Cardiovascular disease (CVD) continues to be the major cause of death globally, calling for predictive models that not only handle diverse and high-dimensional biomedical signals but also maintain interpretability and privacy. We create a single multimodal learning framework that integrates cross modal transformers with graph neural networks and causal representation learning to measure personalized CVD risk. The model combines genomic variation, cardiac MRI, ECG waveforms, wearable streams, and structured EHR data to predict risk while also implementing causal invariance constraints across different clinical subpopulations. To maintain transparency, we employ SHAP based feature attribution, counterfactual explanations and causal latent alignment for understandable risk factors. Besides, we position the design in a federated, privacy, preserving optimization protocol and establish rules for convergence, calibration and uncertainty quantification under distributional shift. Experimental studies based on large-scale biobank and multi institutional datasets reveal state discrimination and robustness, exhibiting fair performance across demographic strata and clinically distinct cohorts. This study paves the way for a principled approach to clinically trustworthy, interpretable and privacy respecting CVD prediction at the population level.

We present ASCENDgpt, a transformer-based model specifically designed for cardiovascular risk prediction from longitudinal electronic health records (EHRs). Our approach introduces a novel phenotype-aware tokenization scheme that maps 47,155 raw ICD codes to 176 clinically meaningful phenotype tokens, achieving 99.6\% consolidation of diagnosis codes while preserving semantic information. This phenotype mapping contributes to a total vocabulary of 10,442 tokens - a 77.9\% reduction when compared with using raw ICD codes directly. We pretrain ASCENDgpt on sequences derived from 19402 unique individuals using a masked language modeling objective, then fine-tune for time-to-event prediction of five cardiovascular outcomes: myocardial infarction (MI), stroke, major adverse cardiovascular events (MACE), cardiovascular death, and all-cause mortality. Our model achieves excellent discrimination on the held-out test set with an average C-index of 0.816, demonstrating strong performance across all outcomes (MI: 0.792, stroke: 0.824, MACE: 0.800, cardiovascular death: 0.842, all-cause mortality: 0.824). The phenotype-based approach enables clinically interpretable predictions while maintaining computational efficiency. Our work demonstrates the effectiveness of domain-specific tokenization and pretraining for EHR-based risk prediction tasks.

Electronic health records (EHRs) contain structured and unstructured data of significant clinical and research value. Various machine learning approaches have been developed to employ information in EHRs for risk prediction. The majority of these attempts, however, focus on structured EHR fields and lose the vast amount of information in the unstructured texts. To exploit the potential information captured in EHRs, in this study we propose a multimodal recurrent neural network model for cardiovascular risk prediction that integrates both medical texts and structured clinical information. The proposed multimodal bidirectional long short-term memory (BiLSTM) model concatenates word embeddings to classical clinical predictors before applying them to a final fully connected neural network. In the experiments, we compare performance of different deep neural network (DNN) architectures including convolutional neural network and long short-term memory in scenarios of using clinical variables and chest X-ray radiology reports. Evaluated on a data set of real world patients with manifest vascular disease or at high-risk for cardiovascular disease, the proposed BiLSTM model demonstrates state-of-the-art performance and outperforms other DNN baseline architectures.

Citation: Weng SF, Reps J, Kai J, Garibaldi JM, Qureshi N (2017) Can machine-learning improve cardiovascular risk prediction using routine clinical data? This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. The authors will make their data available upon specific requests subject to the requestor obtaining ethical and research approvals from the Clinical Practice Research Datalink Independent Scientific Advisory Committee (https://www.cprd.com/intro.asp) at the UK Medicines and Health Products Regulatory Agency. Funding: This paper presents independent research funded by the National Institute for Health Research School for Primary Care Research (NIHR SPCR): personal training fellowship award for SW from 2015-2018. The views expressed are those of the authors and not necessarily those of the NIHR, the NHS, or the Department of Health.

Disease risk estimates can be used as prognostic information and support for treating CVDs. The commonly used Framingham risk score (FRS) for CVD prediction is outdated for the modern population, so FRS may not be accurate enough. In this paper, a novel CVD prediction system based on machine learning is proposed. Methods: This study has been conducted with the data of 689 patients showing symptoms of CVD. Furthermore, the dataset of 5,209 CVD patients of the famous Framingham study has been used for validation purposes.