Risk prediction in people with acute myocardial infarction in England: a cohort study using data from 1521 general practices
Bibliographic record
Abstract
OBJECTIVE: To develop prediction models for short-term outcomes following a first acute myocardial infarction (AMI) event (index) or for past AMI events (prevalent) in a national primary care cohort. DESIGN: Retrospective cohort study using logistic regression models to estimate 1-year and 5-year risks of all-cause mortality and composite cardiovascular outcomes. SETTING: Primary care practices in England contributing data to the Clinical Practice Research Datalink (CPRD) Aurum and CPRD GOLD databases between 2006 and 2019. PARTICIPANTS: Patients with an incident (index) or prevalent AMI event. Models were trained on a random 80% sample of CPRD Aurum (n=1018 practices), internally validated on the remaining 20% (n=255) and externally validated using CPRD GOLD (n=248). OUTCOME MEASURES: Discrimination assessed using sensitivity, specificity and area under the receiver operating characteristic curve (AUC). Calibration assessed using calibration plots. RESULTS: In the index (prevalent) cohorts, 94 241 (64 789) patients were included in the training and internal validation sets, and 16 832 (7479) in the external validation set. For the index cohort, AUCs for 1-year [5-year] all-cause mortality were 0.802 (95% CI 0.793 to 0.812) [0.847 (0.841 to 0.853)] internally and 0.800 (0.790 to 0.810) [0.841 (0.835 to 0.847)] externally. For the primary composite outcome (stroke, heart failure and all-cause death), AUCs were 0.763 (0.756 to 0.771) [0.824 (0.818 to 0.830)] internally and 0.748 (0.739 to 0.756) [0.808 (0.801 to 0.815)] externally. Discrimination was higher in the prevalent cohort, particularly for 1-year mortality (AUC: 0.896, 95% CI 0.887 to 0.904). Models excluding treatment variables showed slightly lower but comparable performance. Calibration was acceptable across models. CONCLUSIONS: These models can support clinicians in identifying patients at increased risk of short-term adverse outcomes following AMI, whether newly diagnosed or with a prior history. This can inform monitoring strategies and secondary prevention and guide patient counselling on modifiable risk factors.
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 | 0.003 | 0.011 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".