RESUMO
Study Objective: The use of the HEART score to risk stratify patients for short-term major adverse cardiac events in the emergency department (ED) setting is well established. Although discharge to home for low-risk HEART score patients is widely accepted as safe practice, there are limited outcomes data on moderate-risk HEART score patients discharged to home. We investigated the safety of discharging moderate-risk HEART score patients to home from the ED with established early cardiology follow-up. Methods: We performed a retrospective cohort analysis of patients presenting to the ED with chest pain from April 2020 through December 2020. Patients were evaluated in the ED and underwent serial conventional troponin testing and electrocardiogram (ECG). Clinicians calculated a HEART score and employed shared decision-making with moderate-risk patients (score 4-6), offering hospital admission versus discharge home with a formalized process for rapid cardiology follow-up (within 2 business days). We assessed the frequency of acute myocardial infarction or death at 30 days and before cardiology follow-up. Results: During our study period, 2939 patient encounters were screened for chest pain. Of these, 333 of 547 eligible moderate-risk HEART score patients were referred for rapid follow-up. The median time to follow-up appointment was 2.9 business days (interquartile range 1.3, 6.5), and 264 (79%) of patients kept their follow-up appointment. One patient (0.3%) suffered death within 30 days, before cardiology follow-up. There were no myocardial infarctions. Conclusions: These results suggest that moderate-risk HEART score patients may be considered for discharge from the ED with rapid cardiology follow-up. Formalizing processes to facilitate these early evaluations may represent a viable alternative to hospital admission, without diminishing patient outcomes.
RESUMO
BACKGROUND: Some patients prescribed opioid analgesic (OA) medications for pain experience serious side effects, including dependence, sedation, and overdose. As most patients are at low risk for OA-related harms, risk reduction interventions requiring multiple counseling sessions are impractical on a large scale. OBJECTIVE: This study evaluates whether an intervention based on reinforcement learning (RL), a field of artificial intelligence, learned through experience to personalize interactions with patients with pain discharged from the emergency department (ED) and decreased self-reported OA misuse behaviors while conserving counselors' time. METHODS: We used data representing 2439 weekly interactions between a digital health intervention ("Prescription Opioid Wellness and Engagement Research in the ED" [PowerED]) and 228 patients with pain discharged from 2 EDs who reported recent opioid misuse. During each patient's 12 weeks of intervention, PowerED used RL to select from 3 treatment options: a brief motivational message delivered via an interactive voice response (IVR) call, a longer motivational IVR call, or a live call from a counselor. The algorithm selected session types for each patient each week, with the goal of minimizing OA risk, defined in terms of a dynamic score reflecting patient reports during IVR monitoring calls. When a live counseling call was predicted to have a similar impact on future risk as an IVR message, the algorithm favored IVR to conserve counselor time. We used logit models to estimate changes in the relative frequency of each session type as PowerED gained experience. Poisson regression was used to examine the changes in self-reported OA risk scores over calendar time, controlling for the ordinal session number (1st to 12th). RESULTS: Participants on average were 40 (SD 12.7) years of age; 66.7% (152/228) were women and 51.3% (117/228) were unemployed. Most participants (175/228, 76.8%) reported chronic pain, and 46.2% (104/225) had moderate to severe depressive symptoms. As PowerED gained experience through interactions over a period of 142 weeks, it delivered fewer live counseling sessions than brief IVR sessions (P=.006) and extended IVR sessions (P<.001). Live counseling sessions were selected 33.5% of the time in the first 5 weeks of interactions (95% CI 27.4%-39.7%) but only for 16.4% of sessions (95% CI 12.7%-20%) after 125 weeks. Controlling for each patient's changes during the course of treatment, this adaptation of treatment-type allocation led to progressively greater improvements in self-reported OA risk scores (P<.001) over calendar time, as measured by the number of weeks since enrollment began. Improvement in risk behaviors over time was especially pronounced among patients with the highest risk at baseline (P=.02). CONCLUSIONS: The RL-supported program learned which treatment modalities worked best to improve self-reported OA risk behaviors while conserving counselors' time. RL-supported interventions represent a scalable solution for patients with pain receiving OA prescriptions. TRIAL REGISTRATION: Clinicaltrials.gov NCT02990377; https://classic.clinicaltrials.gov/ct2/show/NCT02990377.
