Handling Privacy-Sensitive Medical Data With Federated Learning: Challenges and Future Directions

Abstract

Recent medical applications are largely dominated by the application of Machine Learning (ML) models to assist expert decisions, leading to disruptive innovations in radiology, pathology, genomics, and hence modern healthcare systems in general. Despite the profitable usage of AI-based algorithms, these data-driven methods are facing issues such as the scarcity and privacy of user data, as well as the difficulty of institutions exchanging medical information. With insufficient data, ML is prevented from reaching its full potential, which is only possible if the database consists of the full spectrum of possible anatomies, pathologies, and input data types. To solve these issues, Federated Learning (FL) appeared as a valuable approach in the medical field, allowing patient data to stay where it is generated. Since an FL setting allows many clients to collaboratively train a model while keeping training data decentralized, it can protect privacy-sensitive medical data. However, FL is still unable to deliver all its promises and meets the more stringent requirements (e.g., latency, security) of a healthcare system based on multiple Internet of Medical Things (IoMT). For example, although no data are shared among the participants by definition in FL systems, some security risks are still present and can be considered as vulnerabilities from multiple aspects. This paper sheds light upon the emerging deployment of FL, provides a broad overview of current approaches and existing challenges, and outlines several directions of future work that are relevant to solving existing problems in federated healthcare, with a particular focus on security and privacy issues.

Artificial intelligence for clinical decision support for monitoring patients in cardiovascular ICUs: A systematic review

“…Nevertheless, as presented in Table 2, only three of the 21 included studies provided open access web-based user interfaces to facilitate validating their models with external datasets. Although providing freely accessible tools for external validation should be marked as a benefit for novel AI tools, the lack of standardization of external validation schemes considering the high levels of privacy and confidentiality associated with medical data cohorts rank amongst the most important limitations towards integration of AI in clinical routines, especially in multicentric and federated scenarios (90).…”

Next-Generation Protection: Leveraging Federated Learning and Blockchain for Intrusion Detection in Smart Vehicle Network

“…With the passage of time, these networks are steadily getting more integrated into the stream of daily routines thereby making the data they possess and consume more classy and thought-provoking, in turn, rendering major security and privacy issues. Be-sides, such computerized transport is capable of interacting and deliberating on data without humans, which casts difficulty in valuing the security of those communications from being intercepted or modified [4]. Cybersecurity in a smart vehicle network is not lim-ited only to repellent the onboard systems from the unwanted access; it encompasses the sharing of the data which should remain protected in integrity and confidentiality.…”

Privacy-Enhancing Technologies in Federated Learning for the Internet of Healthcare Things: A Survey

“…The federated learning (FL) approach has been proposed as a promising way for eHealth systems to overcome data privacy concerns relating to the IoHT [9]. FL is a distributed ML-based approach that keeps patients' data restricted to their devices while training ML models collaboratively on multiple clients' health data from hospitals or IoHT devices in a decentralized network [10,11].…”