Collaborative Machine Learning-Driven Internet of Medical Things -- A Systematic Literature Review

TL;DR

This systematic review examines distributed machine learning algorithms used in IoMT healthcare applications, highlighting the performance of Random Forest and emphasizing the importance of efficiency and throughput in data processing.

Contribution

It provides a comprehensive overview of distributed ML algorithms in IoMT, identifying the most effective algorithms for different healthcare scenarios and guiding future research directions.

Findings

Random Forest achieved the best prediction accuracy in some studies.

No single algorithm was consistently best across all scenarios.

Distributed processing improves efficiency and throughput in IoMT data analysis.

Abstract

The growing adoption of IoT devices for healthcare has enabled researchers to build intelligence using all the data produced by these devices. Monitoring and diagnosing health have been the two most common scenarios where such devices have proven beneficial. Achieving high prediction accuracy was a top priority initially, but the focus has slowly shifted to efficiency and higher throughput, and processing the data from these devices in a distributed manner has proven to help achieve both. Since the field of machine learning is vast with numerous state-of-the-art algorithms in play, it has been a challenge to identify the algorithms that perform best in different scenarios. In this literature review, we explored the distributed machine learning algorithms tested by the authors of the selected studies and identified the ones that achieved the best prediction accuracy in each healthcare scenario. While no algorithm performed consistently, Random Forest performed the best in a few studies. This could serve as a good starting point for future studies on collaborative machine learning on IoMT data.