Can Early Symptom Reports Improve Risk Prediction in Pediatric Leukemia

Kids with leukemia can experience different side effects from treatments, so this project can use baseline and week-one PRO, mixed with basic clinical information, to identify higher-risk casesduring the following 30 days. I created 3,000 simulated pediatric leukemia records and comparedlogistic regression, random forest, and gradient boosting models. On 600 simulated records that werenot used, logistic regression did the best with a ROC-AUC of 0.915 and 92% sensitivity, showing thepotential of PRO-based risk prediction but still needing validation with real patient data.