Feature Contributions to ECG-based Heart-Failure Detection: Deep Learning vs. Statistical Analysis

Computing in cardiology

Abstract

Assessing feature contributions to a specific diagnosis is commonly done by statistical analysis.In the context of heart failure (HF) diagnosis from the electrocardiogram (ECG), this work compares feature contributions assessed by deep learning with those obtained by statistical analysis.Data consists of ECG pairs (baseline and followup) from patients with a history of myocardial infarction.When the follow-up ECG was made, controls patients had remained stable, while cases patients had developed HF.The 42 features that characterized each ECG served as inputs of a deep-learning neural network (NN) created by our Repeated Structuring & Learning Procedure.Subjectspecific feature ranking was obtained from the localinterpretable model-agnostic explanatory algorithm and processed to obtain feature relevances (FR).Additionally, 42 areas under the curve (AUC) by univariate statistical analysis were obtained.FR and AUC were compared by Pearson's correlation coefficient (ρ).After training, the NN had a 99% classification performance.FR ranged from 0.32 to 4.47; AUC ranged from 23% to 82%.Correlation analysis yielded no significant association between AUC and FR (ρ=0.18,.Deep-learning and statistical-analysis feature contributions to HF detection were discordant.Further studies will investigate which of the two approaches better reflects clinical interpretation.

Authors 5

1. Agnese Sbrollini

   Marche Polytechnic University

   Affiliation as printed

   Università Politecnica delle Marche, Ancona, Italy

2. Marjolein C. De Jongh Aachen

   Leiden University Medical Center

   Affiliation as printed

   Leiden University Medical Center , Leiden , Netherlands

   Leiden University Medical Center, Leiden, Netherlands

3. Micaela Morettini

   Marche Polytechnic University

   Affiliation as printed

   Università Politecnica delle Marche , Ancona , Italy

   Università Politecnica delle Marche, Ancona, Italy

4. Laura Burattini

   Marche Polytechnic University

   Affiliation as printed

   Università Politecnica delle Marche , Ancona , Italy

   Università Politecnica delle Marche, Ancona, Italy

5. Cees A. Swenne Aachen

   Leiden University Medical Center

   Affiliation as printed

   Leiden University Medical Center, Leiden, Netherlands