Association Between Remote Monitoring and Acute Care Visits in High-Risk Patients Initiating Intravenous Antineoplastic Therapy.

PURPOSE: Traditional oncology care models have not effectively identified and managed at-risk patients to prevent acute care. A next step is to harness advances in technology to enable patients to report symptoms any time, enabling digital hovering-intensive symptom monitoring and management. Our objective was to evaluate a digital platform that identifies and remotely monitors high-risk patients initiating antineoplastic therapy with the goal of preventing acute care visits. METHODS: This was a single-institution matched cohort quality improvement study conducted at a National Cancer Institute-designated cancer center between January 1, 2019, and March 31, 2020. Eligible patients were those initiating intravenous antineoplastic therapy who were identified as high risk for seeking acute care. Enrolled patients' symptoms were monitored using a digital platform. A dedicated team of clinicians managed reported symptoms. The primary outcomes of emergency department visits and hospitalizations within 6 months of treatment initiation were analyzed using cumulative incidence analyses with a competing risk of death. RESULTS: Eighty-one patients from the intervention arm were matched by stage and disease with contemporaneous high-risk control patients. The matched cohort had similar baseline characteristics. The cumulative incidence of an emergency department visit for the intervention cohort was 0.27 (95% CI, 0.17 to 0.37) at six months compared with 0.47 (95% CI, 0.36 to 0.58) in the control (P = .01) and of an inpatient admission was 0.23 (95% CI, 0.14 to 0.33) in the intervention cohort versus 0.41 (95% CI, 0.30 to 0.51) in the control (P = .02). CONCLUSION: The narrow employment of technology solutions to complex care delivery challenges in oncology can improve outcomes and innovate care. This program was a first step in using a digital platform and a remote team to improve symptom care for high-risk patients.

Building a Clinically Relevant Risk Model: Predicting Risk of a Potentially Preventable Acute Care Visit for Patients Starting Antineoplastic Treatment.

PURPOSE: To create a risk prediction model that identifies patients at high risk for a potentially preventable acute care visit (PPACV). PATIENTS AND METHODS: We developed a risk model that used electronic medical record data from initial visit to first antineoplastic administration for new patients at Memorial Sloan Kettering Cancer Center from January 2014 to September 2018. The final time-weighted least absolute shrinkage and selection operator model was chosen on the basis of clinical and statistical significance. The model was refined to predict risk on the basis of 270 clinically relevant data features spanning sociodemographics, malignancy and treatment characteristics, laboratory results, medical and social history, medications, and prior acute care encounters. The binary dependent variable was occurrence of a PPACV within the first 6 months of treatment. There were 8,067 observations for new-start antineoplastic therapy in our training set, 1,211 in the validation set, and 1,294 in the testing set. RESULTS: A total of 3,727 patients experienced a PPACV within 6 months of treatment start. Specific features that determined risk were surfaced in a web application, riskExplorer, to enable clinician review of patient-specific risk. The positive predictive value of a PPACV among patients in the top quartile of model risk was 42%. This quartile accounted for 35% of patients with PPACVs and 51% of potentially preventable inpatient bed days. The model C-statistic was 0.65. CONCLUSION: Our clinically relevant model identified the patients responsible for 35% of PPACVs and more than half of the inpatient beds used by the cohort. Additional research is needed to determine whether targeting these high-risk patients with symptom management interventions could improve care delivery by reducing PPACVs.