Developing an algorithm to identify individuals with psychosis in secondary care in England: application using the Mental Health Services Data Set
Bibliographic record
Abstract
BACKGROUND: There is currently no definitive method for identifying individuals with psychosis in secondary care on a population-level using administrative healthcare data from England. AIMS: To develop various algorithms to identify individuals with psychosis in the Mental Health Services Data Set (MHSDS), guided by national estimates of the prevalence of psychosis. METHOD: Using a combination of data elements in the MHSDS for financial years 2017-2018 and 2018-2019 (mental health cluster (a way to describe and classify a group of individuals with similar characteristics), Health of the Nation Outcome Scale (HoNOS) scores, reason for referral, primary diagnosis, first-episode psychosis flag, early intervention in psychosis team flag), we developed 12 unique algorithms to detect individuals with psychosis seen in secondary care. The resulting numbers were then compared with national estimates of the prevalence of psychosis to ascertain whether they were reasonable or not. RESULTS: The 12 algorithms produced 99 204-138 516 and 107 545-134 954 cases of psychosis for financial years 2017-2018 and 2018-2019, respectively, in line with national prevalence estimates. The numbers of cases of psychosis identified by the different algorithms differed according to the type and number (3-6) of data elements used. Most algorithms identified the same core of patients. CONCLUSIONS: The MHSDS can be used to identify individuals with psychosis in secondary care in England. Users can employ several algorithms to do so, depending on the objective of their analysis and their preference regarding the data elements employed. These algorithms could be used for surveillance, research and/or policy purposes.
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 | 0.030 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| 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".