Interpretable machine learning model using CT body composition combined with inflammatory and nutritional indicators to predict pathological complete response after neoadjuvant therapy in breast cancer


Abstract

Objective: Accurate prediction of pathological complete response (pCR) following neoadjuvant therapy (NAT) is critical for surgical risk stratification and treatment decision-making. This study develops and validates an interpretable machine learning (ML) model integrating computed tomography (CT) body composition, inflammatory, and nutritional indicators to predict pCR in breast cancer patients after NAT.

Methods: Retrospective data from 189 breast cancer patients (January 2019–June 2023) at Jiangxi Cancer Hospital were analyzed, including CT-based body composition parameters and blood test variables. After variable selection, eight ML algorithms were used to construct models. The optimal model was identified through receiver operating characteristic (ROC) curve analysis, and its generalizability was verified using the test set; accuracy and utility were evaluated using calibration/decision curve analysis, and Shapley additive explanation (SHAP) analysis visualized individualized predictions.

Results After multivariable adjustment, HR-negative/HER2-negative subtypes, visceral adipose tissue density, skeletal muscle density, albumin-to-alkaline phosphatase ratio, systemic inflammation response index, and intramuscular adipose tissue content were associated with pCR. The XGBoost model performed best, achieving an ROC Area Under the Curve (AUC) of 0.882 (95% CI: 0.756–0.996) in internal validation, and an AUC of 0.845 (95% CI: 0.735–0.955) in the test set. Brier score was 0.184. Decision curve analysis showed a favorable net benefit, and SHAP clarified key factors.

Conclusions Interpretable ML model using CT body composition combined with inflammatory and nutritional indicators effectively predicts pCR after breast cancer NAT, supporting clinical decision-making and potentially improving prognosis.

Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.

  • PeerJ does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].