. Author manuscript; available in PMC: 2019 Oct 9.

Published in final edited form as: Nat Med. 2019 Jan 7;25(1):65–69. doi: 10.1038/s41591-018-0268-3

Table 2:

Deep Neural Network algorithm and cardiologist sensitivity compared to the cardiologist committee consensus, with specificity fixed at the average specificity level achieved by cardiologists.

	Specificity	Average Cardiologist Sensitivity	DNN Algorithm Sensitivity
Atrial Fibrillation & Flutter	0.941	0.710	0.861
Atrio-ventricular Block	0.981	0.731	0.858
Bigeminy	0.996	0.829	0.921
Ectopic Atrial Rhythm	0.993	0.380	0.445
Idioventricular Rhythm	0.991	0.611	0.867
Junctional Rhythm	0.984	0.634	0.729
Noise	0.983	0.749	0.803
Sinus Rhythm	0.859	0.901	0.950
Supraventricular Tachycardia	0.983	0.408	0.487
Trigeminy	0.995	0.832	0.961
Ventricular Tachycardia	0.996	0.652	0.702
Wenckebach	0.986	0.541	0.651