Using Primary Health Care Electronic Medical Records to Predict Hospitalizations, Emergency Department Visits, and Mortality: A Systematic Review
Bibliographic record
Abstract
INTRODUCTION: High-quality primary care can reduce avoidable emergency department visits and emergency hospitalizations. The availability of electronic medical record (EMR) data and capacities for data storage and processing have created opportunities for predictive analytics. This systematic review examines studies which predict emergency department visits, hospitalizations, and mortality using EMR data from primary care. METHODS: Six databases (Ovid MEDLINE, PubMed, Embase, EBM Reviews (Cochrane Database of Systematic Reviews, Database of Abstracts of Reviews of Effects, Cochrane Central Register of Controlled Trials, Cochrane Methodology Register, Health Technology Assessment, NHS Economic Evaluation Database), Scopus, CINAHL) were searched to identify primary peer-reviewed studies in English from inception to February 5, 2020. The search was initially conducted on January 18, 2019, and updated on February 5, 2020. RESULTS: A total of 9456 citations were double-reviewed, and 31 studies met the inclusion criteria. The predictive ability measured by C-statistics (ROC) of the best performing models from each study ranged from 0.57 to 0.95. Less than half of the included studies used artificial intelligence methods and only 7 (23%) were externally validated. Age, medical diagnoses, sex, medication use, and prior health service use were the most common predictor variables. Few studies discussed or examined the clinical utility of models. CONCLUSIONS: This review helps address critical gaps in the literature regarding the potential of primary care EMR data. Despite further work required to address bias and improve the quality and reporting of prediction models, the use of primary care EMR data for predictive analytics holds promise.
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 | 0.014 | 0.075 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.009 | 0.009 |
| Bibliometrics | 0.012 | 0.016 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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 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".