Loading
Colorectal Cancer Surgical Treatments / Diverticular Disease and Complications · Journal article
Frontiers in Medicine · August 10, 2026
Encouraging direction, but not yet definitive.
A multicenter retrospective study developed and externally validated five machine learning models, plus a logistic regression nomogram, to predict major LARS (bowel dysfunction) after rectal cancer surgery. The random forest model achieved AUC 0.903 on external validation, outperforming the nomogram (AUC 0.888), and identified tumor–anal verge distance, stoma reversal time, anastomotic leakage, and diabetes as key independent risk factors. The model is positioned as a postoperative risk-stratification tool for survivorship counseling and rehabilitation planning, not preoperative treatment selection.
Multicenter retrospective cohort study with external validation. Patients undergoing laparoscopic low anterior resection for rectal adenocarcinoma; training cohort from one center (506 patients), external validation cohort from four hospitals (400 patients). Eligibility criteria and comorbidity distribution not detailed in source.. Intervention: Machine learning models (random forest, gradient boosting, support vector machine, neural network, k-nearest neighbors) and logistic regression nomogram integrating 14 biomarkers for LARS prediction.. Compared with: Logistic regression nomogram as conventional baseline; inter-model comparison via AUC and calibration.. n = 906. Multicenter, four hospitals for external validation; primary site for training cohort not specified..
Major LARS incidence 48.0% (243/506) in training cohort and 52.2% (209/400) in external validation cohort. Random forest achieved AUC 0.903 (sensitivity 0.871, specificity 0.796) on external validation; logistic regression nomogram AUC 0.888. LASSO selected 14 biomarkers including preoperative serum albumin, neoadjuvant chemotherapy, and preoperative radiotherapy.
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
Clinicians may use this random forest model to identify rectal cancer patients at high risk of postoperative bowel dysfunction for targeted surveillance, prehabilitation, and survivorship counseling. However, the retrospective design and surrogate endpoint (patient-reported LARS score, not objective functional outcomes) limit immediate practice adoption; prospective validation and assessment of whether predictions change management are needed before deployment in treatment decision-making.
Multicenter external validation of machine learning models for a clinically relevant surrogate endpoint (LARS prediction) with robust discrimination (AUC 0.903) in a reasonable sample, but limited to retrospective design and post-hoc risk stratification rather than prospective clinical decision-making or hard outcomes.
As stated by the source record.
Quoted from the source exactly as published.
Clinicians may use this random forest model to identify rectal cancer patients at high risk of postoperative bowel dysfunction for targeted surveillance, prehabilitation, and survivorship counseling. However, the retrospective design and surrogate endpoint (patient-reported LARS score, not objective functional outcomes) limit immediate practice adoption; prospective validation and assessment of whether predictions change management are needed before deployment in treatment decision-making.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Background Low anterior resection syndrome (LARS) is a prevalent treatment-related complication following sphincter-preserving surgery for rectal cancer that severely impairs survivors’ quality of life. In the era of biomarker-driven personalized cancer therapy, reliable tools integrating clinicopathological biomarkers for individualized risk stratification remain lacking. Machine learning (ML) approaches offer the potential to integrate heterogeneous biomarkers—including nutritional, inflammatory, and treatment-related indicators—for precision prediction, yet their comparative performance against conventional nomograms in LARS prediction has not been rigorously evaluated in multicenter settings. Methods This multicenter retrospective cohort included 906 patients undergoing laparoscopic low anterior resection for rectal adenocarcinoma, with 506 in the training cohort and 400 from four hospitals for external validation. Major LARS was defined as a 6-month LARS score ≥ 21. LASSO selected features from 24 candidate variables. Five machine-learning models and a logistic regression nomogram were evaluated using AUC, calibration, decision curve analysis, and SHAP interpretation. Results The incidence of major LARS was 48.0% (243/506) in the training cohort and 52.2% (209/400) in the validation cohort. LASSO regression selected 14 predictive biomarkers, including preoperative serum albumin, neoadjuvant chemotherapy, and preoperative radiotherapy. In external validation, the random forest model achieved the highest AUC of 0.903 (sensitivity 0.871, specificity 0.796), followed by the logistic regression nomogram (AUC 0.888). Multivariate analysis identified tumor–anal verge distance (OR = 0.733, 95% CI 0.679–0.792, p 0.001), stoma reversal time (OR = 1.240, p 0.001), anastomotic leakage (OR = 7.027, p = 0.004), and diabetes mellitus (OR = 2.793, p = 0.006) as independent risk factors. SHAP analysis confirmed tumor–anal verge distance as the dominant predictor, with preoperative albumin ranking fifth in feature importance, demonstrating the capacity of ML to extract predictive signal from clinically relevant but statistically marginal biomarkers. Conclusion The random forest model integrating clinicopathological biomarkers and treatment-related variables demonstrated robust predictive performance for postoperative or post-treatment risk stratification of treatment-related bowel dysfunction (LARS). The model is intended to support postoperative monitoring, survivorship counseling, and rehabilitation planning rather than purely preoperative treatment selection. These biomarker-driven prediction tools can facilitate individualized functional-risk assessment in rectal cancer patients undergoing multimodal therapy.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.