IMPORTANCEPhysicians commonly hospitalize patients presenting to the emergency department (ED) with acute pulmonary embolism (PE), despite eligibility for safe outpatient management. Risk stratification using electronic health record-embedded clinical decision support systems can aid physician site-of-care decision-making and increase safe outpatient management. The long-term sustainability of early improvements after the cessation of trial-based, champion-led promotion is uncertain. OBJECTIVE To evaluate the sustainability of recommended site-of-care decision-making support 4 years after initial physician champion-led interventions to increase outpatient management for patients with acute PE. DESIGN, SETTING, AND PARTICIPANTS This retrospective cohort study was conducted in 21 US community hospitals in an integrated health system. Participants included adult patients presenting to the ED with acute PE. Study sites had participated in an original decision-support intervention trial 4 years prior to the current study period: 10 sites were intervention sites, 11 sites were controls.In that trial, decision support with champion promotion resulted in significantly higher outpatient management at intervention sites compared with controls. After trial completion, all study sites were given continued access to a modified decision-support tool without further champion-led outreach.Data were analyzed from January 2019 to February 2020.EXPOSURES ED treatment with a modified clinical decision support tool. MAIN OUTCOMES AND MEASURESThe main outcome was frequency of outpatient management, defined as discharge home directly from the ED, stratified by the PE Severity Index. The safety measure of outpatient care was 7-day PE-related hospitalization. RESULTSThis study included 1039 patients, including 533 (51.3%) women, with a median (IQR) age of 65 (52-74) years. Nearly half (474 patients [45.6%]) were rated lower risk on the PE Severity Index.Overall, 278 patients (26.8%) were treated as outpatients, with only four 7-day PE-related hospitalizations (1.4%; 95% CI, 0.4%-3.6%). The practice gap in outpatient management created by the earlier trial persisted in the outpatient management for patients with lower risk: 109 of 236 patients (46.2%) at former intervention sites vs 81 of 238 patients (34.0%) at former control sites (difference, 12.2; [95% CI, 3.4-20.9] percentage points; P = .007), with wide interfacility variation (range, 7.1%-47.1%). CONCLUSIONS AND RELEVANCEIn this cohort study, a champion-led, decision-support intervention to increase outpatient management for patients presenting to the ED with acute pulmonary embolism was associated with sustained higher rates of outpatient management 4 years (continued) Key Points Question Were the outcomes associated with a physician championled, electronic health record-embedded clinical decision support intervention for risk-stratifying adults presenting at the emergency department (ED) with acute pulmonary embolism sustained 4 years after initial promotion? Findings In this coh...