During the lockdown of universities and the COVID-Pandemic most students were restricted to their homes. Novel and instigating teaching methods were required to improve the learning experience and so recent implementations of the annual PhysioNet/Computing in Cardiology (CinC) Challenges posed as a reference. For over 20 years, the challenges have proven repeatedly to be of immense educational value, besides leading to technological advances for specific problems. In this paper, we report results from the class 'Artificial Intelligence in Medicine Challenge', which was implemented as an online project seminar at Technical University Darmstadt, Germany, and which was heavily inspired by the PhysioNet/CinC Challenge 2017 'AF Classification from a Short Single Lead ECG Recording'. Atrial fibrillation is a common cardiac disease and often remains undetected. Therefore, we selected the two most promising models of the course and give an insight into the Transformer-based DualNet architecture as well as into the CNN-LSTM-based model and finally a detailed analysis for both. In particular, we show the model performance results of our internal scoring process for all submitted models and the near state-of-the-art model performance for the two named models on the official 2017 challenge test set. Several teams were able to achieve F1scores above/close to 90% on a hidden test-set of Holter recordings. We highlight themes commonly observed among participants, and report the results from the self-assessed student evaluation. Finally, the self-assessment of the students reported a notable increase in machine learning knowledge.

Department of Biomedical Engineering Georgia Institute of Technology United States of America

Department of Biomedical Informatics Emory University United States of America

Institute of Scientific Instruments of the Czech Academy of Sciences Brno Czech Republic

KIS*MED AI Systems in Medicine Technische Universität Darmstadt Darmstadt Germany

Medical Data Transfer s r o Brno Czech Republic

Zobrazit více v PubMed

Clifford G D, Liu C, Moody B, Li-wei H L, Silva I, Li Q, Johnson A, Mark R G. AF classification from a short single lead ecg recording: the physionet/computing in cardiology challenge 2017. 2017 Computing in Cardiology (CinC). IEEE; 2017. pp. pp 1–4. PubMed DOI PMC

Colombari R, D’Amico E, Paolucci E. Can challenge-based learning be effective online? a case study using experiential learning theory. CERN IdeaSquare J. Exp. Innovation. 2021;5:40–8. doi: 10.23726/cij.2021.1287. DOI

Couceiro R, Carvalho P, Henriques J, Antunes M, Harris M, Habetha J. Detection of atrial fibrillation using model-based ECG analysis. 2008 19th Int. Conf. on Pattern Recognition. IEEE; 2008. pp. pp 1–5. DOI

Datta S, Puri C, Mukherjee A, Banerjee R, Choudhury A D, Singh R, Ukil A, Bandyopadhyay S, Pal A, Khandelwal S. Identifying normal, af and other abnormal ecg rhythms using a cascaded binary classifier. 2017 Computing in Cardiology (cinc). IEEE; 2017. pp. pp 1–4. DOI

de Vries H, Strub F, Mary J, Larochelle H, Pietquin O, Courville A. Modulating early visual processing by language. Advances in Neural Information Processing Systems; 2017. pp. pp 6597–607.

Goodfellow I, Bengio Y, Courville A, Bengio Y. Deep Learning. Vol. 1. Cambridge: MIT Press; 2016. DOI

Hamilton P S. Open source ECG analysis. Computers in Cardiology. IEEE; 2002. pp. pp 101–4. DOI

Harris C R, et al. Array programming with NumPy. Nature. 2020;585:357–62. doi: 10.1038/s41586-020-2649-2. PubMed DOI PMC

Hatamian F N, Ravikumar N, Vesal S, Kemeth F P, Struck M, Maier A. The effect of data augmentation on classification of atrial fibrillation in short single-lead ecg signals using deep neural networks. ICASSP 2020-2020 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP); 2020. pp. pp 1264–8. DOI

He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proc. IEEE Conf. on Computer Vision and Pattern Recognition; 2016. pp. pp 770–8. DOI

Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9:1735–80. doi: 10.1162/neco.1997.9.8.1735. PubMed DOI

Hong S, Wu M, Zhou Y, Wang Q, Shang J, Li H, Xie J. ENCASE: An ENsemble ClASsifiEr for ECG classification using expert features and deep. 2017 Computing in Cardiology (CinC). IEEE; 2017. pp. pp 1–4. DOI

Hong S, Xu Y, Khare A, Priambada S, Maher K, Aljiffry A, Sun J, Tumanov A. HOLMES: health online model ensemble serving for deep learning models in intensive care units. Proc. 26th ACM SIGKDD Int. Conf. on Knowledge Discovery & Data Mining; 2020. pp. pp 1614–24. DOI

Hong S, Zhou Y, Wu M, Shang J, Wang Q, Li H, Xie J. Combining deep neural networks and engineered features for cardiac arrhythmia detection from ECG recordings. Physiol. Meas. 2019;40:054009. doi: 10.1088/1361-6579/ab15a2. PubMed DOI

Huang G, Liu Z, Van Der Maaten L, Weinberger K Q. Densely connected convolutional networks. Proc. IEEE Conf. on Computer Vision and Pattern Recognition; 2017. pp. pp 4700–8. DOI

Khriji L, Fradi M, Machhout M, Hossen A. International Conference on Smart Homes and Health Telematics. Berlin: Springer; 2020. Deep learning-based approach for atrial fibrillation detection; pp. pp 100–13. DOI

Legaki N Z, Xi N, Hamari J, Karpouzis K, Assimakopoulos V. The effect of challenge-based gamification on learning: an experiment in the context of statistics education. Int. J. Hum. Comput. Stud. 2020;144:102496. doi: 10.1016/j.ijhcs.2020.102496. PubMed DOI PMC

Linschmann O, Rohr M, Leonhardt K, Hoog Antink C. 2021 Computing in Cardiology (CinC) Vol. 48. Piscataway, NJ: IEEE; 2021. Multi-label classification of cardiac abnormalities for multi-lead ECG recordings based on auto-encoder features and a neural network classifier. DOI

Lip G Y H, et al. Atrial fibrillation. Nat. Rev. Dis. Primers. 2016:16016. doi: 10.1038/nrdp.2016.16. PubMed DOI

Liu L, Jiang H, He P, Chen W, Liu X, Gao J, Han J. On the variance of the adaptive learning rate and beyond. Int. Conf. on Learning Representations.2020.

Mashrur F R, Roy A D, Saha D K. Automatic identification of arrhythmia from ecg using alexnet convolutional neural network. 2019 4th Int. Conf. on Electrical Information and Communication Technology (EICT). IEEE; 2019. pp. pp 1–5. DOI

Moody G, Mark R. The impact of the MIT-BIH Arrhythmia Database. IEEE Eng. Med. Biol. Mag. 2001;20:45–50. doi: 10.1109/51.932724. PubMed DOI

Mousavi S, Afghah F, Razi A, Acharya U R. ECGNET: learning where to attend for detection of atrial fibrillation with deep visual attention. 2019 IEEE EMBS Int. Conf. on Biomedical & Health Informatics (BHI). IEEE; 2019. pp. pp 1–4. PubMed DOI PMC

Nah F F H, Zeng Q, Telaprolu V R, Ayyappa A P, Eschenbrenner B. International Conference on HCI in Business. Berlin: Springer; 2014. Gamification of education: a review of literature; pp. pp 401–9. DOI

Nonaka N, Seita J. Data augmentation for electrocardiogram classification with deep neural network. 2020 arXiv: 200904398 .

Paszke A, et al. PyTorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst.; 2019. pp. 8026–8037. DOI

Perez L, Wang J. The effectiveness of data augmentation in image classification using deep learning. Convolutional Neural Networks Vis. Recognit. 2017;11:1–8. arXiv: 171204621 .

Plesinger F, Nejedly P, Viscor I, Halamek J, Jurak P. Parallel use of a convolutional neural network and bagged tree ensemble for the classification of holter ECG. Physiol. Meas. 2018;39:094002. doi: 10.1088/1361-6579/aad9ee. PubMed DOI

Prangemeier T, Wildner C, Françani A O, Reich C, Koeppl H. Multiclass yeast segmentation in microstructured environments with deep learning. 2020 IEEE Conf. on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB); 2020. pp. pp 1–8. DOI

Reich C, Prangemeier T, Cetin O ¨, Koeppl H. OSS-Net: memory efficient high resolution semantic segmentation of 3D medical data. British Machine Vision Conf. British Machine Vision Association.2021.

Rohr M, Plesinger F, Bulkova V, Hoog Antink C. 2021 Computing in Cardiology (CinC) Vol. 48. Brno, Czech Republic: IEEE; 2021. Improving machine learning education during the covid-pandemic using past computing in cardiology challenges. DOI

Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015; Berlin. Springer; 2015. pp. 234–41. DOI

Shi X, Chen Z, Wang H, Yeung D Y, Wong W K, Woo W C. Convolutional LSTM Network: a machine learning approach for precipitation nowcasting. Proc. 28th Int. Conf. on Neural Information Processing; 2015. pp. pp 802–10.

Simard P Y, et al. Best practices for convolutional neural networks applied to visual document analysis. Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings; Edinburgh, UK. IEEE; 2003. DOI

Tan S, Androz G, Chamseddine A, Fecteau P, Courville A, Bengio Y, Cohen J P. Icentia11k: an unsupervised representation learning dataset for arrhythmia subtype discovery. 2019 arXiv: 191009570 .

Teijeiro T, García C A, Castro D, Félix P. Abductive Reasoning as a Basis to Reproduce Expert Criteria in ECG Atrial Fibrillation Identification. Physiol. Meas. 2018;39:084006. doi: 10.1088/1361-6579/aad7e4. PubMed DOI

Toda A M, Valle P H, Isotani S. Higher Education for All. Berlin: Springer; 2018. The dark side of gamification: an overview of negative effects of gamification in education; pp. pp 143–56. (From Challenges to Novel Technology-Enhanced Solutions. HEFA 2017). DOI

Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Kaiser L, Polosukhin I. Attention is all you need. Advances in Neural Information Processing Systems; Curran Associates, Inc.; 2017. ( https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf)

Virtanen P, et al. SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat. Methods. 2020;17:261–72. doi: 10.1038/s41592-019-0686-2. PubMed DOI PMC

Wang H, Zhu Y, Green B, Adam H, Yuille A, Chen L C. Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation. Computer Vision – ECCV 2020; Springer; 2020. pp. pp 108–26. DOI

Warrick P A, Homsi M N. Ensembling convolutional and long short-term memory networks for electrocardiogram arrhythmia detection. Physiol. Meas. 2018;39:114002. doi: 10.1088/1361-6579/aad386. PubMed DOI

Xiaolin L, Cardiff B, John D. A 1D convolutional neural network for heartbeat classification from single lead ECG. IEEE ICECS 2020, 27th IEEE Int. Conf. on Electronics Circuits and Systems. IEEE; Glasgow, UK. IEEE; 2020. pp. pp 1–2. DOI

Zabihi M, Rad A B, Katsaggelos A K, Kiranyaz S, Narkilahti S, Gabbouj M. Detection of atrial fibrillation in ecg hand-held devices using a random forest classifier. 2017 Computing in Cardiology (CinC). IEEE; Rennes, France. 2017. pp. pp 1–4. DOI

Zihlmann M, Perekrestenko D, Tschannen M. Convolutional recurrent neural networks for electrocardiogram classification. 2017 Computing in Cardiology (CinC). IEEE; 2017. pp. pp 1–4. DOI