Federated Learning for the Internet-of-Medical-Things: A Survey

Abstract

Recently, in healthcare organizations, real-time data have been collected from connected or implantable sensors, layered protocol stacks, lightweight communication frameworks, and end devices, named the Internet-of-Medical-Things (IoMT) ecosystems. IoMT is vital in driving healthcare analytics (HA) toward extracting meaningful data-driven insights. Recently, concerns have been raised over data sharing over IoMT, and stored electronic health records (EHRs) forms due to privacy regulations. Thus, with less data, the analytics model is deemed inaccurate. Thus, a transformative shift has started in HA from centralized learning paradigms towards distributed or edge-learning paradigms. In distributed learning, federated learning (FL) allows for training on local data without explicit data-sharing requirements. However, FL suffers from a high degree of statistical heterogeneity of learning models, level of data partitions, and fragmentation, which jeopardizes its accuracy during the learning and updating process. Recent surveys of FL in healthcare have yet to discuss the challenges of massive distributed datasets, sparsification, and scalability concerns. Because of this gap, the survey highlights the potential integration of FL in IoMT, the FL aggregation policies, reference architecture, and the use of distributed learning models to support FL in IoMT ecosystems. A case study of a trusted cross-cluster-based FL, named Cross-FL, is presented, highlighting the gradient aggregation policy over remotely connected and networked hospitals. Performance analysis is conducted regarding system latency, model accuracy, and the trust of consensus mechanism. The distributed FL outperforms the centralized FL approaches by a potential margin, which makes it viable for real-IoMT prototypes. As potential outcomes, the proposed survey addresses key solutions and the potential of FL in IoMT to support distributed networked healthcare organizations.

Post-COVID-19 Pandemic Era and Sustainable Healthcare: Organization and Delivery of Health Economics Research (Principles and Clinical Practice)

“…Future studies that examine pricing and the rates at which practitioners embrace new technology are urgently required throughout the spectrum of medical device categories, including orthopedics and spine. It is also vital to realize that breakthroughs, such as those allowing for minimally invasive procedures, may affect practices, the value provided to patients, and as a result, changes in purchasing volumes and pricing [24,25].…”

Federated Learning for Healthcare: A Comprehensive Review

“…Data-driven deep learning models hold great promise in assisting with medical treatment and diagnosis, but they allow massive quantities of different data to be widely useful. For instance, deep learning is extremely useful for text identification in medical laboratory reports [1], tumor segmentation and classification from MRI scans, and cancer diagnosis and forecasting. Machine learning applications actually require enormous quantities of data.…”

“…So far, huge data collection and resource sharing may raise operational challenges, and overcoming privacy and ethical issues might take time. For instance, only a specific hospital or clinic might have access to a patient's medical records [1]. The significance of data security and privacy protection is increasingly being widely recognized [1], particularly as the frequency of data breaches at health care organizations rises.…”

“…For instance, only a specific hospital or clinic might have access to a patient's medical records [1]. The significance of data security and privacy protection is increasingly being widely recognized [1], particularly as the frequency of data breaches at health care organizations rises. Medical images of the patient may include private and sensitive data about patients that should not be shared with anyone except the institutions where they were produced, especially when complete de-identification is indeed not practicable [2].…”

Game-o-Meta: Trusted Federated Learning Scheme for P2P Gaming Metaverse beyond 5G Networks

“…To address these limitations, federated learning (FL) is a viable choice in GMs and mobile devices. FL has been extensively used for medical ecosystems, as FL utilization in mobile devices enables the support of increasingly complex tasks and operations and contributes to safeguarding user privacy and exploiting the computing resources available on mobile devices [12]. FL is a promising candidate to support the gaming ecosystem due to its high potential.…”