Artificial Intelligence and Precision Health Through Lenses of Ethics and Social Determinants of Health: Protocol for a State-of-the-Art Literature Review
Bibliographic record
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 risk assessment, early detection of disease, and initiation of timely preventative health interventions that can be highly tailored to the individual. Despite such promise, ethical concerns arising from the rapid development and use of AI-related technologies have led to development of national and international frameworks to address responsible use of AI. OBJECTIVE: We aimed to address research gaps and provide new knowledge regarding (1) examples of existing AI applications and what role they play 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 (SDOH). METHODS: This protocol delineates a state-of-the-art literature review of novel AI-based applications in precision health. Published and unpublished studies were retrieved from 6 electronic databases. Articles included in this study were from the inception of the databases to January 2023. 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. It includes any geographical location or setting, including the internet, community-based, and acute or clinical settings, reporting clinical, behavioral, and psychosocial outcomes, including detection-, diagnosis-, promotion-, prevention-, management-, and treatment-related outcomes. RESULTS: This is step 1 toward 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 SDOH will be analyzed. Keyword cluster relationships and analyses will be visualized 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 includes primary analyses, visualization of sources, and secondary analyses. Implications for future research and person-centered public health will be discussed. CONCLUSIONS: Results from the review will potentially guide the continued development of AI applications, future research in reducing the knowledge gaps, and improvement of 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 that exists for their effects on precision health outcomes will be demonstrated. Additionally, a demonstration of how existing AI applications address equity and SDOH and comply with established ethical and responsible frameworks will be provided. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/40565.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.090 | 0.136 |
| Meta-epidemiology (narrow) | 0.004 | 0.004 |
| Meta-epidemiology (broad) | 0.012 | 0.014 |
| Bibliometrics | 0.027 | 0.024 |
| Science and technology studies | 0.004 | 0.006 |
| Scholarly communication | 0.010 | 0.009 |
| Open science | 0.005 | 0.008 |
| Research integrity | 0.009 | 0.006 |
| Insufficient payload (model declined to judge) | 0.057 | 0.012 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".