Prediction of Pathological Complete Response after Chemoradiation for Locally Advanced Rectal Cancer Using…

AI / informaticsJournal of the anus, rectum and colon· 2026

Prediction of Pathological Complete Response after Chemoradiation for Locally Advanced Rectal Cancer Using Machine Learning with Clinical Features, the INTERCEPTOR Study Preliminary Model.

David Mens, Soogyeong Shin, Farhan Akram … Jan von der Thüsen

Colon & Rectal SurgeryAI / informaticsQ3IF 1.6

Positive lymph node count best predicts complete response, but weakly

Prediction of Pathological Complete Response after Chemoradiation for Locally Advanced Rectal Cancer Using Machine Learning with Clinical Features, the INTERCEPTOR Study Preliminary Model.

David Mens … Jan von der Thüsen

Journal of the anus, rectum and colon · 2026 · Q3 in General Medicine

Background

Organ-preserving strategies are increasingly used in rectal cancer for those achieving a pathological complete response (pCR) following chemoradiotherapy (chemoradiotherapy).

Methods

With locally advanced rectal cancer who received chemoradiotherapy followed by total mesorectal excision between 2004 and 2018 at a tertiary referral center were analyzed.

n = 238 patients

Results

positive lymph node count only weakly separates who responds

0.65score

AUROC

0.83score

Sensitivity

0.45score

Specificity

More results

Among 238 included patients, 30 (12.6%) achieved CR.

Combining positive node count with additional clinical variables led to a modest improvement in performance.

SHAP analysis confirmed positive lymph node count was the most influential predictor.

“

Conclusion

Pretreatment clinical variables alone provide poor-to-fair accuracy for predicting CR after chemoradiotherapy in locally advanced rectal cancer.

Prediction of Pathological Complete Response after Chemoradiation for Locally Advanced Rectal Cancer Using Machine Learning with Clinical Features, the INTERCEPTOR Study Preliminary Model.

Prediction of Pathological Complete Response after Chemoradiation for Locally Advanced Rectal Cancer Using Machine Learning with Clinical Features, the INTERCEPTOR Study Preliminary Model.

Related papers