Leveraging Artificial Intelligence to Inform Care Coordination by Identifying and Intervening in Patients' Unmet Social Needs: A Scoping Review
Bibliographic record
Abstract
AIM: We reviewed how artificial intelligence has been applied to inform care coordination by identifying and/or intervening in patients' unmet social needs. DESIGN: Scoping review. DATA SOURCES: PubMed, CINAHL, PsycInfo, and Scopus databases were searched for articles published by November 2023. METHODS: Articles were excluded if they were reviews or protocols, did not explicitly mention artificial intelligence, or did not primarily focus on using it to identify and/or address unmet needs to inform care coordination. RESULTS: Of 476 articles that underwent title and abstract screening, 102 were assessed for full-text eligibility, and eight were ultimately included. Five articles used both natural language processing and machine learning; two articles used natural language processing; and one article used machine learning. Half (n = 4) of the articles focused on using artificial intelligence to identify/predict social needs, and two each focused on artificial intelligence to examine social resource provision or to indirectly identify social needs or using artificial intelligence to facilitate addressing unmet needs through care coordination. CONCLUSIONS: This review can inform an understanding of facilitators and barriers to the implementation of artificial intelligence in practice, to potentially improve patient care, health outcomes, and population health equity. IMPLICATIONS FOR PATIENTS AND THE PROFESSION: Using artificial intelligence to promote care coordination can expand opportunities to identify and intervene on social needs across more patients, with implications for nurses and other health professionals. It can also potentially exacerbate inequities and harm patient trust. IMPACT: The findings suggest a gap between the practice of incorporating artificial intelligence into integrated care platforms and the available scientific literature. This review can provide healthcare providers and organisations with insights into integrating artificial intelligence into clinical workflows, which may inform decisions about whether or how to implement these technologies in clinical settings. REPORTING METHOD: We followed PRISMA-ScR guidelines. No Patient or Public Contribution.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".