AI in Health: State of the Art, Challenges, and Future Directions

Abstract

Introduction: Artificial intelligence (AI) technologies continue to attract interest from a broad range of disciplines in recent years, including health. The increase in computer hardware and software applications in medicine, as well as digitization of health-related data together fuel progress in the development and use of AI in medicine. This progress provides new opportunities and challenges, as well as directions for the future of AI in health. Objective: The goals of this survey are to review the current state of AI in health, along with opportunities, challenges, and practical implications. This review highlights recent developments over the past five years and directions for the future. Methods: Publications over the past five years reporting the use of AI in health in clinical and biomedical informatics journals, as well as computer science conferences, were selected according to Google Scholar citations. Publications were then categorized into five different classes, according to the type of data analyzed. Results: The major data types identified were multi-omics, clinical, behavioral, environmental and pharmaceutical research and development (R&D) data. The current state of AI related to each data type is described, followed by associated challenges and practical implications that have emerged over the last several years. Opportunities and future directions based on these advances are discussed. Conclusion: Technologies have enabled the development of AI-assisted approaches to healthcare. However, there remain challenges. Work is currently underway to address multi-modal data integration, balancing quantitative algorithm performance and qualitative model interpretability, protection of model security, federated learning, and model bias.

Artificial Intelligence (AI) in Rare Diseases: Is the Future Brighter?

“…In the "big data" era, there is a growing need to automate tasks that currently require human intervention. In biomedicine, AI technologies have been developed to analyze a diverse array of data, from individual clinical phenotypes in EHR to large and multiparametric patient cohort analysis, attenuating outstanding difficulties in RDs [97].…”

“…Additionally, as multi-omics data are highly heterogeneous, AI strategies performing network-based approaches are required to further promote combinatory analysis of big data [97].…”

“…However, designing and training these models in RDs faces various confounding and detrimental factors, such as small patient cohorts and differences in patient ethnicity. Because a high number of relatively homogeneous images are needed to optimize the model, these limitations may lead to erroneous calculations and/or recommendations [97].…”

“…Recently developed ML tools to analyze heterogeneous, sparse, and noisy clinical data have shed light on this neglected topic [73][74][75][76]97]. Nevertheless, most advances have occurred in unconcerted actions or in disease niches.…”

Precision Medicine, AI, and the Future of Personalized Health Care

“…[2][3][4] However, multimodal data integration, security, federated learning (which requires fundamental advances in areas, such as privacy, large-scale machine learning, and distributed optimization), model performance, and bias may pose challenges to the use of AI in health care. 5 Three main principles for successful adoption of AI in health care include data and security, analytics and insights, and shared expertise. Data and security equate to full transparency and trust in how AI systems are trained and in the data and knowledge used to train them.…”