Optimizing the Use of Electronic Health Records to Identify High-Risk Psychosocial Determinants of Health
Bibliographic record
Abstract
BACKGROUND: Care coordination programs have traditionally focused on medically complex patients, identifying patients that qualify by analyzing formatted clinical data and claims data. However, not all clinically relevant data reside in claims and formatted data. Recently, there has been increasing interest in including patients with complex psychosocial determinants of health in care coordination programs. Psychosocial risk factors, including social determinants of health, mental health disorders, and substance abuse disorders, are less amenable to rapid and systematic data analyses, as these data are often not collected or stored as formatted data, and due to US Health Insurance Portability and Accountability Act (HIPAA) regulations are often not available as claims data. OBJECTIVE: The objective of our study was to develop a systematic approach using word recognition software to identifying psychosocial risk factors within any part of a patient's electronic health record (EHR). METHODS: We used QPID (Queriable Patient Inference Dossier), an ontology-driven word recognition software, to scan adult patients' EHRs to identify terms predicting a high-risk patient suitable to be followed in a care coordination program in Massachusetts, USA. Search terms identified high-risk conditions in patients known to be enrolled in a care coordination program, and were then tested against control patients. We calculated precision, recall, and balanced F-measure for the search terms. RESULTS: We identified 22 EHR-available search terms to define psychosocial high-risk status; the presence of 9 or more of these terms predicted that a patient would meet inclusion criteria for a care coordination program. Precision was .80, recall .98, and balanced F-measure .88 for the identified terms. For adult patients insured by Medicaid and enrolled in the program, a mean of 14 terms (interquartile range [IQR] 11-18) were present as identified by the search tool, ranging from 2 to 22 terms. For patients enrolled in the program but not insured by Medicaid, a mean of 6 terms (IQR 3-8) were present as identified by the search tool, ranging from 1 to 21. CONCLUSIONS: Selected informatics tools such as word recognition software can be leveraged to improve health care delivery, such as an EHR-based protocol that identifies psychosocially complex patients eligible for enrollment in a care coordination program.
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 | 0.012 | 0.063 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.009 | 0.005 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".