> ## Content Index
> Fetch the complete content index at: https://www.coios.me/llms.txt
> Use this file to discover other available public pages before exploring further.

# Multimorbidity after myocardial infarction clusters into three trajectories in UK Biobank
- URL: https://www.coios.me/multimorbidity-after-myocardial-infarction-clusters-into/
- Published: 2026-11-01T09:19:59.000Z
- Updated: 2026-11-02T07:06:37.000Z
- Description: In 12 701 UK Biobank participants after myocardial infarction, three multimorbidity trajectories emerged; the SMART score predicted mortality better.
- Author: Daniel Ryan
- Tags: Data, models and systems, What linked data reveals, AI in medicine, United Kingdom, #peer-reviewed, #refines, #item, #source-2026-11, #score-55

The study analysed hospital diagnoses for five years after incident acute myocardial infarction in 12 701 UK Biobank participants. Dynamic Time Warping clustering grouped patients whose diagnoses built up in a similar pattern, even at different speeds. The groups were cardiometabolic (63.4%), heart-valve, atrial fibrillation and kidney-metabolic disease (13.5%), and smoking-related multisystem disease (23.1%; five-year mortality 43.9%). XGBoost predicted the group from pre-infarction diagnoses with an AUC of 0.906, but only 0.635 without the final pre-infarction week. The SMART score predicted mortality better (C-index 0.65 vs 0.59); trajectory effects lost significance after full adjustment. UK Biobank volunteers are healthier and mostly White British, and only hospital diagnosis codes were used.

*Why it is interesting: Diagnosis clusters after a heart attack separated survival before adjustment but added little beyond an established vascular risk score. Their predictive accuracy depended heavily on diagnoses recorded in the week before infarction.*

Source

[Journal of the American Medical Informatics Association, 1 November 2026](https://doi.org/10.1093/jamia/ocag135?ref=coios.me)

Paper

Explainable temporal machine learning of multimorbidity trajectories after acute myocardial infarction: complementing clinical risk scores with mechanistic phenotypes

Authors

Onoja A, Elomaa K, Whetton AD, Geifman N

DOI

10.1093/jamia/ocag135

Full text

[Open copy](https://pmc.ncbi.nlm.nih.gov/articles/PMC13687755/?ref=coios.me) (open-access copy, PubMed Central)

Type

Peer-reviewed article

Design

Retrospective cohort, unsupervised temporal clustering (DTW k-means) plus supervised classifiers and PheWAS, 12,701 UK Biobank participants after acute myocardial infarction, 5-year mortality endpoint

Verdict

Refines prior evidence

Driver

[What linked data reveals](https://www.coios.me/d-linked-data/)

Driver

[AI in medicine](https://www.coios.me/d-ai-medicine/)

Free full text

[Free to read at the publisher](https://doi.org/10.1093/jamia/ocag135?ref=coios.me)

Attention

1 citation (Crossref) · as of 2026-11-02

Abstract — the authors' own words, CC BY

Objective

This study aimed to identify trajectories of multimorbidity following acute myocardial infarction (AMI), using explainable temporal machine-learning methods, and assess their clinical, prognostic, and biological significance. Materials and methods

Dynamic Time Warping k-means clustering was applied to post-AMI diagnostic sequences from 12 701 UK-Biobank participants. Latent Dirichlet Allocation characterised cluster themes. Multiclass classifiers (CatBoost, XGBoost, random forest, logistic regression) trained on pre-AMI diagnoses and demographics predicted trajectory membership, with SHAP interpretability. SMART scores and Cox models evaluated 5-year mortality; Phenotype-Wide Association (PheWAS) and Reactome pathway enrichment were used to identify associated biological mechanisms. Results

Three trajectories of multimorbidity were identified: acute cardiorenal-respiratory with metabolic disease (ACUTE-CARD; 63.4%), cardiometabolic disease with arrhythmic-ischemic burden (CARDIOMIX; 13.5%), and smoking-related multisystem multimorbidity (SMO-CARD; 23.1%). XGBoost achieved the highest discrimination (AUC-ROC 0.906; 95% CI, 0.895-0.916), with CatBoost showing comparable performance (AUC-ROC 0.900; 95% CI, 0.889-0.910). SMO-CARD had the highest 5-year mortality (43.9%). The established SMART cardiovascular risk score remained the dominant predictor of mortality while the identified trajectories provided complementary prognostic signals; these associations were weaker after full adjustment for potential confounders with each profile displaying distinct genetic and pathway signatures. Discussion

The SMART score outperformed in capturing mortality risk, whereas the trajectories complement it by revealing nuanced clustering of risk factors across organ systems and in identifying trajectory-specific intervention priorities. Conclusion

Explainable temporal modeling of EHR data reveals clinically interpretable, biologically grounded multimorbidity trajectories after AMI that complement established risk scores and provide a reproducible approach to mechanistic phenotyping and precision care.