted to assess feature importance. Results Key variables influencing pCR included grade, N stage, months from diagnosis to treatment, and molecular subtype. The Naive Bayes model emerged as the most effective, with accuracy (0.746), sensitivity (0.699), specificity (0.808), and F1 score (0.759) surpassing other models. Both internal and external validation confirmed the model’s robust predictive power. A web tool was developed for clinical use, aiding in personalized treatment planning. Interpretability analysis further elucidated the contribution of features to pCR prediction, enhancing clinical applicability. Conclusion The Naive Bayes model provides a robust tool for personalized treatment decisions in patients with breast cancer undergoing neoadjuvant therapy. By accurately predicting pCR rates, it enables clinicians to tailor treatment strategies, potentially improving outcomes.
format Article
id doaj-art-24f54e67bae44cb08c897b2bcc47b9b4
institution Kabale University
issn 1471-2407
language English
publishDate 2025-05-01
publisher BMC
record_format Article
series BMC Cancer
spelling doaj-art-24f54e67bae44cb08c897b2bcc47b9b42025-08-20T03:48:18ZengBMCBMC Cancer1471-24072025-05-0125111210.1186/s12885-025-14335-1Clinical prediction of pathological complete response in breast cancer: a machine learning studyChongwu He0Tenghua Yu1Liu Yang2Longbo He3Jin Zhu4Jing Chen5Department of Breast Surgery, The Second Affiliated Hospital of Nanchang Medical College, Jiangxi Cancer HospitalDepartment of Breast Surgery, The Second Affiliated Hospital of Nanchang Medical College, Jiangxi Cancer HospitalDepartment of Pathology, Nanchang People’s HospitalDepartment of Breast Surgery, The Second Affiliated Hospital of Nanchang Medical College, Jiangxi Cancer HospitalDepartment of Breast Surgery, The Second Affiliated Hospital of Nanchang Medical College, Jiangxi Cancer HospitalDepartment of Nursing, Nanchang Medical CollegeAbstract Background This study aimed to develop and validate machine learning models to predict pathological complete response (pCR) after neoadjuvant therapy in patients with breast cancer patients. Methods Clinical and pathological data from 1143 patients were analyzed, encompassing variables such as age, gender, marital status, histologic grade, T stage, N stage, months from diagnosis to treatment, molecular subtype, and response to neoadjuvant therapy. Seven machine learning models were trained and validated using both internal and external datasets. Model performance was evaluated using multiple metrics, and interpretability analysis was conducted to assess feature importance. Results Key variables influencing pCR included grade, N stage, months from diagnosis to treatment, and molecular subtype. The Naive Bayes model emerged as the most effective, with accuracy (0.746), sensitivity (0.699), specificity (0.808), and F1 score (0.759) surpassing other models. Both internal and external validation confirmed the model’s robust predictive power. A web tool was developed for clinical use, aiding in personalized treatment planning. Interpretability analysis further elucidated the contribution of features to pCR prediction, enhancing clinical applicability. Conclusion The Naive Bayes model provides a robust tool for personalized treatment decisions in patients with breast cancer undergoing neoadjuvant therapy. By accurately predicting pCR rates, it enables clinicians to tailor treatment strategies, potentially improving outcomes.https://doi.org/10.1186/s12885-025-14335-1Breast cancerMachine learningPathological complete responsePCRPrediction
spellingShingle Chongwu He
Tenghua Yu
Liu Yang
Longbo He
Jin Zhu
Jing Chen
Clinical prediction of pathological complete response in breast cancer: a machine learning study
BMC Cancer
Breast cancer
Machine learning
Pathological complete response
PCR
Prediction
title Clinical prediction of pathological complete response in breast cancer: a machine learning study
title_full Clinical prediction of pathological complete response in breast cancer: a machine learning study
title_fullStr Clinical prediction of pathological complete response in breast cancer: a machine learning study
title_full_unstemmed Clinical prediction of pathological complete response in breast cancer: a machine learning study
title_short Clinical prediction of pathological complete response in breast cancer: a machine learning study
title_sort clinical prediction of pathological complete response in breast cancer a machine learning study
topic Breast cancer
Machine learning
Pathological complete response
PCR
Prediction
url https://doi.org/10.1186/s12885-025-14335-1
work_keys_str_mv AT chongwuhe clinicalpredictionofpathologicalcompleteresponseinbreastcanceramachinelearningstudy
AT tenghuayu clinicalpredictionofpathologicalcompleteresponseinbreastcanceramachinelearningstudy
AT liuyang clinicalpredictionofpathologicalcompleteresponseinbreastcanceramachinelearningstudy
AT longbohe clinicalpredictionofpathologicalcompleteresponseinbreastcanceramachinelearningstudy
AT jinzhu clinicalpredictionofpathologicalcompleteresponseinbreastcanceramachinelearningstudy
AT jingchen clinicalpredictionofpathologicalcompleteresponseinbreastcanceramachinelearningstudy