Pathomics-based machine learning models for predicting pathological complete response and prognosis in locally advanced rectal cancer patients post-neoadjuvant chemoradiotherapy: insights from two independent institutional studies

Accurate prediction of pathological complete response (pCR) and disease-free survival (DFS) in locally advanced rectal cancer (LARC) patients undergoing neoadjuvant chemoradiotherapy (NCRT) is essential for formulating effective treatment plans. This study aimed to construct and validate the machine...

Full description

Saved in:
Bibliographic Details
Published in:BMC cancer 2024-12, Vol.24 (1), p.1580-13, Article 1580
Main Authors: Zhang, Yiyi, Huang, Ying, Xu, Meifang, Zhuang, Jiazheng, Zhou, Zhibo, Zheng, Shaoqing, Zhu, Bingwang, Guan, Guoxian, Chen, Hong, Liu, Xing
Format: Article
Language:English
Subjects:
Adult
Aged
Algorithms
Biopsy
Cancer
Cancer patients
Cancer therapies
Chemoradiotherapy
Chemoradiotherapy - methods
Chemotherapy
Colonoscopy
Colorectal cancer
Datasets
Development and progression
Disease-Free Survival
Female
Health aspects
Histology, Pathological
Hospitals
Humans
Kaplan-Meier Estimate
Learning algorithms
Locally advanced rectal cancer
Machine Learning
Male
Medical imaging
Medical prognosis
Middle Aged
Neoadjuvant chemoradiotherapy
Neoadjuvant therapy
Neoadjuvant Therapy - methods
Nomograms
Oncology, Experimental
Pathomics
Patients
Prognosis
Radiation therapy
Rectal Neoplasms - mortality
Rectal Neoplasms - pathology
Rectal Neoplasms - therapy
Rectum
Regression analysis
Retrospective Studies
ROC Curve
Statistical analysis
Surgery
Technology application
Treatment Outcome
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurate prediction of pathological complete response (pCR) and disease-free survival (DFS) in locally advanced rectal cancer (LARC) patients undergoing neoadjuvant chemoradiotherapy (NCRT) is essential for formulating effective treatment plans. This study aimed to construct and validate the machine learning (ML) models to predict pCR and DFS using pathomics. A retrospective analysis was conducted on 294 patients who received NCRT from two independent institutions. Pathomics from pre-NCRT H&E stains were extracted, and five ML models were developed and validated across two centers using ROC, Kaplan-Meier, time-dependent ROC, and nomogram analyses. Among the five ML models, the Xgboost (XGB) model demonstrated superior performance in predicting pCR, achieving an AUC of 1.000 (p 
ISSN:1471-2407
1471-2407
DOI:10.1186/s12885-024-13328-w