Machine learning-based approach to the risk assessment of potentially preventable outpatient cancer treatment-related emergency care and hospitalizations.

Abstract

333 Background: Patients undergoing outpatient infusion chemotherapy for cancer are at risk for potentially preventable, unplanned acute care in the form of emergency department (ED) visits and hospital admissions. This can impact outcomes, patient decisions, and costs to the patient and healthcare system. To address this need, the Centers for Medicare & Medicaid Services developed the Chemotherapy Measure (OP-35). Recent randomized controlled data indicate that electronic health record (EHR)-based machine learning (ML) approaches accurately direct supportive care to reduce acute care during radiotherapy. As this may extend to systemic therapy, this study aims to develop and evaluate ML approaches to predict the risk of OP-35 qualifying, potentially preventable acute care within 30 days of infusional systemic therapy. Methods: This study included data from UCSF cancer patients receiving infusional chemotherapy from July 1, 2017, to February 11, 2021, (total 7,068 patients over 84,174 treatments). The data incorporated into the ML included 430 EHR-derived variables, including cancer diagnosis, therapeutic agents, laboratory values, vital signs, medications, and encounter history. Three ML approaches were trained to predict an OP-35 acute care risk following a systemic therapy infusion with least absolute shrinkage selection operator (LASSO), random forest, and gradient boosted trees (GBT; XGBoost) approaches. The models were trained on a subset (75% of patients; before October 12, 2019) of the dataset and validated on a mutually exclusive subset (25% patients; after October 12, 2019) based on the receiver operating characteristic (ROC) curves and calibration plots. Results: There were 1,651 total acute care visits (244 ED visits and 1,407 ED visits converted into hospitalization); 1,310 infusions included a qualifying acute care visit (200 with ED visits only, 0 direct hospital admissions, and 1,110 with both ED visit and hospitalization). Each ML approach demonstrated good performance in the internal validation cohort, with GBT (AUC 0.805) outpacing the random forest (0.750) and LASSO logistic regression (0.755) approaches. Visualization of calibration plots verified concordance between predicted and observed rates of acute care. All three models shared patient age and days elapsed since last treatment as important contributors. Conclusions: EHR-based ML approaches demonstrate high predictive ability for OP-35 qualifying acute care rates on a per-infusion basis, identifying 30-day potentially preventable acute care risk for patients undergoing chemotherapy. Prospective validation of these models is ongoing. Early prediction can facilitate interventional strategies which may reduce acute care, improve health outcomes, and reduce costs.