A Systematic Review of the Challenges and Opportunities of Machine Learning in Older Adults Clinical Care

Introduction: Machine learning as one of the components of artificial intelligence is known to play an effective role in increasing the accuracy of diagnosis, sensitivity and clinical features for predicting complications related to elderly people. However, the widespread adoption of machine learning has challenged the development of clinically relevant models due to the lack of expert programming in the medical community and access to health data. The aim of this study was to determine the challenges and opportunities of machine learning in older adults.Material and Methods: The protocol of this systematic review followed the PRISMA guideline. An extensive search was carried in online databases including PubMed, ISI, Scopus, Google Scholar, and ProQuest with the keywords such as “Machine Learning”, “Transfer Learning”, “Artificial Intelligence”, “elderly”, “Geriatrics”, “care”, “clinical care”, from the earliest records up to October ۲۰, ۲۰۲۲. Also, all English-language opinions, lesson learned and Letters to the editor studies related to the purpose of the present study were included. All stages of search and quality evaluation of articles were conducted by two researchers, independently.Results: ۶ out of ۳۴۱ studies were included in the study. The challenges of machine learning in clinical care were including lack of complete expertise in using machine learning (n=۶), lack of expert programming (n=۵) and inappropriate access to health data (n=۴). On the other hand, these challenges lead to the creation of opportunities such as the development of automatic machine learning platforms to facilitate clinical studies to fully understand the high capabilities of artificial intelligence in the health field, especially clinical care (n=۳), extensive education of healthcare workers, especially doctors (n=۳), and improving the standard of clinical care (n=۲).Conclusion: In general, the use of machine learning, despite the challenges raised, can avoid heavy costs for the patient, family and medical systems by accurately and early diagnosis of complications when care resources are limited and expensive.

Keywords:

Machine Learning , Artificial Intelligence , elderly , Geriatrics , clinical care.