Time-to-Event Supervised Genetic Algorithm Enables Induction Chemotherapy Decision Making for Nasopharyngeal Carcinoma

Do nasopharyngeal carcinoma (NPC) patients benefit from induction chemotherapy (IC)? This problem is of great clinical interest; however, it difficult to obtain an accurate and interpretable model inform IC decisions for NPC patients. In this study, a time-to-event supervised genetic algorithm was developed decision-making algorithm, the fitness function directly related time-to-event, which reflects therapeutic effect NPC. Then, optimal models are obtained by stability validation analysis. The comprehensive determined feature analysis using “or” operation. overall survival non-IC vs. in potential group 63.4% 81.5%, with p = 0.020, exhibited good generalization ability. However, benefits OS according current NCCN guidelines limited (p > 0.05). None possible processes LASSO we tried could significant validated testing cohort. proposed method provides construction process, reasonable data grouping strategy, concise experimental design, convenient application. Moreover, will develop toolkit treatment research facilitate use clinicians provide technical support precision medicine.