Zachi I Attia1, Suraj Kapa1, Xiaoxi Yao2,3, Francisco Lopez-Jimenez1, Tarun L Mohan1, Patricia A Pellikka1, Rickey E Carter4, Nilay D Shah2,3, Paul A Friedman1, Peter A Noseworthy1,3. 1. Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota. 2. Department of Health Sciences Research, Division of Health Care Policy and Research, Mayo Clinic, Rochester, Minnesota. 3. Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery, Mayo Clinic, Rochester, Minnesota. 4. Division of Biomedical Statistics and Informatics, Health Sciences Research, Mayo Clinic College of Medicine, Jacksonville, Florida.
Abstract
OBJECTIVES: We sought to validate a deep learning algorithm designed to predict an ejection fraction (EF) less than or equal to 35% based on the 12-lead electrocardiogram (ECG) in a large prospective cohort. BACKGROUND: Patients undergoing routine ECG may have undetected left ventricular (LV) dysfunction that warrants further echocardiographic assessment. However, identification of these patients can be challenging. METHODS: We applied the algorithm to all ECGs interpreted by the Mayo Clinic ECG laboratory in September 2018. The performance of the algorithm was tested among patients with recent echocardiographic assessments of LV function. We also applied the algorithm in patients with no recent echocardiographic assessments of LV function to determine the rate of new "positive screens." RESULTS: Among 16 056 adult patients who underwent routine ECG, 8600 (age 67.1 ± 15.2 years, 45.6% male), had a transthoracic echocardiogram (TTE) and 3874 patients had a TTE and ECG less than 1 month apart. Among these patients, the algorithm was able to detect an EF less than or equal to 35% with 86.8% specificity, 82.5% sensitivity, and 86.5% accuracy, (area under the curve, 0.918). Among 474 "false-positives screens," 189 (39.8%) had an EF of 36% to 50%. Among patients with no prior TTE, the algorithm identified 3.5% of the patients with suspected EF less than or equal to 35%. Exploratory analysis suggests false positives could be reduced by assessing NT-pro-BNP after the initial "positive screen." CONCLUSIONS: A deep learning algorithm detected depressed LV function with good accuracy in routine practice. Further studies are needed to validate the algorithm in patients with no prior echocardiogram and to assess the impact on echocardiography utilization, cost, and clinical outcomes.
OBJECTIVES: We sought to validate a deep learning algorithm designed to predict an ejection fraction (EF) less than or equal to 35% based on the 12-lead electrocardiogram (ECG) in a large prospective cohort. BACKGROUND:Patients undergoing routine ECG may have undetected left ventricular (LV) dysfunction that warrants further echocardiographic assessment. However, identification of these patients can be challenging. METHODS: We applied the algorithm to all ECGs interpreted by the Mayo Clinic ECG laboratory in September 2018. The performance of the algorithm was tested among patients with recent echocardiographic assessments of LV function. We also applied the algorithm in patients with no recent echocardiographic assessments of LV function to determine the rate of new "positive screens." RESULTS: Among 16 056 adult patients who underwent routine ECG, 8600 (age 67.1 ± 15.2 years, 45.6% male), had a transthoracic echocardiogram (TTE) and 3874 patients had a TTE and ECG less than 1 month apart. Among these patients, the algorithm was able to detect an EF less than or equal to 35% with 86.8% specificity, 82.5% sensitivity, and 86.5% accuracy, (area under the curve, 0.918). Among 474 "false-positives screens," 189 (39.8%) had an EF of 36% to 50%. Among patients with no prior TTE, the algorithm identified 3.5% of the patients with suspected EF less than or equal to 35%. Exploratory analysis suggests false positives could be reduced by assessing NT-pro-BNP after the initial "positive screen." CONCLUSIONS: A deep learning algorithm detected depressed LV function with good accuracy in routine practice. Further studies are needed to validate the algorithm in patients with no prior echocardiogram and to assess the impact on echocardiography utilization, cost, and clinical outcomes.
Authors: Albert K Feeny; Mina K Chung; Anant Madabhushi; Zachi I Attia; Maja Cikes; Marjan Firouznia; Paul A Friedman; Matthew M Kalscheur; Suraj Kapa; Sanjiv M Narayan; Peter A Noseworthy; Rod S Passman; Marco V Perez; Nicholas S Peters; Jonathan P Piccini; Khaldoun G Tarakji; Suma A Thomas; Natalia A Trayanova; Mintu P Turakhia; Paul J Wang Journal: Circ Arrhythm Electrophysiol Date: 2020-07-06
Authors: Daniel Sierra-Lara Martinez; Peter A Noseworthy; Oguz Akbilgic; Joerg Herrmann; Kathryn J Ruddy; Abdulaziz Hamid; Ragasnehith Maddula; Ashima Singh; Robert Davis; Fatma Gunturkun; John L Jefferies; Sherry-Ann Brown Journal: Am Heart J Plus Date: 2022-04-01
Authors: Peter A Noseworthy; Zachi I Attia; LaPrincess C Brewer; Sharonne N Hayes; Xiaoxi Yao; Suraj Kapa; Paul A Friedman; Francisco Lopez-Jimenez Journal: Circ Arrhythm Electrophysiol Date: 2020-02-16
Authors: Anthony H Kashou; Peter A Noseworthy; Christopher V DeSimone; Abhishek J Deshmukh; Samuel J Asirvatham; Adam M May Journal: J Am Heart Assoc Date: 2020-05-19 Impact factor: 5.501
Authors: I Tonhajzerova; I Ondrejka; N Ferencova; I Bujnakova; M Grendar; L B Olexova; I Hrtanek; Z Visnovcova Journal: Physiol Res Date: 2021-06-01 Impact factor: 1.881
Authors: Patrik Bachtiger; Carla M Plymen; Punam A Pabari; James P Howard; Zachary I Whinnett; Felicia Opoku; Stephen Janering; Aldo A Faisal; Darrel P Francis; Nicholas S Peters Journal: Card Fail Rev Date: 2020-05-12
Authors: Adetola O Ladejobi; Jessica Cruz; Zachi I Attia; Martin van Zyl; Jason Tri; Francisco Lopez-Jimenez; Peter A Noseworthy; Paul A Friedman; Suraj Kapa; Samuel J Asirvatham Journal: Cardiovasc Digit Health J Date: 2020-08-28