TY  - JOUR
AU  - Rahim, Shahnila
AU  - Kong, Xiao
AU  - Abdullah, Fatima
PY  - 2025
DA  - 2025/12/09
TI  - Navigating Ethical Boundaries in Federated Learning for Biomedical Research
JO  - Journal of Artificial Intelligence in Bioinformatics
T2  - Journal of Artificial Intelligence in Bioinformatics
JF  - Journal of Artificial Intelligence in Bioinformatics
VL  - 1
IS  - 2
SP  - 72
EP  - 78
DO  - 10.62762/JAIB.2025.703433
UR  - https://www.icck.org/article/abs/JAIB.2025.703433
KW  - federated learning
KW  - biomedical ethics
KW  - data privacy
KW  - precision medicine
KW  - AI governance
KW  - fairness
AB  - Biomedical research is increasingly shaped by vast and diverse datasets, yet their integration is constrained by privacy concerns, regulatory barriers, and fragmented infrastructures. Federated learning (FL) has emerged as a promising paradigm that enables institutions to collaboratively train machine learning models while keeping sensitive data local. This approach has the potential to accelerate discovery in areas such as precision medicine, rare disease research, and population health by pooling knowledge without centralizing data. However, federated learning also introduces new ethical and governance challenges. Risks of information leakage, inequitable participation, algorithmic bias, unclear accountability, and regulatory complexity must be carefully addressed. This editorial highlights these boundaries and emphasizes that technical solutions alone are insufficient. We argue that responsible deployment of FL requires dedicated ethical frameworks, innovative governance structures, continuous auditing, and inclusive global participation. By embedding responsibility into its design and implementation, federated learning can not only advance biomedical science but also foster trust, equity, and sustainability in the future of data-driven health research.
SN  - 3068-7535
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Rahim2025Navigating,
  author = {Shahnila Rahim and Xiao Kong and Fatima Abdullah},
  title = {Navigating Ethical Boundaries in Federated Learning for Biomedical Research},
  journal = {Journal of Artificial Intelligence in Bioinformatics},
  year = {2025},
  volume = {1},
  number = {2},
  pages = {72-78},
  doi = {10.62762/JAIB.2025.703433},
  url = {https://www.icck.org/article/abs/JAIB.2025.703433},
  abstract = {Biomedical research is increasingly shaped by vast and diverse datasets, yet their integration is constrained by privacy concerns, regulatory barriers, and fragmented infrastructures. Federated learning (FL) has emerged as a promising paradigm that enables institutions to collaboratively train machine learning models while keeping sensitive data local. This approach has the potential to accelerate discovery in areas such as precision medicine, rare disease research, and population health by pooling knowledge without centralizing data. However, federated learning also introduces new ethical and governance challenges. Risks of information leakage, inequitable participation, algorithmic bias, unclear accountability, and regulatory complexity must be carefully addressed. This editorial highlights these boundaries and emphasizes that technical solutions alone are insufficient. We argue that responsible deployment of FL requires dedicated ethical frameworks, innovative governance structures, continuous auditing, and inclusive global participation. By embedding responsibility into its design and implementation, federated learning can not only advance biomedical science but also foster trust, equity, and sustainability in the future of data-driven health research.},
  keywords = {federated learning, biomedical ethics, data privacy, precision medicine, AI governance, fairness},
  issn = {3068-7535},
  publisher = {Institute of Central Computation and Knowledge}
}