Validity of algorithms for identifying five chronic conditions in MedicineInsight, an Australian national general practice database
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
BACKGROUND: MedicineInsight is a database containing de-identified electronic health records (EHRs) from over 700 Australian general practices. It is one of the largest and most widely used primary health care EHR databases in Australia. This study examined the validity of algorithms that use information from various fields in the MedicineInsight data to indicate whether patients have specific health conditions. This study examined the validity of MedicineInsight algorithms for five common chronic conditions: anxiety, asthma, depression, osteoporosis and type 2 diabetes. METHODS: Patients' disease status according to MedicineInsight algorithms was benchmarked against the recording of diagnoses in the original EHRs. Fifty general practices contributing data to MedicineInsight met the eligibility criteria regarding patient load and location. Five were randomly selected and four agreed to participate. Within each practice, 250 patients aged ≥ 40 years were randomly selected from the MedicineInsight database. Trained staff reviewed the original EHR for as many of the selected patients as possible within the time available for data collection in each practice. RESULTS: A total of 475 patients were included in the analysis. All the evaluated MedicineInsight algorithms had excellent specificity, positive predictive value, and negative predictive value (above 0.9) when benchmarked against the recording of diagnoses in the original EHR. The asthma and osteoporosis algorithms also had excellent sensitivity, while the algorithms for anxiety, depression and type 2 diabetes yielded sensitivities of 0.85, 0.89 and 0.89 respectively. CONCLUSIONS: The MedicineInsight algorithms for asthma and osteoporosis have excellent accuracy and the algorithms for anxiety, depression and type 2 diabetes have good accuracy. This study provides support for the use of these algorithms when using MedicineInsight data for primary health care quality improvement activities, research and health system policymaking and planning.
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.
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 | 0.016 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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 it