Identification of Relationships Between Patients Through Elements in a Data Warehouse Using the Familial, Associational, and Incidental Relationship (FAIR) Initiative: A Pilot Study
Bibliographic record
Abstract
BACKGROUND: Over the last several years there has been widespread development of medical data warehouses. Current data warehouses focus on individual cases, but lack the ability to identify family members that could be used for dyadic or familial research. Currently, the patient's family history in the medical record is the only documentation we have to understand the health status and social habits of their family members. Identifying familial linkages in a phenotypic data warehouse can be valuable in cohort identification and in beginning to understand the interactions of diseases among families. OBJECTIVE: The goal of the Familial, Associational, & Incidental Relationships (FAIR) initiative is to identify an index set of patients' relationships through elements in a data warehouse. METHODS: Using a test set of 500 children, we measured the sensitivity and specificity of available linkage algorithm identifiers (eg, insurance identification numbers and phone numbers) and validated this tool/algorithm through a manual chart audit. RESULTS: Of all the children, 52.4% (262/500) were male, and the mean age of the cohort was 8 years old (SD 5). Of the children, 51.6% (258/500) were identified as white in race. The identifiers used for FAIR were available for the majority of patients: insurance number (483/500, 96.6%), phone number (500/500, 100%), and address (497/500, 99.4%). When utilizing the FAIR tool and various combinations of identifiers, sensitivity ranged from 15.5% (62/401) to 83.8% (336/401), and specificity from 72% (71/99) to 100% (99/99). The preferred method was matching patients using insurance or phone number, which had a sensitivity of 72.1% (289/401) and a specificity of 94% (93/99). Using the Informatics for Integrating Biology and the Bedside (i2b2) warehouse infrastructure, we have now developed a Web app that facilitates FAIR for any index population. CONCLUSIONS: FAIR is a valuable research and clinical resource that extends the capabilities of existing data warehouses and lays the groundwork for family-based research. FAIR will expedite studies that would otherwise require registry or manual chart abstraction data sources.
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 | 0.020 | 0.050 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".