New machine learning model accurately predicts cancer treatment response

A novel machine learning model, utilizing systemic inflammation-nutritional index (SINI), successfully predicts pathological complete response (PCR) in patients with locally advanced rectal cancer undergoing neoadjuvant chemoradiotherapy (NCRT). The model achieved a mean area under the curve (AUC) of 0.877 during training and demonstrated consistent performance in both internal (AUC 0.86) and external validation sets (AUC 0.83). Identified key predictors included SINI, clinical T-stage, and tumor size, supporting tailored treatment strategies.