What does this research mean for the field?

An integrated machine learning model combining clinical data and CT-based radiomics features can effectively predict tumor recurrence in breast cancer patients before neoadjuvant systemic therapy. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To develop and validate machine learning models that integrate pretreatment computed tomography radiomics and clinical features to predict breast cancer recurrence following neoadjuvant systemic therapy.

August 29, 2026The Kaohsiung Journal of Medical SciencesOpen Access

Pretreatment Prediction of Tumor Recurrence in Breast Cancer After Neoadjuvant Systemic Therapy Using Machine Learning With Clinical and CT Radiomics Features

View Full Paper

Ask AI

Bookmark

Authors

HTHuei‐Yi Tsai JWJo‐Ching Wang WCWei-Shiuan Chung

Discussion

Member takes

Overview

Retrospective study shows integrated CT radiomics and clinical machine learning models predict tumor recurrence in breast cancer, indicating a path toward optimized pretreatment risk assessment.

Key Points

To develop and validate machine learning models that integrate pretreatment computed tomography radiomics and clinical features to predict breast cancer recurrence following neoadjuvant systemic therapy.
Retrospectively evaluated 235 patients with 237 breast tumors who underwent contrast-enhanced CT prior to neoadjuvant systemic therapy.
Partitioned datasets into training and testing sets and used nested five-fold cross-validation to assess three machine learning algorithms across clinical, radiomics, and integrated models.
Stratified patients into risk tiers and compared recurrence-free survival curves using Kaplan-Meier analysis and the log-rank test.
The random survival forest clinical model (mean AUC = 0.755) and the Cox-LASSO radiomics model (mean AUC = 0.636) demonstrated the highest performance among individual algorithms.
The integrated model combining random survival forest clinical features and Cox-LASSO radiomics achieved a superior mean AUC of 0.777 for recurrence prediction.
Log-rank analysis showed statistically significant differences in survival curves between the high- and low-risk cohorts stratified by the integrated model on the testing sets.

Cite This Study

Tsai et al. (2026) studied this question.

synapsesocial.com/papers/6a9299ac8e5d7d1fc0c11ca0 https://doi.org/10.1002/kjm2.70288

View Full Paper

Ask AI

Bookmark

August 29, 2026The Kaohsiung Journal of Medical SciencesOpen Access

Pretreatment Prediction of Tumor Recurrence in Breast Cancer After Neoadjuvant Systemic Therapy Using Machine Learning With Clinical and CT Radiomics Features

View Full Paper

Ask AI

Bookmark

Authors

HTHuei‐Yi Tsai JWJo‐Ching Wang WCWei-Shiuan Chung

Discussion

Member takes

Overview

Retrospective study shows integrated CT radiomics and clinical machine learning models predict tumor recurrence in breast cancer, indicating a path toward optimized pretreatment risk assessment.

Key Points

To develop and validate machine learning models that integrate pretreatment computed tomography radiomics and clinical features to predict breast cancer recurrence following neoadjuvant systemic therapy.
Retrospectively evaluated 235 patients with 237 breast tumors who underwent contrast-enhanced CT prior to neoadjuvant systemic therapy.
Partitioned datasets into training and testing sets and used nested five-fold cross-validation to assess three machine learning algorithms across clinical, radiomics, and integrated models.
Stratified patients into risk tiers and compared recurrence-free survival curves using Kaplan-Meier analysis and the log-rank test.
The random survival forest clinical model (mean AUC = 0.755) and the Cox-LASSO radiomics model (mean AUC = 0.636) demonstrated the highest performance among individual algorithms.
The integrated model combining random survival forest clinical features and Cox-LASSO radiomics achieved a superior mean AUC of 0.777 for recurrence prediction.
Log-rank analysis showed statistically significant differences in survival curves between the high- and low-risk cohorts stratified by the integrated model on the testing sets.

Cite This Study

Tsai et al. (2026) studied this question.

synapsesocial.com/papers/6a9299ac8e5d7d1fc0c11ca0 https://doi.org/10.1002/kjm2.70288

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark