Abstract Aims Risk scores are essential to evidence-based cardiovascular care, but manual calculation is labour intensive and error prone. Large language models (LLMs) could automate this process, yet LLMs are limited by their propensity for calculation errors and factual hallucinations. Pipelines separating LLM-based data extraction from deterministic score computation may improve reliability and transparency. Methods and results We conducted a retrospective diagnostic study at a quaternary heart centre in Germany (January 2020 to July 2023). Patients with atrial fibrillation (n = 179) from an ablation registry and patients with severe aortic stenosis (n = 76) evaluated by a heart team were included. Six LLMs (GPT-5.2, Gemini 3.1 Pro, DeepSeek-R1, Qwen3, GPT-OSS 120B, and Kimi K2.5) were tested in standalone, retrieval-augmented generation (RAG), and pipeline configurations to compute HAS-BLED, CHA2DS2-VASc, and EuroSCORE II scores from routine clinical reports. Accuracy was assessed against expert-adjudicated ground truth using root mean squared error (RMSE) and Krippendorff’s α to evaluate numerical deviation and categorical agreement, respectively. Pipeline-generated scores showed substantially higher agreement with expert adjudication than standalone LLMs, LLMs with RAG, and treating physicians (mean Krippendorff’s α: 0.78 vs. 0.32 vs. 0.39 vs. 0.31) and lower deviation from ground truth (mean RMSE: 0.89 vs. 5.81 vs. 1.85 vs. 1.34). Conclusion Pipelines combining expert-curated knowledge injection, LLM-based clinical data extraction, and deterministic score calculation enable accurate and scalable cardiovascular risk score computation from unstructured real-world clinical data, outperforming physician-documented scores. Such pipelines could form the basis for clinical decision-support systems that automate routine risk assessment, reduce clinician workload, and promote more consistent evidence-based care.
Tobias Roeschl, Marie Hoffmann, A. Unbehaun et al.· European Heart Journal - Dig...· 0 citations
BACKGROUND AND AIM
Randomized trials conducted in the early 2000s established the survival benefit of primary prevention implantable cardioverter-defibrillator (ICD) therapy in patients with reduced left ventricular ejection fraction (LVEF) after myocardial infarction. However, management of myocardial infarction and heart failure has substantially evolved since that time. We investigated whether the estimated association between primary prevention ICD implantation in post-myocardial infarction patients with reduced LVEF and mortality reduction has changed over time.
METHODS
We analyzed individual participant data from 32,214 patients with LVEF ≤35% after myocardial infarction included in the PROFID pooled cohort, comprising 7,477 patients carrying a primary prevention ICD (ICD patients) and 24,737 patients without an ICD (non-ICD patients). The primary endpoint was all-cause mortality. Propensity scores were estimated using multivariable logistic regression including age, sex, LVEF, renal function, and diabetes, and overlap weighting was applied to balance treatment groups. Time period-specific analyses were performed across three prespecified time periods defined by inclusion year: 1995-2004, 2005-2014, and 2015-2020. Weighted cumulative mortality curves were generated for each time period. Temporal changes in the estimated association between ICD implantation and mortality reduction were assessed using a weighted Cox proportional hazards model.
RESULTS
A total of 12,097 deaths occurred during a mean follow-up of 43.7 months. The estimated association between ICD implantation and mortality changed significantly across time (P for interaction <0.001). In weighted time period-specific analyses, the estimated mortality reduction associated with ICD implantation progressively decreased over more recent periods. The hazard ratio for ICD versus non-ICD patients was 0.54 (95% CI 0.47-0.62; P<0.001) in 1995-2004, 0.67 (95% CI 0.62-0.72; P<0.001) in 2005-2014, and 0.89 (95% CI 0.73-1.07; P=0.221) in 2015-2020, with negligible separation of the weighted cumulative mortality curves in the most recent time period.
CONCLUSIONS
In this analysis including a large cohort of post-myocardial infarction patients with reduced LVEF, the estimated mortality reduction associated with primary prevention ICD implantation progressively decreased over time.
A. Sepehri Shamloo, T. Chiba, J. G. Tijssen et al.· European Heart Journal· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
