InSight Care Pilot Program: Redefining Seeing a Patient.

PURPOSE: Early detection and management of symptoms in patients with cancer improves outcomes. However, the optimal approach to symptom monitoring and management is unknown. InSight Care is a mobile health intervention that captures symptom data and facilitates patient-provider communication to mitigate symptom escalation. PATIENTS AND METHODS: Patients initiating antineoplastic treatment at a Memorial Sloan Kettering regional location were eligible. Technology supporting the program included the following: a predictive model that identified patient risk for a potentially preventable acute care visit; a secure patient portal enabling communication, televisits, and daily delivery of patient symptom assessments; alerts for concerning symptoms; and a symptom-trending application. The main outcomes of the pilot were feasibility and acceptability evaluated through enrollment and response rates and symptom alerts, and perceived value evaluated on the basis of qualitative patient and provider interviews. RESULTS: The pilot program enrolled 100 high-risk patients with solid tumors and lymphoma (29% of new treatment starts v goal of 25%). Over 6 months of follow-up, the daily symptom assessment response rate was 56% (the goal was 50%), and 93% of patients generated a severe symptom alert. Patients and providers perceived value in the program, and archetypes were developed for program improvement. Enrolled patients were less likely to use acute care than were other high-risk patients. CONCLUSION: InSight Care was feasible and holds the potential to improve patient care and decrease facility-based care. Future work should focus on optimizing the cadence of patient assessments, the workforce supporting remote symptom management, and the return of symptom data to patients and clinical teams.

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.