Continual learning framework for a multicenter study with an application to electrocardiogram

BMC Medical Informatics and Decision Making
Junmo Kim1, Min Hyuk Lim2, Kwangsoo Kim2, Hyung‐Jin Yoon1
1Interdisciplinary Program in Bioengineering, Seoul National University, Seoul, Republic of Korea
2Transdisciplinary Department of Medicine and Advanced Technology, Seoul National University Hospital, Seoul, Republic of Korea

Tóm tắt

AbstractDeep learning has been increasingly utilized in the medical field and achieved many goals. Since the size of data dominates the performance of deep learning, several medical institutions are conducting joint research to obtain as much data as possible. However, sharing data is usually prohibited owing to the risk of privacy invasion. Federated learning is a reasonable idea to train distributed multicenter data without direct access; however, a central server to merge and distribute models is needed, which is expensive and hardly approved due to various legal regulations. This paper proposes a continual learning framework for a multicenter study, which does not require a central server and can prevent catastrophic forgetting of previously trained knowledge. The proposed framework contains the continual learning method selection process, assuming that a single method is not omnipotent for all involved datasets in a real-world setting and that there could be a proper method to be selected for specific data. We utilized the fake data based on a generative adversarial network to evaluate methods prospectively, not ex post facto. We used four independent electrocardiogram datasets for a multicenter study and trained the arrhythmia detection model. Our proposed framework was evaluated against supervised and federated learning methods, as well as finetuning approaches that do not include any regulation to preserve previous knowledge. Even without a central server and access to the past data, our framework achieved stable performance (AUROC 0.897) across all involved datasets, achieving comparable performance to federated learning (AUROC 0.901).

Từ khóa


Tài liệu tham khảo

Rieke N, et al. The future of digital health with federated learning. Npj Digit Med. 2020;3(1):119. https://doi.org/10.1038/s41746-020-00323-1.

Kaissis GA, et al. Secure, privacy-preserving and federated machine learning in medical imaging. Nat Mach Intell. 2020;2(6):305–11. https://doi.org/10.1038/s42256-020-0186-1.

Nguyen DC, et al. Federated learning for smart healthcare: a survey. ACM Comput Surv (CSUR). 2022;55(3):1–37. https://doi.org/10.1145/3501296.

Liu X, et al. Federated Neural Architecture Search for Medical Data Security. IEEE Trans Industr Inf. 2022;18(8):5628–36. https://doi.org/10.1109/TII.2022.3144016.

Sarma KV, et al. Federated learning improves site performance in multicenter deep learning without data sharing. J Am Med Inform Assoc. 2021;28(6):1259–64. https://doi.org/10.1093/jamia/ocaa341.

Ye D, et al. Federated Learning in Vehicular Edge Computing: a selective Model Aggregation Approach. IEEE Access. 2020;8:23920–35. https://doi.org/10.1109/ACCESS.2020.2968399.

Wang KIK, et al. Federated Transfer learning based Cross-domain Prediction for Smart Manufacturing. IEEE Trans Industr Inf. 2022;18(6):4088–96. https://doi.org/10.1109/TII.2021.3088057.

Cui X, Lu S, Kingsbury B. Federated Acoustic Modeling for Automatic Speech Recognition. in ICASSP 2021–2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2021.

Zhang C, et al. A survey on federated learning. Knowl Based Syst. 2021;216:106775. https://doi.org/10.1016/j.knosys.2021.106775.

Lange MD, et al. A continual learning survey: defying forgetting in classification tasks. IEEE Trans Pattern Anal Mach Intell. 2022;44(7):3366–85. https://doi.org/10.1109/TPAMI.2021.3057446.

Chen Z, Liu B. Lifelong machine learning. Synthesis lectures on Artificial Intelligence and Machine Learning. 2018. 12(3):1–207.

Zheng J, et al. A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patients. Sci Data. 2020;7(1):48. https://doi.org/10.1038/s41597-020-0386-x.

Wagner P, et al. Sci Data. 2020;7(1):154. https://doi.org/10.1038/s41597-020-0495-6. PTB-XL, a large publicly available electrocardiography dataset.

Perez Alday EA, et al. Classification of 12-lead ECGs: the PhysioNet/Computing in Cardiology Challenge 2020. Physiol Meas. 2020;41(12):124003. https://doi.org/10.1088/1361-6579/abc960.

Liu F, et al. An open access database for evaluating the algorithms of electrocardiogram rhythm and morphology abnormality detection. J Med Imaging Health Inf. 2018;8(7):1368–73. https://doi.org/10.1166/jmihi.2018.2442.

McMahan B, et al. Communication-efficient learning of deep networks from decentralized data. Artificial intelligence and statistics. PMLR; 2017.

Yang Q, et al. Federated Machine Learning: Concept and Applications. ACM Trans Intell Syst Technol. 2019;10(2).): p. Article 12 https://doi.org/10.1145/3298981.

Mermillod M, Bugaiska A, BONIN P. The stability-plasticity dilemma: investigating the continuum from catastrophic forgetting to age-limited learning effects. Front Psychol. 2013;4. https://doi.org/10.3389/fpsyg.2013.00504.

Grossberg S. Nonlinear neural networks: principles, mechanisms, and architectures. Neural Netw. 1988;1(1):17–61. https://doi.org/10.1016/0893-6080(88)90021-4.

Lopez-Paz D, Ranzato MA. Gradient episodic memory for continual learning. Adv Neural Inf Process Syst. 2017;30.

Rebuffi S-A et al. icarl: Incremental classifier and representation learning. in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2017.

Shin H et al. Continual learning with deep generative replay. Adv Neural Inf Process Syst. 2017;30.

Li Z, Hoiem D. Learning without forgetting. IEEE Trans Pattern Anal Mach Intell. 2018;40(12):2935–47. https://doi.org/10.1109/TPAMI.2017.2773081.

Kirkpatrick J, et al. Overcoming catastrophic forgetting in neural networks. Proc Natl Acad Sci. 2017;114(13):3521–6. https://doi.org/10.1073/pnas.1611835114.

Aljundi R et al. Memory aware synapses: Learning what (not) to forget. in Proceedings of the European conference on computer vision (ECCV). 2018.

Mallya A, Lazebnik S, Packnet. Adding multiple tasks to a single network by iterative pruning. in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2018.

Goodfellow I, et al. Generative adversarial networks. Commun ACM. 2020;63(11):139–44. https://doi.org/10.1145/3422622.

Arjovsky M, Chintala S, Bottou L, Wasserstein Generative Adversarial Networks, in Proceedings of the 34th International Conference on Machine Learning, Doina P, Yee Whye T. Editors. 2017, PMLR: Proceedings of Machine Learning Research. p. 214–223.

Gulrajani I et al. Improved training of Wasserstein Gans. Adv Neural Inf Process Syst. 2017;30.

Donahue C, McAuley J, Puckette M. Adversarial audio synthesis. arXiv Preprint arXiv:1802 04208. 2018. https://doi.org/10.48550/arXiv.1802.04208.

Thambawita V, et al. DeepFake electrocardiograms using generative adversarial networks are the beginning of the end for privacy issues in medicine. Sci Rep. 2021;11(1):21896. https://doi.org/10.1038/s41598-021-01295-2.

Ghanem RN, et al. Heart-surface reconstruction and ECG electrodes localization using fluoroscopy, epipolar geometry and stereovision: application to noninvasive imaging of cardiac electrical activity. IEEE Trans Med Imaging. 2003;22(10):1307–18. https://doi.org/10.1109/TMI.2003.818263.

Kwon J-m, et al. A deep learning algorithm to detect anaemia with ECGs: a retrospective, multicentre study. Lancet Digit Health. 2020;2(7):e358-e367. https://doi.org/10.1016/S2589-7500(20)30108-4.

Lin C, et al. Point-of-care artificial intelligence-enabled ECG for dyskalemia: a retrospective cohort analysis for accuracy and outcome prediction. Npj Digit Med. 2022;5(1):8. https://doi.org/10.1038/s41746-021-00550-0.

Raghunath S, et al. Deep neural networks can predict new-onset atrial fibrillation from the 12-lead ECG and help identify those at risk of atrial fibrillation–related stroke. Circulation. 2021;143(13):1287–98. https://doi.org/10.1161/CIRCULATIONAHA.120.047829.

Kiyasseh D, Zhu T, Clifton DA. CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients, in Proceedings of the 38th International Conference on Machine Learning, M. Marina and Z. Tong, Editors. 2021, PMLR: Proceedings of Machine Learning Research. p. 5606–5615.

Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network. arXiv Preprint arXiv:1503 02531. 2015. https://doi.org/10.48550/arXiv.1503.02531.

Pascanu R, Bengio Y. Revisiting natural gradient for deep networks. arXiv Preprint arXiv:1301 3584. 2013. https://doi.org/10.48550/arXiv.1301.3584.

Kwon Jm, et al. Artificial intelligence for detecting electrolyte imbalance using electrocardiography. Ann Noninvasive Electrocardiol. 2021;26(3):e12839. https://doi.org/10.1111/anec.12839.

Kim B-H, Pyun J-Y. Identification for personal authentication using LSTM-Based deep recurrent neural networks. Sensors. 2020;20. https://doi.org/10.3390/s20113069.

Li Y, et al. Toward improving ECG biometric identification using cascaded convolutional neural networks. Neurocomputing. 2020;391:83–95. https://doi.org/10.1016/j.neucom.2020.01.019.

Mirza M, et al. Mechanisms of arrhythmias and conduction disorders in older adults. Clin Geriatr Med. 2012;28(4):555–73. https://doi.org/10.1016/j.cger.2012.08.005.

Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014 https://doi.org/10.48550/arXiv.1412.6980.

Li T, et al. Federated optimization in heterogeneous networks. Proc Mach Learn Syst. 2020;2:429–50.

Hwang H et al. Towards the Practical Utility of Federated Learning in the Medical Domain, in Proceedings of the Conference on Health, Inference, and Learning, J.M. Bobak, Editors. 2023, PMLR: Proceedings of Machine Learning Research. p. 163–181.

Sheta A, et al. Diagnosis of obstructive sleep apnea from ECG signals using machine learning and deep learning classifiers. Appl Sci. 2021;11. https://doi.org/10.3390/app11146622.

Thông tin
Thông tin xuất bản

BMC Medical Informatics and Decision Making

Thông tin tác giả