Automatic Classification of Full- and Reduced-Lead Electrocardiograms Using Morphological Feature Extraction

Research output: Contribution to book/conference proceedings/anthology/reportConference contributionContributedpeer-review


Cardiovascular diseases are the global leading cause of death. Automated electrocardiogram (ECG) analysis can support clinicians to identify abnormal excitation of the heart and prevent premature cardiovascular death. An explainable classification is particularly important for support systems. Our contribution to the PhysioNet/CinC Challenge 2021 (team name: ibmtPeakyFinders) therefore pursues an approach that is based on interpretable features to be as explainable as possible. To meet the challenge goal of developing an algorithm that works for both 12-lead and reduced lead ECGs, we processed each lead separately. We focused on signal processing techniques based on template delineation that yield the template's fiducial points to take the ECG waveform morphology into account. In addition to beat intervals and amplitudes obtained from the template, various heart rate variability and QT interval variability features were extracted and supplemented by signal quality indices. Our classification approach utilized a decision tree ensemble in a one-vs-rest approach. The model parameters were determined using an extensive grid search. Our approach achieved challenge scores of 0.47, 0.47, 0.34, 0.40, and 0.41 on hidden 12-, 6-, 3-, 4-, and 2-lead test sets, respectively, which corresponds to the ranks 12, 10, 23, 18, and 16 out of 39 teams.


Original languageEnglish
Title of host publication48th Conference Computing in Cardiology (CinC)
PublisherWiley-IEEE Press
Number of pages4
ISBN (print)978-1-6654-6721-6
Publication statusPublished - 15 Sept 2021


Title2021 Computing in Cardiology (CinC)
Abbreviated titleCinC 2021
Conference number48
Duration12 - 15 September 2021
Degree of recognitionInternational event
LocationHotel Passage & online
CountryCzech Republic

External IDs

Scopus 85124741157
ORCID /0000-0001-6754-5257/work/142232821
ORCID /0000-0003-4012-0608/work/142235699
ORCID /0000-0002-1984-580X/work/142257671


Sustainable Development Goals


  • Heart, Signal processing algorithms, Morphology, Electrocardiography, Lead, Signal processing, Feature extraction, Classification algorithms, Decision trees, Heart rate variability