Systematic Reviews of Machine Learning in Healthcare: A Literature Review

Abstract

Abstract The increasing availability of data and computing power has made machine learning (ML) a viable approach to faster, more efficient healthcare delivery. To exploit the potential of data-driven technologies, further integration of artificial intelligence (AI) into healthcare systems is warranted. A systematic literature review (SLR) of published SLRs evaluated evidence of ML applications in healthcare settings published in PubMed, IEEE Xplore, Scopus, Web of Science, EBSCO, and the Cochrane Library up to March 2023. Studies were classified based on the disease area and the type of ML algorithm used. In total, 220 SLRs covering 10,462 ML algorithms were identified, the majority of which aimed at solutions towards clinical prediction, categorisation, and disease prognosis in oncology and neurology primarily using imaging data. Accuracy, specificity, and sensitivity were 56%, 28%, and 25%, respectively. Internal validation was reported in 53% of the ML algorithms and external validation in below 1%. The most common modelling approach was neural networks (2,454 ML algorithms), followed by support vector machine and random forest/decision trees (1,578 and 1,522 ML algorithms, respectively). The review indicated that there is potential for greater adoption of AI in healthcare, with 10,462 ML algorithms identified compared to 523 approved by the Food and Drug Administration (FDA). However, the considerable reporting gaps call for more effort towards internal and external validation. Greater accessibility to healthcare data for developers can ensure the faster adoption of ML algorithms.