DFML: Dynamic Federated Meta-Learning for Rare Disease Prediction
Authors: 
Bingyang Chen, Tao Chen, Xingjie Zeng, Weishan Zhang, Qinghua Lu, Zhaoxiang Hou, Jiehan Zhou, Sumi HelalAuthors Info & Claims
Pages 880 - 889
Abstract
Millions of patients suffer from rare diseases around the world. However, the samples of rare diseases are much smaller than those of common diseases. Hospitals are usually reluctant to share patient information for data fusion due to the sensitivity of medical data. These challenges make it difficult for traditional AI models to extract rare disease features for disease prediction. In this paper, we propose a Dynamic Federated Meta-Learning (DFML) approach to improve rare disease prediction. We design an Inaccuracy-Focused Meta-Learning (IFML) approach that dynamically adjusts the attention to different tasks according to the accuracy of base learners. Additionally, a dynamic weight-based fusion strategy is proposed to further improve federated learning, which dynamically selects clients based on the accuracy of each local model. Experiments on two public datasets show that our approach outperforms the original federated meta-learning algorithm in accuracy and speed with as few as five shots. The average prediction accuracy of the proposed model is improved by 13.28% compared with each hospital's local model.
References
[1]
X. Zhou, Y. Li, and W. Liang, “CNN-RNN based intelligent recommendation for online medical pre-diagnosis support,” IEEE/ACM Trans. Comput. Biol. Bioinf., vol. 18, no. 3, pp. 912–921, May/Jun. 2021.
[2]
X. Zhou, W. Liang, K. Wang, and S. Shimizu, “Multi-modality behavioral influence analysis for personalized recommendations in health social media environment,” IEEE Trans. Comput. Social Syst., vol. 6, no. 5, pp. 888–897, Oct. 2019.
[3]
J. Jia, R. Wang, Z. An, Y. Guo, X. Ni, and T. Shi, “RDAD: A machine learning system to support phenotype-based rare disease diagnosis,” Front. Genet., vol. 9, pp. 1–10, Dec. 2018.
[4]
E. Choi, A. Schuetz, and W. F. Stewart, “Using recurrent neural network models for early detection of heart failure onset,” J. Amer. Med. Inform. Assoc., vol. 24, no. 2, pp. 361–370, 2017.
[5]
V. K. R. Chimmula and L. Zhang, “Time series forecasting of COVID-19 transmission in Canada using LSTM networks,” Chaos Solitons Fractals, vol, vol. 135, 2020, Art. no.
[6]
M. C. Younis, “Evaluation of deep learning approaches for identification of different corona-virus species and time series prediction,” Computerized Med. Imag. Graph., vol. 90, 2021, Art. no.
[7]
F. Ali et al., “A smart healthcare monitoring system for heart disease prediction based on ensemble deep learning and feature fusion,” Inf. Fusion, vol. 63, pp. 208–222, 2020.
[8]
N. Nnamoko and I. Korkontzelos, “Efficient treatment of outliers and class imbalance for diabetes prediction,” Artif. Intell. Med., vol. 104, 2020, Art. no.
[9]
X. S. Zhang et al., “MetaPred: Meta-learning for clinical risk prediction with limited patient electronic health records,” in Proc. 25th ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, 2019, pp. 2487–2495.
[10]
C. Finn, P. Abbeel, and S. Levine, “Model-agnostic meta-learning for fast adaptation of deep networks,” in Proc. Int. Conf. Mach. Learn., 2017, pp. 1126–1135.
[11]
H. B. McMahan et al., “Federated learning of deep networks using model averaging,” 2016,.
[12]
F. Chen et al., “Federated meta-learning with fast convergence and efficient communication,” 2018,.
[13]
L. I. Fan-Zhang et al., “A survey on recent advances in meta-learning,” Chin. J. Comput., vol. 44, no. 2, pp. 422–446, 2021.
[14]
O. Vinyals et al., “Matching networks for one shot learning,” in Proc. Adv. Neural Inf. Process. Syst., 2016, pp. 3630–3638.
[15]
F. Sung, Y. Yang, L. Zhang, P. H. S. Torr, and T. M. Hospedales, “Learning to compare: Relation network for few-shot learning,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2018, pp. 1199–1208.
[16]
V. Naumova, S. V. Pereverzyev, and S. Sivananthan, “A meta-learning approach to the regularized learning—Case study: Blood glucose prediction,” Neural Netw., vol. 33, pp. 181–193, 2012.
[17]
Z. Li et al., “Meta-SGD: Learning to learn quickly for few-shot learning,” 2017,.
[18]
X. Li et al., “Difficulty-aware meta-learning for rare disease diagnosis,” in Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervention, 2020, pp. 357–366.
[19]
V. Mothukuri, P. Khare, R. M. Parizi, S. Pouriyeh, A. Dehghantanha, and G. Srivastava, “Federated learning-based anomaly detection for IoT security attacks,” IEEE Internet Things J., vol. 9, no. 4, pp. 2545–2554, Feb. 2022.
[20]
D. Połap et al., “Federated learning model with augmentation and samples exchange mechanism,” in Proc. Int. Conf. Artif. Intell. Soft Comput., 2021, pp. 214–223.
[21]
X. Zhou, W. Liang, J. Ma, Z. Yan, and K. I.-K. Wang, “2D federated learning for personalized human activity recognition in cyber-physical-social systems,” IEEE Trans. Netw. Sci. Eng., vol. 9, no. 6, pp. 3934–3944, Nov./Dec. 2022.
[22]
X. Zhou, W. Liang, J. She, Z. Yan, and K. Wang, “Two-layer federated learning with heterogeneous model aggregation for 6G supported internet of vehicles,” IEEE Trans. Veh. Technol., vol. 70, no. 6, pp. 5308–5317, Jun. 2021.
[23]
J. Xu et al., “Federated learning for healthcare informatics,” J. Healthcare Inform. Res., vol. 5, no. 1, pp. 1–19, 2021.
[24]
W. Zhang et al., “Blockchain-based federated learning for device failure detection in industrial IoT,” IEEE Internet Things J., vol. 8, no. 7, pp. 5926–5937, Apr. 2021.
[25]
S. K. Lo et al., “A systematic literature review on federated machine learning: From a software engineering perspective,” ACM Comput. Surveys, vol. 54, no. 5, pp. 1–39, 2021.
[26]
N. Rieke et al., “The future of digital health with federated learning,” NPJ Digit. Med., vol. 3, no. 1, pp. 1–7, 2020.
[27]
J. Li et al., “A federated learning based privacy-preserving smart healthcare system,” IEEE Trans. Ind. Inform., vol. 18, no. 3, pp. 2021–2031, Mar. 2022.
[28]
T. S. Brisimi et al., “Federated learning of predictive models from federated electronic health records,” Int. J. Med. Inform., vol. 112, pp. 59–67, 2018.
[29]
S. Boughorbel et al., “Federated uncertainty-aware learning for distributed hospital EHR data,” 2019,.
[30]
W. Zhang et al., “Dynamic fusion-based federated learning for COVID-19 detection,” IEEE Internet Things J., vol. 8, no. 21, pp. 15884–15891, Nov. 2021.
[31]
A. Fallah, A. Mokhtari, and A. Ozdaglar, “Personalized federated learning: A meta-learning approach,” 2020,.
[32]
Y. Jiang et al., “Improving federated learning personalization via model agnostic meta learning,” 2019,.
[33]
A. Fallah, A. Mokhtari, and A. Ozdaglar, “Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach,” in Proc. Adv. Neural Inf. Process. Syst., 2020, pp. 3557–3568.
[34]
W. Zheng et al., “Federated meta-learning for fraudulent credit card detection,” in Proc. Int. Joint Conf. Artif. Intell., 2020, pp. 4654–4660.
[35]
T. Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in Proc. IEEE Int. Conf. Comput. Vis., 2017, pp. 2980–2988.
[36]
G. B. Moody and R. G. Mark, “The impact of the MIT-BIH Arrhythmia Database,” IEEE Eng. Med. Biol., vol. 20, no. 3, pp. 45–50, May/Jun. 2001.
[37]
X. Li et al., “On the convergence of FedAvg on non-IID data,” 2019,.
Recommendations
Deep learning for rare disease: A scoping review
Graphical abstractDisplay Omitted
AbstractAlthough individually rare, collectively more than 7,000 rare diseases affect about 10% of patients. Each of the rare diseases impacts the quality of life for patients and their families, and incurs significant societal costs. The low prevalence ...
Chronic disease prediction using administrative data and graph theory: The case of type 2 diabetes
Highlights- Administrative healthcare data is used to identify high-risk chronic patients.
- Graph theory and social network analysis concepts were used to understand the disease progression.
- Prediction framework showed between 82% to 87% ...
AbstractClinical diagnosis and regular monitoring of the population at risk of chronic diseases is clinically and financially resource-intensive. Mining administrative data could be an effective alternative way to identify this high-risk cohort. In this ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
1545-5963 © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.
Publisher
IEEE Computer Society Press
Washington, DC, United States
Publication History
Published: 26 January 2023
Published in TCBB Volume 21, Issue 4
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 8Total Downloads
- Downloads (Last 12 months)8
- Downloads (Last 6 weeks)8
Reflects downloads up to 01 Oct 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in