Artificial Intelligence and Machine Learning in Personalized Medicine: Emerging Technologies and Applications
Taiwo Oluwole Fabiyi
*
Department of Bioinformatics, University of Maryland Global Campus, USA.
Mary Oluwabunmi Oyebode
Department of Public Health, Osun State University, Nigeria.
Kehinde Oluwafemi Fabiyi
Department of Public Health, Indiana University, USA.
Damilola Ayodeji Akinwale
Department of Medical Laboratory Science, Canadian Armed Forces, Canada.
Damilola Caroline Adeoye
Department of Food Science, Atiba University, Nigeria.
Paul-Miki Raluchukwu Ibekwe
Isenberg School of Management and Institute for Applied Life Sciences, University of Massachusetts - Amherst, MA, United States.
Olaitan Ololade Funke
Department of Business, information Systems, University of Utah, USA.
Onyinye Henrietta Okolo
Nursing and Health Professions, University of Southern Mississippi, USA.
Irene Adjoa Anderson
Department of Pharmacology, Kwame Nkrumah University of Science and Technology, Ghana.
*Author to whom correspondence should be addressed.
Abstract
Personalized medicine is a revolutionary paradigm shift in the health sector, to customize medical decisions and initiatives to the distinct biological and contextual peculiarities of individual patients. This approach differs from the generalized strategies of traditional medicine, which can enhance patient outcomes and minimize adverse effects. The incorporation of machine learning and Artificial Intelligence is very crucial in the improvement of personalized medicine, which facilitates the productive extraction of practical findings from complex and multifaceted datasets in healthcare. This review gives a comprehensive overview of how AI and ML have and can transform personalized medicine by improving diagnostics, maximizing therapy plans, predicting disease risks, and identifying novel therapeutic targets. It scrutinizes the rudimentary concepts of AI and ML, and their various uses in oncology, cardiology, pharmacogenomics, and rare disease diagnosis, and the critical role of robust data infrastructures. Moreover, the review discusses the ethical, legal, and regulatory challenges, which include algorithmic bias and data privacy, and also discusses current trends in limitations such as data heterogeneity and model interpretability. Conclusively, we emphasize the future directions and the importance of interdisciplinary collaboration in overcoming these challenges and completely recognize the hope personalized medicine presents.
Keywords: Personalized medicine, biomedical science, artificial intelligence, machine learning, oncology