Algorithmic approach to finding people with multiple sclerosis using routine healthcare data in Wales
Bibliographic record
Abstract
BACKGROUND: Identification of multiple sclerosis (MS) cases in routine healthcare data repositories remains challenging. MS can have a protracted diagnostic process and is rarely identified as a primary reason for admission to the hospital. Difficulties in identification are compounded in systems that do not include insurance or payer information concerning drug treatments or non-notifiable disease. AIM: To develop an algorithm to reliably identify MS cases within a national health data bank. METHOD: Retrospective analysis of the Secure Anonymised Information Linkage (SAIL) databank was used to identify MS cases using a novel algorithm. Sensitivity and specificity were tested using two existing independent MS datasets, one clinically validated and population-based and a second from a self-registered MS national registry. RESULTS: From 4 757 428 records, the algorithm identified 6194 living cases of MS within Wales on 31 December 2020 (prevalence 221.65 (95% CI 216.17 to 227.24) per 100 000). Case-finding sensitivity and specificity were 96.8% and 99.9% for the clinically validated population-based cohort and sensitivity was 96.7% for the self-declared registry population. DISCUSSION: The algorithm successfully identified MS cases within the SAIL databank with high sensitivity and specificity, verified by two independent populations and has important utility in large-scale epidemiological studies of MS.
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 | 0.010 | 0.039 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.001 |
| Open science | 0.002 | 0.003 |
| 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".