ThinkRare: A search algorithm to identify patients with undiagnosed rare genetic disease in an electronic medical record
Bibliographic record
Abstract
PURPOSE: Undiagnosed rare genetic diseases (RGD) can go unrecognized by health care providers, delaying appropriate genetic testing. This proof-of-concept study aimed to address this barrier through the development of a rule-based search algorithm called "ThinkRare." METHODS: The algorithm used structured electronic medical record data and clinical criteria to identify patients who may have a complex undiagnosed RGD, are eligible for clinical exome sequencing, and are not yet referred to genetics (true positives). Iterative testing on gold standard and test data sets (input) informed algorithm design and optimization. Medical record reviews were conducted to verify whether the algorithm identified patients (output) were true positives or false positives, and these outcomes informed algorithm modifications. Physicians of identified patients were notified with the option to refer to genetics. RESULTS: The search algorithm was applied retrospectively to 262,296 patients (test data set), excluding 99.9% of patients and identifying 30 patients eligible for exome sequencing. The algorithm's estimated recall (sensitivity) was 60% and precision (positive predictive value) was 15%. This process resulted in the diagnosis of 50% of patients (4/8) referred and evaluated in genetics. CONCLUSION: The search algorithm effectively identified patients retrospectively with an RGD and prospective deployment will ultimately help physicians "think rare."
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 | 0.007 | 0.041 |
| 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 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".