{"stable_id":"304701f2a0cd4f80","slug":"mayo-eagle-ai-ecg-screening","company":"Mayo Clinic primary-care practices","workflow_name":"EAGLE AI-ECG clinical decision support","function_code":"customer_service","pattern_codes":["continuous_decisioning"],"changed_assumption":"A routine ECG can trigger evaluation for asymptomatic low ejection fraction before specialist suspicion.","evidence_strength":"verified","publication_tier":"showcase","freshness":"current","reviewed_at":"2026-08-23","updated_at":"2026-08-22","source_quality_summary":"1 peer reviewed; publication outcomes are verified.","caveat_summary":"Pragmatic cluster-randomized result supports causality for diagnosis, not downstream morbidity or mortality benefit.","freshness_caveat":null,"workflow_summary":{"before":[{"actor":"Primary-care clinician","action":"Order ECGs for routine clinical reasons and evaluate heart failure using usual-care signals.","actor_type":"human"},{"actor":"Clinician","action":"Order echocardiography when symptoms or judgment indicate it.","actor_type":"human"}],"hinge":"A routine ECG can trigger evaluation for asymptomatic low ejection fraction before specialist suspicion.","after":[{"actor":"AI-ECG model","action":"Analyzes routine ECGs and reports high likelihood of low ejection fraction.","actor_type":"ai"},{"actor":"Primary-care clinician","action":"Interprets the AI result and decides whether to order echocardiography and diagnose low EF.","actor_type":"human"}],"decision_mode":"moved","decision_marker":"Selection moves from a fixed rule to the model"},"before":[{"order":1,"actor":"Primary-care clinician","action":"Order ECGs for routine clinical reasons and evaluate heart failure using usual-care signals.","handoff_to":"Patient","control":"Usual care"},{"order":2,"actor":"Clinician","action":"Order echocardiography when symptoms or judgment indicate it.","handoff_to":"Imaging service","control":"Human suspicion"}],"after":[{"order":1,"actor":"AI-ECG model","action":"Analyzes routine ECGs and reports high likelihood of low ejection fraction.","handoff_to":"Primary-care clinician","control":"Positive/negative decision support"},{"order":2,"actor":"Primary-care clinician","action":"Interprets the AI result and decides whether to order echocardiography and diagnose low EF.","handoff_to":"Imaging and treatment pathway","control":"Clinician retains diagnostic authority"}],"decision_rights":"The model flags risk; clinicians decide whether to order an echocardiogram and make the diagnosis.","exception_path":"A positive result does not diagnose low EF; clinicians can decline imaging, and usual care continues for negative results.","removed_work":["Reliance on symptoms alone to surface occult low EF","Untargeted escalation of all routine ECGs to echocardiography"],"outcomes":[{"metric":"New diagnosis of ejection fraction at or below 50% within 90 days","baseline":"1.6% in usual-care control practices","result":"2.1% with clinician access to AI-ECG results; odds ratio 1.32, P=0.007","period":"90 days after routine ECG during the 2019-2020 trial","scale":"22,641 adults, 120 primary-care teams, 45 practices","attribution_caveat":"Pragmatic cluster-randomized result supports causality for diagnosis, not downstream morbidity or mortality benefit.","evidence_label":"verified"}],"executive_lesson":"A low-cost model created value because it changed which existing ECGs triggered confirmatory action, while the clinician retained the diagnosis.","anti_pattern":"Calling the AI output a diagnosis or extrapolating increased case finding to mortality reduction.","questions_for_leaders":["What confirmatory action follows a positive score?","Are we measuring patient outcomes beyond detection?"],"collections":[],"bundle_version":"1.0.0","bundle_fingerprint":"sha256:c23c6cc2b88153d008ea8fda928f632ce0011fc2d4c5036672a16e5d895bab93","canonical_url":"https://brianletort.ai/transformations/mayo-eagle-ai-ecg-screening"}