Demonstration of the potential of white-box machine learning approaches to gain insights from cardiovascular disease electrocardiograms
Open accessThe DOI matches its Crossref record; 59 of the 60 references it cites were found in a registry or an index, and 1 are not checked yet.
Abstract
We present the results from a white-box machine learning approach to detect cardiac arrhythmias using electrocardiographic data. A C5.0 is trained to recognize four classes using common features. The four classes are (i) atrial fibrillation and atrial flutter, (ii) tachycardias (iii), sinus bradycardia and (iv) sinus rhythm. Data from 10,646 subjects, 83% of whom have at least one arrhythmia and 17% of whom exhibit a normal sinus rhythm, are used. The C5.0 is trained using 10-fold cross-validation and is able to achieve a balanced accuracy of 95.35%. By using the white-box machine learning approach, a clear and comprehensible tree structure can be revealed, which has selected the 5 most important features from a total of 24 features. These 5 features are ventricular rate, RR-Interval variation, atrial rate, age and difference between longest and shortest RR-Interval. The combination of ventricular rate, RR-Interval variation and atrial rate is especially relevant to achieve classification accuracy, which can be disclosed through the tree. The tree assigns unique values to distinguish the classes. These findings could be applied in medicine in the future. It can be shown that a white-box machine learning approach can reveal granular structures, thus confirming known linear relationships and also revealing nonlinear relationships. To highlight the strength of the C5.0 with respect to this structural revelation, the results of further white-box machine learning and black-box machine learning algorithms are presented.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures








Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Other methods are gradient based, like saliency maps,68 and calculate the contribution of each input pixel to the overall classification performance.”
From Addressing bias in big data and AI for health care: A call for open science (2021) · cites this paper as [68]
In the citing paper
“As an example, transparent techniques like decision trees, relying on interpretable features, can provide a “white-box” approach for diagnosis.68”
From Addressing bias in big data and AI for health care: A call for open science (2021) · cites this paper as [68]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 4×
“A wrong decision in medicine can have serious consequences for the patient; therefore, high transparency and interpretability in the decision making process are important [6].”
BackgroundInfluentialGulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016) · JAMA · doi:10.1001/jama.2016.17216 · Cited by 7,697
January, C. T., Wann, L. S., Alpert, J. S., Calkins, H., Cigarroa, J. E., Cleveland, J. C., Conti, J. B., Ellinor, P. T., Ezekowitz, M. D., Field, M. E., et al. (2014) · Circulation · doi:10.1161/cir.0000000000000041 · Cited by 7,115
2016 ESC Guidelines for the management of atrial fibrillation developed in collaboration with EACTS
Kirchhof, P., Benussi, S., Kotecha, D., Ahlsson, A., Atar, D., Casadei, B., Castella, M., Diener, H.-C., Heidbuchel, H., Hendriks, J., et al. (2016) · Europace · doi:10.1093/europace/euw295 · Cited by 6,439
Hannun, A. Y., Rajpurkar, P., Haghpanahi, M., Tison, G. H., Bourn, C., Turakhia, M. P., & Ng, A. Y. (2019) · Nature Medicine · doi:10.1038/s41591-018-0268-3 · Cited by 3,148 · cited 1×
“The detection of cardiovascular diseases is extremely complex in everyday clinical practice [1].”
Background2014 AHA/ACC/HRS Guideline for the Management of Patients With Atrial Fibrillation
January, C. T., Wann, L. S., Alpert, J. S., Calkins, H., Cigarroa, J. E., Cleveland, J. C., Conti, J. B., Ellinor, P. T., Ezekowitz, M. D., Field, M. E., et al. (2014) · Journal of the American College of Cardiology · doi:10.1016/j.jacc.2014.03.022 · Cited by 2,955
Ting, D. S. W., Cheung, C. Y.-L., Lim, G., Tan, G. S. W., Quang, N. D., Gan, A., Hamzah, H., Garcia-Franco, R., San Yeo, I. Y., Lee, S. Y., et al. (2017) · JAMA · doi:10.1001/jama.2017.18152 · Cited by 2,402
Definitions, methods, and applications in interpretable machine learning
Murdoch, W. J., Singh, C., Kumbier, K., Abbasi-Asl, R., & Yu, B. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1900654116 · Cited by 2,167 · cited 1×
“Stability is of high relevance for ML models, especially for white-box ML models, where reliable information is to be obtained directly from the models [56].”
BackgroundNew ideas about atrial fibrillation 50 years on
Nattel, S. (2002) · Nature · doi:10.1038/415219a · Cited by 1,481 · cited 1×
“Class 0 can also lead to significantly increased heartbeat [16, 42].”
Background2016 ESC Guidelines for the management of atrial fibrillation developed in collaboration with EACTS
Kirchhof, P., Benussi, S., Kotecha, D., Ahlsson, A., Atar, D., Casadei, B., Castella, M., Diener, H.-C., Heidbuchel, H., Hendriks, J., et al. (2016) · European Journal of Cardio-Thoracic Surgery · doi:10.1093/ejcts/ezw313 · Cited by 1,403 · cited 2×
“Together with the fact that class 0 is well detected, this can be seen as a further confirmation of the suitability of the rules used in practice and science [16, 17].”
Background
Cited by
Ali, S., Abuhmed, T., El-Sappagh, S., Muhammad, K., Alonso-Moral, J. M., Confalonieri, R., Guidotti, R., Del Ser, J., Díaz-Rodríguez, N., & Herrera, F. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101805 · Cited by 1,762
Addressing bias in big data and AI for health care: A call for open science
Norori, N., Hu, Q., Aellen, F. M., Faraci, F. D., & Tzovara, A. (2021) · Patterns · doi:10.1016/j.patter.2021.100347 · Cited by 903
“niques like decision trees, relying on interpretable features, can provide a ‘‘white-box’’ approach for diagnosis.(68) The field of computer vision has dedicated a substantial effort in obtaining interpretable features and understanding the process of classification.”
BackgroundA Comprehensive Survey on Artificial Intelligence Empowered Edge Computing on Consumer Electronics
Syu, J.-H., Lin, J. C.-W., Srivastava, G., & Yu, K. (2023) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2023.3318150 · Cited by 212
“XAI refers to understandable and transparent explanations of the AI decision-making process [52], and can further verify existing knowledge, challenge existing knowledge, and generate new knowledge [53].”
BackgroundAlugubelli, N. R., Abuissa, H. S., & Róka, A. (2022) · Sensors · doi:10.3390/s22228903 · Cited by 172
Explainable AI decision model for ECG data of cardiac disorders
Anand, A., Kadian, T., Shetty, M. K., & Gupta, A. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.103584 · Cited by 154
Machine learning and artificial intelligence in neuroscience: A primer for researchers
Badrulhisham, F., Pogatzki-Zahn, E. M., Segelcke, D., Spisák, T., & Vollert, J. (2023) · Brain Behavior and Immunity · doi:10.1016/j.bbi.2023.11.005 · Cited by 126
“XAIs aim to be transparent, interpretable and explainable, features which would make them ideal for assisted decision making in healthcare (Rieg et al., 2020).”
Khan, F. S., Mazhar, S. S., Mazhar, K., AlSaleh, D., & Mazhar, A. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11215-9 · Cited by 151
Moreno-Sánchez, P. A., Isla, G. G., Corino, V., Vehkaoja, A. T., Brukamp, K., van Gils, M., & Mainardi, L. T. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108235 · Cited by 122
Heart rate variability for medical decision support systems: A review
Faust, O., Hong, W., Loh, H. W., Xu, S., Tan, R., Chakraborty, S., Barua, P. D., Molinari, F., & Acharya, U. R. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105407 · Cited by 91
Ackermann, M., & Haase, C. (2022) · Additive manufacturing · doi:10.1016/j.addma.2023.103585 · Cited by 49
Verhaeghe, J., Corte, T. D., Sauer, C. M., Hendriks, T., Thijssens, O., Ongenae, F., Elbers, P., Waele, J. J. D., & Hoecke, S. V. (2023) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2023.105086 · Cited by 34
Mumtaz, H., Saqib, M., Jabeen, S., Muneeb, M., Mughal, W., Sohail, H., Safdar, M., Mehmood, Q., Khan, M. A., & Ismail, S. M. (2023) · Frontiers in Medicine · doi:10.3389/fmed.2023.1227168 · Cited by 33
“When the results were validated using signals from various records, each of which had a 1,000-data-point interval and contained at least four heartbeats, they showed very high correlation values for several common ECG parameters, including PR intervals of 0.984 +/ − 0.021, QRS intervals of 1+/ − SD, QT intervals of 0.…”
BackgroundMethodInfluentialExplainable Artificial Intelligence (XAI) Approaches in Predictive Maintenance: A Review
Sharma, J., Mittal, M. L., Soni, G., & Keprate, A. (2023) · Recent Patents on Engineering · doi:10.2174/1872212118666230417084231 · Cited by 26
A Systematic Literature Review on Transfer Learning for 3D-CNNs
Klaiber, M., Sauter, D., Baumgartl, H., & Buettner, R. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533302 · Cited by 24
“While TL for 3D CNNs has been applied for various medical use cases, its applicability has to be proven in further areas with latent constructs like personality [103, 104] or diseases like alcoholism [105] and different types of data like eye-tracking [106] or EEG [107].”
BackgroundSelf-citationNelson, A. R., Christiansen, S. L. M., Naegle, K. M., & Saucerman, J. J. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2303513121 · Cited by 23
“Motivated by “white - box” machine learning strategies that combine mechanistic models with machine learning (29, 30), we designed a logic - based mechanistic machine learning (LogiMML) model to predict key regulators that conduct signaling from network model inputs and simulated drugs to…”
Agrawal, R., & Agrawal, R. (2025) · Discover Mental Health · doi:10.1007/s44192-025-00232-3 · Cited by 26
“AI techniques enable (i) the assessment of current knowledge, (ii) the advancement of knowledge, and (iii) the formation of new conjectures and assumptions [15].”
Computational modeling for medical data: From data collection to knowledge discovery
Yin, Y., Xu, S., Hong, Y., Cai, Y., Tang, W., Wang, J., Shen, B., Zong, H., & Yu, G. (2024) · The Innovation Life · doi:10.59717/j.xinn-life.2024.100079 · Cited by 13
Hatanaka, M., Kato, H., Sakai, M., Kariya, K., Nakatani, S., Yoshimura, T., & Inagaki, T. (2023) · The Journal of Physical Chemistry A · doi:10.1021/acs.jpca.3c02179 · Cited by 10
Explainable AI for Next Generation Agriculture—Current Scenario and Future Prospects
Dawar, I., Negi, S., & Chauhan, A. (2024) · Studies in computational intelligence · doi:10.1007/978-3-031-67450-1_7 · Cited by 9
Defect Detection of Metal Nuts Applying Convolutional Neural Networks
Sauter, D., Schmitz, A., Dikici, F., Baumgartl, H., & Buettner, R. (2021) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac51774.2021.00043 · Cited by 9
Self-citationSon, J. G., Shon, H. K., Kim, J., Lee, I., & Lee, T. G. (2024) · Journal of the American Society for Mass Spectrometry · doi:10.1021/jasms.4c00325 · Cited by 7
Breitenbach, J., Raab, D., Fezer, E., Sauter, D., Baumgartl, H., & Buettner, R. (2021) · IEEE International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob) · doi:10.1109/wimob52687.2021.9606314 · Cited by 7
Self-citationThe AI Efficiency Paradox: Reclaiming Quality Patient Care in an Era of Optimization
Burwell, J. M. (2025) · Journal of Medical Systems · doi:10.1007/s10916-025-02183-2 · Cited by 6
“Furthermore, “Black Box” models lack interpretability [ 5 ].”
Penava, P., & Buettner, R. (2025) · Electronic Markets · doi:10.1007/s12525-025-00778-8 · Cited by 7
“When implementing the artifact, the design principle should therefore be to use “white-box” approaches to ensure that the decisions are transparent (Rieg et al., 2020).”
Self-citationPain Level Assessment for Infants Using Facial Expression Scores
Baumgartl, H., Flathau, D., Bayerlein, S., Sauter, D., Timm, I. J., & Buettner, R. (2021) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac51774.2021.00087 · Cited by 3
Self-citationFrassão, K. O., Filho, S. M. S., Pedroso, R. V., Nascimento, C. M. C., Pott, H., Cominetti, M. R., & Fraga, F. J. (2024) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc53108.2024.10782085 · Cited by 3
Romero, P., Lozano, M., Dux‐Santoy, L., Guala, A., Teixidó‐Turà, G., Sebastián, R., & García‐Fernández, I. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109176 · Cited by 2
Interpreting Predictive Models through Causality: A Query-Driven Methodology
Ali, M. H., Biannic, Y. L., & Wuillemin, P.-H. (2023) · Proceedings of the ... International Florida Artificial Intelligence Research Society Conference · doi:10.32473/flairs.36.133387 · Cited by 5
“Indeed, using models in the context of automatic decision-making requires detailed knowledge of their behavior in order to be able to justify the decision; for instance, in the medical domain of automatic prescription, in the legal domain, or in a legal context (Rieg et al. 2020).”
MethodDetecting atrial fibrillation with a wearable device
Sandelin, J., Sirkiä, J., Anzanpour, A., & Koivisto, T. (2022) · Computing in cardiology · doi:10.22489/cinc.2022.184
“35%, but with much more complicated machine learning system [8].”
BackgroundColombo, M. (2023) · Fuzzy management methods · doi:10.1007/978-3-031-42819-7_6
Alvariño-Durán, J., Hernández-Ocaña, B., Hernández-Torruco, J., & Chávez-Bosquez, O. (2024) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-031-62502-2_67
Santhiya, C., Lavanya, R., Chakkaravarthy, G. V., Indira, K., Subashini, S., & Mohammed Fayaz, A. (2025) · International Conference on Computational Robotics, Testing and Engineering Evaluation (ICCRTEE) · doi:10.1109/iccrtee64519.2025.11052857
Yıldırım, B., Alsan, H. F., & Arsan, T. (2026) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3798051
Metadata
- Authors
- Rieg, T., Frick, J., Baumgartl, H., & Buettner, R.
- Affiliations
- Hochschule Aalen (DE)
- Corresponding author
- Rieg, Thilo
- Venue
- PLOS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2020-12-17
- Volume
- 15
- Issue
- 12
- Pages
- e0243615
- ISSN
- 1932-6203 (ISSN-L)
- PMC
- PMC7746264
- OpenAlex
- W3112230406
- Cited by
- 34
- References
- 59
- Citations by year
- 2026: 1 · 2025: 5 · 2024: 9 · 2023: 9 · 2022: 5 · 2021: 5
- FWCI
- 2.94
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- PLoS ONE (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- OPUS (Aalen University) (submittedVersion)
- Funders
- Carl-Zeiss-Stiftung
- Bundesministerium für Bildung und Forschung
- Topics
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Cardiac electrophysiology and arrhythmias
- Keywords
- arrhythmia detection, electrocardiogram, C5.0 decision tree, atrial fibrillation, atrial flutter, tachycardia, sinus bradycardia, ventricular rate, atrial rate, feature selection, cardiovascular disease
- MeSH terms
- Machine Learning, Adult, Aged, Aged, 80 and over, Algorithms, Arrhythmias, Cardiac, Electrocardiography, Female, Humans, Male, Middle Aged
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.