Adoption of Federated Learning for Healthcare Informatics: Emerging Applications and Future Directions
The smart healthcare system has improved the patients quality of life (QoL), where the records are being analyzed remotely by distributed stakeholders. It requires a voluminous exchange of data for disease prediction via the open communication channel, i.e., the Internet to train artificial intellig...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9867987/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846128646641680384 |
|---|---|
| author | Vishwa Amitkumar Patel Pronaya Bhattacharya Sudeep Tanwar Rajesh Gupta Gulshan Sharma Pitshou N. Bokoro Ravi Sharma |
| author_facet | Vishwa Amitkumar Patel Pronaya Bhattacharya Sudeep Tanwar Rajesh Gupta Gulshan Sharma Pitshou N. Bokoro Ravi Sharma |
| author_sort | Vishwa Amitkumar Patel |
| collection | DOAJ |
| description | The smart healthcare system has improved the patients quality of life (QoL), where the records are being analyzed remotely by distributed stakeholders. It requires a voluminous exchange of data for disease prediction via the open communication channel, i.e., the Internet to train artificial intelligence (AI) models efficiently and effectively. The open nature of communication channels puts data privacy at high risk and affects the model training of collected data at centralized servers. To overcome this, an emerging concept, i.e., federated learning (FL) is a viable solution. It performs training at client nodes and aggregates their results to train the global model. The concept of local training preserves the privacy, confidentiality, and integrity of the patient’s data which contributes effectively to the training process. The applicability of FL in the healthcare domain has various advantages, but it has not been explored to its extent. The existing surveys majorly focused on the role of FL in diverse applications, but there exists no detailed or comprehensive survey on FL in healthcare informatics (HI). We present a relative comparison of recent surveys with the proposed survey. To strengthen healthcare data privacy and increase the QoL of patients, we proposed an FL-based layered healthcare informatics architecture along with the case study on FL-based electronic health records (FL-EHR). We discuss the emerging FL models, and present the statistical and security challenges in FL adoption in medical setups. Thus, the review presents useful insights for both academia and healthcare practitioners to investigate FL application in HI ecosystems. |
| format | Article |
| id | doaj-art-e245704b9f2248c3a43126cd3b2d7c44 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-e245704b9f2248c3a43126cd3b2d7c442024-12-11T00:02:54ZengIEEEIEEE Access2169-35362022-01-0110907929082610.1109/ACCESS.2022.32018769867987Adoption of Federated Learning for Healthcare Informatics: Emerging Applications and Future DirectionsVishwa Amitkumar Patel0Pronaya Bhattacharya1https://orcid.org/0000-0002-1206-2298Sudeep Tanwar2https://orcid.org/0000-0002-1776-4651Rajesh Gupta3https://orcid.org/0000-0003-3298-4238Gulshan Sharma4Pitshou N. Bokoro5https://orcid.org/0000-0002-9178-2700Ravi Sharma6https://orcid.org/0000-0002-8584-9753Sardar Vallabhbhai Patel Institute of Technology, Vasad, Gujarat, IndiaDepartment of Computer Science and Engineering, Institute of Technology, Nirma University, Ahmedabad, Gujarat, IndiaDepartment of Computer Science and Engineering, Institute of Technology, Nirma University, Ahmedabad, Gujarat, IndiaDepartment of Computer Science and Engineering, Institute of Technology, Nirma University, Ahmedabad, Gujarat, IndiaDepartment of Electrical Engineering Technology, University of Johannesburg, Auckland Park, South AfricaDepartment of Electrical Engineering Technology, University of Johannesburg, Auckland Park, South AfricaCentre for Inter-Disciplinary Research and Innovation, University of Petroleum and Energy Studies, Dehradun, IndiaThe smart healthcare system has improved the patients quality of life (QoL), where the records are being analyzed remotely by distributed stakeholders. It requires a voluminous exchange of data for disease prediction via the open communication channel, i.e., the Internet to train artificial intelligence (AI) models efficiently and effectively. The open nature of communication channels puts data privacy at high risk and affects the model training of collected data at centralized servers. To overcome this, an emerging concept, i.e., federated learning (FL) is a viable solution. It performs training at client nodes and aggregates their results to train the global model. The concept of local training preserves the privacy, confidentiality, and integrity of the patient’s data which contributes effectively to the training process. The applicability of FL in the healthcare domain has various advantages, but it has not been explored to its extent. The existing surveys majorly focused on the role of FL in diverse applications, but there exists no detailed or comprehensive survey on FL in healthcare informatics (HI). We present a relative comparison of recent surveys with the proposed survey. To strengthen healthcare data privacy and increase the QoL of patients, we proposed an FL-based layered healthcare informatics architecture along with the case study on FL-based electronic health records (FL-EHR). We discuss the emerging FL models, and present the statistical and security challenges in FL adoption in medical setups. Thus, the review presents useful insights for both academia and healthcare practitioners to investigate FL application in HI ecosystems.https://ieeexplore.ieee.org/document/9867987/Blockchainfederated learninghealthcare informaticsgradientmodel aggregation |
| spellingShingle | Vishwa Amitkumar Patel Pronaya Bhattacharya Sudeep Tanwar Rajesh Gupta Gulshan Sharma Pitshou N. Bokoro Ravi Sharma Adoption of Federated Learning for Healthcare Informatics: Emerging Applications and Future Directions IEEE Access Blockchain federated learning healthcare informatics gradient model aggregation |
| title | Adoption of Federated Learning for Healthcare Informatics: Emerging Applications and Future Directions |
| title_full | Adoption of Federated Learning for Healthcare Informatics: Emerging Applications and Future Directions |
| title_fullStr | Adoption of Federated Learning for Healthcare Informatics: Emerging Applications and Future Directions |
| title_full_unstemmed | Adoption of Federated Learning for Healthcare Informatics: Emerging Applications and Future Directions |
| title_short | Adoption of Federated Learning for Healthcare Informatics: Emerging Applications and Future Directions |
| title_sort | adoption of federated learning for healthcare informatics emerging applications and future directions |
| topic | Blockchain federated learning healthcare informatics gradient model aggregation |
| url | https://ieeexplore.ieee.org/document/9867987/ |
| work_keys_str_mv | AT vishwaamitkumarpatel adoptionoffederatedlearningforhealthcareinformaticsemergingapplicationsandfuturedirections AT pronayabhattacharya adoptionoffederatedlearningforhealthcareinformaticsemergingapplicationsandfuturedirections AT sudeeptanwar adoptionoffederatedlearningforhealthcareinformaticsemergingapplicationsandfuturedirections AT rajeshgupta adoptionoffederatedlearningforhealthcareinformaticsemergingapplicationsandfuturedirections AT gulshansharma adoptionoffederatedlearningforhealthcareinformaticsemergingapplicationsandfuturedirections AT pitshounbokoro adoptionoffederatedlearningforhealthcareinformaticsemergingapplicationsandfuturedirections AT ravisharma adoptionoffederatedlearningforhealthcareinformaticsemergingapplicationsandfuturedirections |