Evaluating the Effect of a COVID-19 Predictive Model to Facilitate Discharge: A Randomized Controlled Trial.

BACKGROUND: We previously developed and validated a predictive model to help clinicians identify hospitalized adults with coronavirus disease 2019 (COVID-19) who may be ready for discharge given their low risk of adverse events. Whether this algorithm can prompt more timely discharge for stable patients in practice is unknown. OBJECTIVES: The aim of the study is to estimate the effect of displaying risk scores on length of stay (LOS). METHODS: We integrated model output into the electronic health record (EHR) at four hospitals in one health system by displaying a green/orange/red score indicating low/moderate/high-risk in a patient list column and a larger COVID-19 summary report visible for each patient. Display of the score was pseudo-randomized 1:1 into intervention and control arms using a patient identifier passed to the model execution code. Intervention effect was assessed by comparing LOS between intervention and control groups. Adverse safety outcomes of death, hospice, and re-presentation were tested separately and as a composite indicator. We tracked adoption and sustained use through daily counts of score displays. RESULTS: Enrolling 1,010 patients from May 15, 2020 to December 7, 2020, the trial found no detectable difference in LOS. The intervention had no impact on safety indicators of death, hospice or re-presentation after discharge. The scores were displayed consistently throughout the study period but the study lacks a causally linked process measure of provider actions based on the score. Secondary analysis revealed complex dynamics in LOS temporally, by primary symptom, and hospital location. CONCLUSION: An AI-based COVID-19 risk score displayed passively to clinicians during routine care of hospitalized adults with COVID-19 was safe but had no detectable impact on LOS. Health technology challenges such as insufficient adoption, nonuniform use, and provider trust compounded with temporal factors of the COVID-19 pandemic may have contributed to the null result. TRIAL REGISTRATION: ClinicalTrials.gov identifier: NCT04570488.

Effects of Real-time Prescription Benefit Recommendations on Patient Out-of-Pocket Costs: A Cluster Randomized Clinical Trial.

Importance: Rising drug costs contribute to medication nonadherence and adverse health outcomes. Real-time prescription benefit (RTPB) systems present prescribers with patient-specific out-of-pocket cost estimates and recommend lower-cost, clinically appropriate alternatives at the point of prescribing. Objective: To investigate whether RTPB recommendations lead to reduced patient out-of-pocket costs for medications. Design, Setting, and Participants: In this cluster randomized trial, medical practices in a large, urban academic health system were randomly assigned to RTPB recommendations from January 13 to July 31, 2021. Participants were adult patients receiving outpatient prescriptions during the study period. The analysis was limited to prescriptions for which RTPB could recommend an available alternative. Electronic health record data were used to analyze the intervention's effects on prescribing. Data analyses were performed from August 20, 2021, to June 8, 2022. Interventions: When a prescription was initiated in the electronic health record, the RTPB system recommended available lower-cost, clinically appropriate alternatives for a different medication, length of prescription, and/or choice of pharmacy. The prescriber could select either the initiated order or one of the recommended options. Main Outcomes and Measures: Patient out-of-pocket cost for a prescription. Secondary outcomes were whether a mail-order prescription and a 90-day supply were ordered. Results: Of 867 757 outpatient prescriptions at randomized practices, 36 419 (4.2%) met the inclusion criteria of having an available alternative. Out-of-pocket costs were $39.90 for a 30-day supply in the intervention group and $67.80 for a 30-day supply in the control group. The intervention led to an adjusted 11.2%; (95% CI, -15.7% to -6.4%) reduction in out-of-pocket costs. Mail-order pharmacy use was 9.6% and 7.6% in the intervention and control groups, respectively (adjusted 1.9 percentage point increase; 95% CI, 0.9 to 3.0). Rates of 90-day supply were not different. In high-cost drug classes, the intervention reduced out-of-pocket costs by 38.9%; 95% CI, -47.6% to -28.7%. Conclusions and Relevance: This cluster randomized clinical trial showed that RTPB recommendations led to lower patient out-of-pocket costs, with the largest savings occurring for high-cost medications. However, RTPB recommendations were made for only a small percentage of prescriptions. Trial Registration: ClinicalTrials.gov Identifier: NCT04940988; American Economic Association Registry: AEARCTR-0006909.