ArticleThe Lancet. Digital health2025
Refined selection of individuals for preventive cardiovascular disease treatment with a transformer-based risk model.
Article in The Lancet. Digital health, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 13 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
13 citing papers in PubMed.
- Artificial Intelligence in Cardiovascular Risk Prediction: An Up-to-Date Narrative Review on the Emerging Role of Lipid Profile-Based Models.Journal of clinical medicine · 2026Review
- Article
- Big Data and Trustworthy AI for Heart Failure: A Review.Circulation. Heart failure · 2026Review
- Preoperative identification of tumor deposits in rectal cancer using a transformer-based multimodal fusion model: a multicenter retrospective study.BMC medical imaging · 2026Article
- Integrated Deep Learning Surveillance of Unknown Pathogens with Pandemic Potential Using Pneumonia of Unknown Etiology.Pathogens (Basel, Switzerland) · 2026Article
- Computational Nutrition in Practice: Challenges and Opportunities From an Early-Career Perspective.The Journal of nutrition · 2026Article
- Automotive Health 2.0: Steering Toward Proactive Preventive Care.Mayo Clinic proceedings. Digital health · 2026Article
- Large Language Models in Cardiovascular Prevention: A Narrative Review and Governance Framework.Diagnostics (Basel, Switzerland) · 2026Review
- A transformer-based survival model for prediction of all-cause mortality in patients with heart failure: a multi-cohort study.NPJ digital medicine · 2026Article
- Redefining cardiometabolic biomarkers in the big data era: toward a personalized medicine-centered reconstruction of risk prediction models.Frontiers in cardiovascular medicine · 2026Article
- Performance comparison of different machine learning models to predict the risk of postcraniotomy nausea and vomiting: a retrospective study.Frontiers in medicine · 2026Article
- Redefining endpoints in heart failure clinical trials: the emerging role of wearable technologies in contemporary trial design.Heart failure reviews · 2025Review
- Advancing Risk-Based Approaches in Blood Pressure Management: Reflections on the 2025 AHA/ACC Statement.Hypertension (Dallas, Tex. : 1979) · 2025Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
12 authors.
Funding
Abstract
backgroundAlthough statistical models have been commonly used to identify patients at risk of cardiovascular disease for preventive therapy, these models tend to over-recommend therapy. Moreover, in populations with pre-existing diseases, the current approach is to indiscriminately treat all, as modelling in this context is currently inadequate. This study aimed to develop and validate the Transformer-based Risk assessment survival (TRisk) model, a novel deep learning model, for predicting 10-year risk of cardiovascular disease in both the primary prevention population and individuals with diabetes.
methodsAn open cohort of 3 million adults aged 25-84 years was identified using linked electronic health records from 291 general practices, for model development, and 98 general practices, for validation, across England from 1998 to 2015. Comparison against the QRISK3 score and a deep learning derivation of it was done. Additional analyses compared discriminatory performance in other age groups, by sex, and across categories of socioeconomic status.
findingsTRisk showed superior discrimination (C index in the primary prevention population 0·910; 95% CI 0·906-0·913). TRisk's performance was found to be less sensitive to population age range than the benchmark models and outperformed other models also in analyses stratified by age, sex, or socioeconomic status. All models were overall well calibrated. In decision curve analyses, TRisk showed a greater net benefit than benchmark models across the range of relevant thresholds. At the widely recommended 10% risk threshold and the higher 15% threshold, TRisk reduced both the total number of patients classified at high risk (by 20·6% and 34·6%, respectively) and the number of false negatives as compared with recommended strategies. TRisk similarly outperformed other models in patients with diabetes. Compared with the widely recommended treat-all policy approach for patients with diabetes, TRisk at a 10% risk threshold would lead to deselection of 24·3% of individuals, with a small fraction of false negatives (0·2% of the cohort).
interpretationTRisk enabled a more targeted selection of individuals at risk of cardiovascular disease in both the primary prevention population and cohorts with diabetes, compared with benchmark approaches. Incorporation of TRisk into routine care could potentially reduce the number of treatment-eligible patients by approximately one-third while preventing at least as many events as with currently adopted approaches.
fundingNone.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.