A recent study aimed to develop and validate predictive models for identifying patients with cancer at high risk of experiencing acute care events (ACEs), such as emergency department visits and hospitalizations, after receiving systemic anticancer treatment. The study analyzed data from a cohort of patients with cancer and found that factors such as age, chemotherapy type, cancer diagnosis, and prior ACEs were predictive of ACEs. Three predictive models were created, with the simplest model achieving a C-statistic of 0.79, sensitivity of 0.28, and specificity of 0.93. Researchers concluded that these models offer a broad application for cancer care organizations to identify high-risk patients and allocate resources effectively to reduce ACEs during cancer treatment.

Reference: Stein JN, Dunham L, Wood WA, Ray E, Sanoff H, Elston-Lafata J. Predicting Acute Care Events Among Patients Initiating Chemotherapy: A Practice-Based Validation and Adaptation of the PROACCT Model. JCO Oncol Pract. 2023;19(8):577-585. doi: 10.1200/OP.22.00721.