JMIR Publications

ABSTRACT

Background:

Precision health is a rapidly developing field, largely driven by the development of Artificial intelligence (AI)-related solutions. AI facilitates complex analysis of numerous health data sources, and AI-based digital health technologies are increasingly employed to assess risks, detect early signs of disease, and initiate timely preventative health interventions that are highly tailored to the individual. This may contribute to a more integrated assessment of previously siloed health data and thus provide more holistic and accurate health management from a person-centred perspective. Despite such promise, ethical concerns arising from the rapid development and use of AI-related technologies have led to the establishment of new national and international frameworks and guidelines that define their ethical and responsible use.

Objective:

This protocol delineates a state-of-the-art literature review of novel AI-based applications in precision health. The objective is to address research gaps and provide new knowledge regarding 1) examples of existing AI applications and what role they play with regards have regarding precision health, 2) what salient features can be used to categorize them, 3) what evidence exists for their effects on precision health outcomes, 4) how do these AI applications comply with established ethical and responsible framework, and 5) how these AI applications address equity and social determinants of health.

Methods:

The review will encompass applications that use AI as a primary or supporting system or method when primarily applied for precision health purposes in human populations. Any geographical location or setting, including online, community-based, acute, or clinical settings will be included, reporting clinical, behavioural, and/or psychosocial outcomes, including detection-, diagnosis-, promotion-, prevention-, management- and/or treatment-related outcomes. Primary empirical research studies published in scientific or grey literature in English language will be included, for all dates prior to onset of searches. The review will follow the PRISMA reporting guidelines. Primary analyses will report main statistics grouped by population, AI application, setting, area of focus, and outcomes. Secondary analyses will describe the compliance of AI interventions with the WHO principles for ethical use of AI.

Results:

This is step 1 towards a full state-of-the-art literature review with data analyses, results and discussion of findings which will also be published. The anticipated consequences on equity from the perspective of social determinants of health will be analysed. Keyword cluster relationships will be visualised to indicate which research foci are leading the development of the field and where research gaps exist. Results will be presented based on the data analysis plan that include primary analyses, visualization of sources and secondary analyses. Implications for future research and the person-centred public health will be discussed.

Conclusions:

Results from this review will potentially guide continued development of AI applications, future research in reducing the knowledge gaps and improve practice related to precision health. New insights regarding examples of existing AI applications, their salient features, their role regarding precision health and the existing evidence exists for their effects on precision health outcomes will be demonstrated. Additionally, demonstration of how existing AI applications address equity and social determinants of health and comply with established ethical and responsible framework will be provided.