Bibliographic record
Abstract
Aims: <br/>Misclassification of diabetes types (type 1, type 2 and MODY) is common, affecting 7%–15% of type 1 and 2 cases and 77% of MODY cases. We developed a decision support tool using validated prediction models to automatically search primary care systems and identify patients with diabetes at high probability of misclassification, and who may benefit from further investigations or referral to secondary care. This study evaluates the feasibility and acceptability of using this tool to improve diabetes classification in adults diagnosed ≤50 years.<br/><br/>Methods: <br/>A mixed-methods, non-randomised intervention study across 12 primary care practices in the Southwest and East Midlands, UK. Feasibility is assesed through practice uptake, data quality, misclassification rates and practitioner workload. Acceptability is explored via one-to-one qualitative interviews with up to 40 practice staff and patients and thematically analysed.<br/><br/>Results: <br/>Eleven practices have run the tool (mean practice size: 15,623), identifying a mean of 27 patients with diabetes per practice with potential misclassification: 3 with a high probability of MODY, 12 coded as type 1 but more likely type 2 and 12 coded as type 2 but more likely type 1. Preliminary qualitative data suggest the tool can help to audit miscoding and improve patient care. Practice staff reported that the tool was easy to use, though embedding in primary care systems was preferred.<br/><br/>Conclusions: <br/>The DePICtion tool shows promise for improving diabetes classification and is potentially acceptable to both practitioners and patients. Further refinement could ensure better diagnosis and management for more patients.
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 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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 teacher head, 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".