Application of Artificial Intelligence to the Electrocardiogram

Zachi I. Attia; David M. Harmon; Elijah R. Behr; Paul A. Friedman

Eur Heart J. 2021;42(46):4717-4730.

Abstract and Introduction

Abstract

Artificial intelligence (AI) has given the electrocardiogram (ECG) and clinicians reading them super-human diagnostic abilities. Trained without hard-coded rules by finding often subclinical patterns in huge datasets, AI transforms the ECG, a ubiquitous, non-invasive cardiac test that is integrated into practice workflows, into a screening tool and predictor of cardiac and non-cardiac diseases, often in asymptomatic individuals. This review describes the mathematical background behind supervised AI algorithms, and discusses selected AI ECG cardiac screening algorithms including those for the detection of left ventricular dysfunction, episodic atrial fibrillation from a tracing recorded during normal sinus rhythm, and other structural and valvular diseases. The ability to learn from big data sets, without the need to understand the biological mechanism, has created opportunities for detecting non-cardiac diseases as COVID-19 and introduced challenges with regards to data privacy. Like all medical tests, the AI ECG must be carefully vetted and validated in real-world clinical environments. Finally, with mobile form factors that allow acquisition of medical-grade ECGs from smartphones and wearables, the use of AI may enable massive scalability to democratize healthcare.

Graphical Abstract

(Enlarge Image)

The application of artificial intelligence to the standard electrocardiogram enables it to diagnose conditions not previously identifiable by an electrocardiogram, or to do so with a greater performance than previously possible.

Table 1. Summary of artificial intelligence electrocardiogram algorithms and their performance and characteristics
Model	Author/Group	Test geography hospital vs. development	Prospective or retrospective	Number of patients tested	Disease prevalence (%)	Description of controls	Hardware specification (12 lead vs. other; specify manufactures/performance of 12 lead)	Bias analysis: population reporting (age, sex, race, other)	AUC	Sensitivity (%)	Specificity (%)
LVSD/HF	Attia et al. ² Mayo	All Mayo Clinic Sites	Retrospective	52 870	7.8	Low EF confirmed by TTE	12 Lead ECG (GE-Marquette)	No formal analysis	0.93	86.3	85.7
LVSD/HF	Attia et al. ¹⁸ Mayo	All Mayo Clinic Sites	Prospective	3874	7.0	Low EF confirmed by TTE or HF prediction by NT-proBNP	12 Lead ECG (GE-Marquette)	No formal analysis	0.918	82.5	86.8
LVSD/HF	Adedinsewo et al. ¹⁹ Mayo	All Mayo Clinic Sites	Retrospective	1606	10.2	Low EF confirmed by TTE	12 Lead ECG (GE-Marquette)	Age, Sex	0.89	73.8	87.3
LVSD/HF	Noseworthy et al. ²⁰ Mayo	All Mayo Clinic Sites	Retrospective	52 870	7.8	Low EF confirmed by TTE	12 Lead ECG (GE-Marquette)	Race	>0.93 in all groups tested	—	—
LVSD/HF	Attia et al. ²¹ Mayo	Mayo Rochester	Prospective	100	7	Low EF confirmed by TTE	AI-enhanced ECG-enabled stethoscope (Eko); single lead	No formal analysis	0.906	—	—
LVSD/HF	Attia et al. ²² Mayo/Multi-Institution	Know Your Heart Sites (Russia)	Retrospective	4277	0.6	Low EF confirmed by TTE	12 Lead ECG (Cardiax; IMED Ltd, Hungary)	Age, sex	0.82	26.9	97.4
LVSD/HF	Cho et al. ²³ Sejong/Korea	Mediplex/Sejong (Korea)	Retrospective	IV-2908 EV-4176	6.8	Low EF confirmed by echo	12 Lead ECG (Page Writer Cardiograph; Philips, Netherlands)	Age, sex, obesity	IV-0.913 EV-0.961	IV-90.5 EV-91.5	IV-75.6 EV-91.1
LVSD/HF	Cho et al. ²³ Sejong/Korea	Mediplex/Sejong (Korea)	Retrospective	IV-2908 EV-4176	6.8	Low EF confirmed by echo	Single lead (LI) from 12 lead ECG (Page Writer Cardiograph; Philips, Netherlands)	Performance of all single leads	IV-0.874 EV-0.929	IV-93.2 EV-92.1	IV-63.2 EV-82.1
LVSD/HF	Kwon et al. ²⁴ Sejong/Korea	Mediplex/Sejong (Korea)	Retrospective	IV-3378 EV-5901	IV-9.7 EV-4.2	Low EF confirmed by echo	12 Lead ECG (Page Writer Cardiograph; Philips, Netherlands)	No formal analysis	IV-0.843 EV-0.889	IV-n/a EV-90	IV-n/a EV-60.4
HCM	Ko et al. ¹³ Mayo	All Mayo Clinic Sites	Retrospective	13 400	4.6	Sex/age matched	12 Lead ECG (GE-Marquette)	Age, sex, ECG finding	0.96	87	90
HCM	Rahman et al. ²⁵ Hopkins Queens (CA)	Hopkins Baltimore	Retrospective	762	29.0	Patients with ICD and CM diagnosis	12 Lead ECG (unspecified)	No formal analysis	RF-0.94 SVM-0.94	RF-87 SVM-0.91	RF-92 SVF-0.91
Hyperkalaemia	Galloway et al. ²⁶ Mayo	All Mayo Clinic Sites	Retrospective	MN-50 099 AZ-5855 FL-6011	MN-2.6 AZ-4.6 FL-4.8	Confirmation by serum potassium	12 Lead ECG (GE-Marquette); 2 Lead evaluation LI/LII	No formal analysis	MN-0.883 AZ-0.853 FL-0.860	MN-90.2 AZ-88.9 FL-91.3	MN-54.7 AZ-55.0 FL-54.7
Sex and age >40 years	Attia et al. ¹ Mayo	All Mayo Clinic Sites	Retrospective	275 056	n/a	Confirmed age/sex in medical record	12 Lead ECG (GE-Marquette)	Co-morbidity impact on ECG age	Sex-0.968 Age-0.94	Sex-n/a Age-87.8	Sex-n/a Age-86.8
Afib	Attia et al. ³ Mayo	All Mayo Clinic Sites	Retrospective	36 280	8.4	Patients without Afib on prior EKG	12 Lead ECG (GE-Marquette)	Analysis with 'window of interest'	0.87	79.0	79.5
Afib	Tison et al. ²⁷ UCSF	Remote study; UCSF	Prospective	9750	3.4	12 lead EKG diagnosis of Afib	Apple Watch photoplethysmography (Apple Inc.)	No formal analysis	0.97	98.0	90.2
Afib	Hill et al. ²⁸ UK-Multi-institution	UK	Retrospective	2 994 837	3.2	CHARGE-AF score	Time-varying neural network; based on clinic data and risk scores	No formal analysis	0.827	75.0	74.9
Afib	Jo et al. ²⁹ Sejong/Korea	Multiple sites (Korea)	Retrospective	IV-6287 EV-38 018	IV-13 EV-6.0	Patients without afib	12 lead, 6 lead, and single lead ECG (unspecified)	No formal analysis	IV/EV for 12,6, single lead all >0.95	All >98%	All >99%
Afib	Poh et al. ³⁰ Boston	Hong Kong	Retrospective	1013	2.8	Patients without afib	Photoplethysmographic pulse waveform	No formal analysis	0.997	97.6	96.5
Afib	Raghunath et al. ³¹	Geisinger Clinic, PA, USA	Retrospective	1.6M		Patients without afib	12 lead ECG	Age, sex, race analysed	0.85	69	81
Long QT (>500 ms)	Giudicessi et al. ³² Mayo	Mayo Clinic Rochester	Both; prospective data reported	686	3.6	QT expert/lab over-read of 12 lead ECGs	6 lead smartphone-enabled ECG (AliveCor Kardia Mobile 6L)	No formal analysis	0.97	80.0	94.4
Long QT	Bos et al. ³³ Mayo	Mayo Clinic Rochester	Retrospective	2059	47	Patients without LQTS	12 Lead ECG (GE-Marquette)	LQTS genotype subgroup analysis	0.900	83.7	80.6
Multiple Pathologies	Tison et al. ³⁴ UCSF	UCSF	Retrospective	36 816 (ECGs)	HCM-27.4 PAH-29.8 Amyloid-28.3 MVP-21.0	Individual pathologies determined by standard care (i.e. echo, biopsy)	12 Lead ECG (GE-Marquette)	No formal analysis	HCM-0.91 PAH-0.94 Amyloid-0.86 MVP-0.77	—	—
Mod-Sev AS	Cohen-Shelly et al. ⁶ Mayo	All Mayo Clinic Sites	Retrospective	102 926	3.7	Mod-Sev AS confirmed by TTE	12 Lead ECG (GE-Marquette)	Age, sex	0.85	78	74
Significant AS	Kwon et al. ⁷ Sejong/Korea	Mediplex/Sejong (Korea)	Retrospective	IV-6453 EV-10 865	IV-3.8 EV-1.7	Significant AS confirmed by echo	12 Lead ECG (Unspecified)	No formal analysis	IV-0.884 EV-0.861	IV-80.0 EV-80.0	IV-81.4 EV-78.3
Significant AS	Kwon et al. ⁷ Sejong/Korea	Mediplex/Sejong (Korea)	Retrospective	IV-6453 EV-10 865	IV-3.8 EV-1.7	Significant AS confirmed by echo	Single lead (L2) from 12 lead ECG (unspecified)	No formal analysis	IV-0.845 EV-0.821	—	—
Mod-Sev MR	Kwon et al. ³⁵ Sejong/Korea	Mediplex/Sejong (Korea)	Retrospective	IV-3174 EV-10 865	IV-n/a EV-3.9	Mod-Sev MR confirmed by echo	12 Lead ECG (Unspecified)	No formal analysis	IV 0.816 EV 0.877	IV 0.900 EV 0.901	IV 0.533 EV 0.699
Mod-Sev MR	Kwon et al. ³⁵ Sejong/Korea	Mediplex/Sejong (Korea)	Retrospective	IV-3174 EV-10 865	IV-n/a EV 3.9	Mod-Sev MR confirmed by echo	Single lead (aVR) from 12 lead ECG (unspecified)	No formal analysis	IV 0.758 EV 0.850	IV 0.900 EV 0.901	IV 0.408 EV 0.560

Afib, atrial fibrillation; AI, artificial intelligence; AUC, area under the curve; AZ, Arizona; CA, Canada; ECG, electrocardiogram; echo, echocardiography; EV, external validation; FL, Florida; HCM, hypertrophic cardiomyopathy; HF, heart failure; ICD, implantable cardiac defibrillator; IV, internal validation; LVSD, left ventricular systolic dysfunction; LQTS, long QT syndrome; MN, Minnesota; mod-sev AS, moderate to severe aortic stenosis; mod-sev MR, moderate to severe mitral regurgitation; MVP, mitral valve prolapse; NT-proBNP, N-terminus of brain natriuretic peptide; PAH, pulmonary arterial hypertension; RF, random forest classifier; SVM, support vector machine classifier; TTE, transthoracic echocardiogram.