The emergence of large-scale human genome projects, advances in DNA sequencing technologies, and the massive volume of electronic medical records [EMR] shift the transformation of healthcare research into the next paradigm, namely 'Precision Medicine.' This new clinical system model uses patients' genomic profiles and disparate healthcare data sources to a greater extent and provides personalized deliverables. As an advanced analytical technique, deep learning models significantly impact precision medicine because they can process voluminous amounts of diversified data with improved accuracy. Two salient features of deep learning models, namely processing a massive volume of multi-model data at multiple levels of abstraction and the ability to identify inherent features from the input data on their own, attract the implication of deep learning techniques in precision medicine research. The proposed review highlights the importance of deep learning-based analytical models in handling diversified and disparate big data sources of precision medicine. To augment further, state-of-the-art precision medicine research based on the taxonomy of deep learning models has been reviewed along with their research outcomes. The diversified data inputs used in research attempts, their applications, benchmarking data repositories, and usage of various evaluation measures for accuracy estimations are highlighted in this review. This review also brings out some promising analytical avenues of precision medicine research that give directions for future exploration.
Keywords: Artificial intelligence; Deep learning; Healthcare big data; Personalized medicine; Precision medicine.
Copyright © 2022 Elsevier Ltd. All rights reserved.