TY - JOUR
T1 - Discovering and Visualizing Disease-Specific Electrocardiogram Features Using Deep Learning
T2 - Proof-of-Concept in Phospholamban Gene Mutation Carriers
AU - van de Leur, Rutger R
AU - Taha, Karim
AU - Bos, Max N
AU - van der Heijden, Jeroen F
AU - Gupta, Deepak
AU - Cramer, Maarten J
AU - Hassink, Rutger J
AU - van der Harst, Pim
AU - Doevendans, Pieter A
AU - Asselbergs, Folkert W
AU - van Es, René
PY - 2021/2
Y1 - 2021/2
N2 - BACKGROUND: ECG interpretation requires expertise and is mostly based on physician recognition of specific patterns, which may be challenging in rare cardiac diseases. Deep neural networks (DNNs) can discover complex features in ECGs and may facilitate the detection of novel features which possibly play a pathophysiological role in relatively unknown diseases. Using a cohort of PLN (phospholamban) p.Arg14del mutation carriers, we aimed to investigate whether a novel DNN-based approach can identify established ECG features, but moreover, we aimed to expand our knowledge on novel ECG features in these patients.METHODS: A DNN was developed on 12-lead median beat ECGs of 69 patients and 1380 matched controls and independently evaluated on 17 patients and 340 controls. Differentiating features were visualized using Guided Gradient Class Activation Mapping++. Novel ECG features were tested for their diagnostic value by adding them to a logistic regression model including established ECG features.RESULTS: The DNN showed excellent discriminatory performance with a c-statistic of 0.95 (95% CI, 0.91-0.99) and sensitivity and specificity of 0.82 and 0.93, respectively. Visualizations revealed established ECG features (low QRS voltages and T-wave inversions), specified these features (eg, R- and T-wave attenuation in V2/V3) and identified novel PLN-specific ECG features (eg, increased PR-duration). The logistic regression baseline model improved significantly when augmented with the identified features (P<0.001).CONCLUSIONS: A DNN-based feature detection approach was able to discover and visualize disease-specific ECG features in PLN mutation carriers and revealed yet unidentified features. This novel approach may help advance diagnostic capabilities in daily practice.
AB - BACKGROUND: ECG interpretation requires expertise and is mostly based on physician recognition of specific patterns, which may be challenging in rare cardiac diseases. Deep neural networks (DNNs) can discover complex features in ECGs and may facilitate the detection of novel features which possibly play a pathophysiological role in relatively unknown diseases. Using a cohort of PLN (phospholamban) p.Arg14del mutation carriers, we aimed to investigate whether a novel DNN-based approach can identify established ECG features, but moreover, we aimed to expand our knowledge on novel ECG features in these patients.METHODS: A DNN was developed on 12-lead median beat ECGs of 69 patients and 1380 matched controls and independently evaluated on 17 patients and 340 controls. Differentiating features were visualized using Guided Gradient Class Activation Mapping++. Novel ECG features were tested for their diagnostic value by adding them to a logistic regression model including established ECG features.RESULTS: The DNN showed excellent discriminatory performance with a c-statistic of 0.95 (95% CI, 0.91-0.99) and sensitivity and specificity of 0.82 and 0.93, respectively. Visualizations revealed established ECG features (low QRS voltages and T-wave inversions), specified these features (eg, R- and T-wave attenuation in V2/V3) and identified novel PLN-specific ECG features (eg, increased PR-duration). The logistic regression baseline model improved significantly when augmented with the identified features (P<0.001).CONCLUSIONS: A DNN-based feature detection approach was able to discover and visualize disease-specific ECG features in PLN mutation carriers and revealed yet unidentified features. This novel approach may help advance diagnostic capabilities in daily practice.
KW - Adult
KW - Calcium-Binding Proteins/genetics
KW - DNA Mutational Analysis
KW - DNA/genetics
KW - Deep Learning
KW - Electrocardiography
KW - Female
KW - Heart Diseases/diagnosis
KW - Humans
KW - Male
KW - Mutation
KW - Retrospective Studies
U2 - https://doi.org/10.1161/CIRCEP.120.009056
DO - https://doi.org/10.1161/CIRCEP.120.009056
M3 - Article
C2 - 33401921
SN - 1941-3149
VL - 14
SP - e009056
JO - Circulation. Arrhythmia and electrophysiology
JF - Circulation. Arrhythmia and electrophysiology
IS - 2
ER -