Cardiovascular disease risk prediction using automated machine learning: A prospective study of 423,604 UK Biobank participants

Measuring early vascular aging in youth: an expert consensus document from the Youth Vascular Consortium

Since the conceptualization of early vascular aging (EVA) in 2008, significant efforts have been made to develop and improve its assessment. Initially lead by the investigation of arterial stiffness through pulse wave velocity (PWV), several additional vascular aging biomarkers have gained prominence in recent years. Despite expanding literature addressing methodological concerns associated with these biomarkers in youth, a standardized approach for clinical evaluation of EVA remains elusive, leaving pertinent gaps in understanding the optimal methodology. This article, resulting from international consensus efforts from the Youth Vascular Consortium, aims to provide an updated overview of methods available to measure EVA in youth and to discuss challenges in translating these methods into clinical practice.

CATI: A medical context-enhanced framework for diagnosis code assignment in the UK Biobank study

Diagnosis codes are standard code format of diseases or medical conditions. This study is aimed at assigning diagnosis codes to patients in large-scale biobanks, particularly addressing the issue of missing codes for some patients. This is crucial for downstream disease-related tasks. While recent methods primarily rely on structured biobank data for code assignment, they often overlook the valuable medical context provided by textual information in the biobanks and hierarchical structure of the disease coding system. To address this gap, we have developed CATI, a medical context-enhanced framework for diagnosis Code Assignment by integrating Textual details derived from key features and disease hIerarchy. The study is based on the UK Biobank data and considers Phecodes and ICD-10 codes as standard disease formats. We start by representing ten informative codified features using their formal names and then integrate them into CATI as text embeddings, achieved through prompt tuning on the pre-trained language model BioBERT. Recognizing the hierarchical structure of diagnosis codes, we have developed a novel convolution layer in our method that effectively propagates logits between adjacent diagnosis codes. Evaluation results demonstrate that CATI outperforms existing state-of-the-art methods in terms of both Phecodes and ICD-10 codes, boasting at least a 5.16% improvement in average AUROC for unseen disease codes and an 8.68% rise in average AUPRC for disease codes with training instances ranging in (1000,10000]. This framework contributes to the formation of well-defined cohorts for downstream studies and offers a unique perspective for addressing complex healthcare tasks by incorporating vital medical context.

Role of artificial intelligence in early identification and risk evaluation of non-communicable diseases: a bibliometric analysis of global research trends

OBJECTIVE

This study aims to shed light on the transformative potential of artificial intelligence (AI) in the early detection and risk assessment of non-communicable diseases (NCDs).

STUDY DESIGN

Bibliometric analysis.

SETTING

Articles related to AI in early identification and risk evaluation of NCDs from 2000 to 2024 were retrieved from the Scopus database.

METHODS

This comprehensive bibliometric study focuses on a single database, Scopus and employs narrative synthesis for concise yet informative summaries. Microsoft Excel V.365 and VOSviewer software (V.1.6.20) were used to summarise bibliometric features.

RESULTS

The study retrieved 1745 relevant articles, with a notable surge in research activity in recent years. Core journals included Scientific Reports and IEEE Access, and core institutions included the Harvard Medical School and the Ministry of Education of the People's Republic of China, while core countries comprised China, the USA, India, the UK and Saudi Arabia. Citation trends indicated substantial growth and recognition of AI's impact on NCDs management. Frequent author keywords identified key research hotspots, including specific NCDs like Alzheimer's disease and diabetes. Risk assessment studies demonstrated improved predictions for heart failure, cardiovascular risk, breast cancer, diabetes and inflammatory bowel disease.

CONCLUSION

Our findings highlight the increasing role of AI in early detection and risk prediction of NCDs, emphasising its widening research impact and future clinical potential.

UKB-MDRMF: a multi-disease risk and multimorbidity framework based on UK biobank data

The rapid accumulation of biomedical cohort data presents opportunities to explore disease mechanisms, risk factors, and prognostic markers. However, current research often has a narrow focus, limiting the exploration of risk factors and inter-disease correlations. Additionally, fragmented processes and time constraints can hinder comprehensive analysis of the disease landscape. Our work addresses these challenges by integrating multimodal data from the UK Biobank, including basic, lifestyle, measurement, environment, genetic, and imaging data. We propose UKB-MDRMF, a comprehensive framework for predicting and assessing health risks across 1560 diseases. Unlike single disease models, UKB-MDRMF incorporates multimorbidity mechanisms, resulting in superior predictive accuracy, with all disease types showing improved performance in risk assessment. By jointly predicting and assessing multiple diseases, UKB-MDRMF uncovers shared and distinctive connections among risk factors and diseases, offering a broader perspective on health and multimorbidity mechanisms.

Do positive psychosocial factors contribute to the prediction of coronary artery disease? A UK Biobank-based machine learning approach

AIMS

Most prediction models for coronary artery disease (CAD) compile biomedical and behavioural risk factors using linear multivariate models. This study explores the potential of integrating positive psychosocial factors (PPFs), including happiness, satisfaction with life, and social support, into conventional and machine learning-based CAD-prediction models.

METHODS AND RESULTS

We included UK Biobank (UKB) participants without CAD at baseline. First, we estimated associations of individual PPFs with subsequent acute myocardial infarction (AMI) and chronic ischaemic heart disease (CIHD) using logistic regression. Then, we compared the performances of logistic regression and eXtreme Gradient Boosting (XGBoost) prediction models when adding PPFs as predictors to the Framingham Risk Score (FRS). Based on a sample size between 160 226 and 441 419 of UKB participants, happiness, satisfaction with health and life, and participation in social activities were linked to lower AMI and CIHD risk (all P-for-trend ≤ 0.04), while social support was not. In a validation sample, adding PPFs to the FRS using logistic regression and XGBoost prediction models improved neither AMI [area under the receiver operating characteristic curve (AUC) change: 0.02 and 0.90%, respectively] nor CIHD (AUC change: -1.10 and -0.88%, respectively) prediction.

CONCLUSION

Positive psychosocial factors were individually linked to CAD risk, in line with previous studies, and as reflected by the new European Society of Cardiology guidelines on cardiovascular disease prevention. However, including available PPFs in CAD-prediction models did not improve prediction compared with the FRS alone. Future studies should explore whether PPFs may act as CAD-risk modifiers, especially if the individual's risk is close to a decision threshold.

Deep conditional generative model for personalization of 12-lead electrocardiograms and cardiovascular risk prediction

Background

12-lead electrocardiograms (ECGs) are a cornerstone for diagnosing and monitoring cardiovascular diseases (CVDs). They play a key role in detecting abnormalities such as arrhythmias and myocardial infarction, enabling early intervention and risk stratification. However, traditional analysis relies heavily on manual interpretation, which is time-consuming and expertise-dependent. Moreover, existing machine learning models often lack personalization, as they fail to integrate subject-specific anatomical and demographic information. Advances in deep generative models offer an opportunity to overcome these challenges by synthesizing personalized ECGs and extracting clinically relevant features for improved risk assessment.

Methods

We propose a conditional Variational Autoencoder (cVAE) framework to generate realistic, subject-specific 12-lead ECGs by incorporating demographic metadata, anatomical heart features, and ECG electrodes' positions as conditioning factors. This allows for physiologically consistent and personalized ECG synthesis. Furthermore, we introduce a revised Cox proportional-hazards regression model that utilizes the latent embeddings learned by the cVAE to predict future CVD risk. This approach not only enhances the interpretability of ECG-derived risk factors but also demonstrates the potential of deep generative models in personalized cardiac assessment.

Results

Our model is trained and validated on the UK Biobank dataset and in silico simulation data. By incorporating heart position and electrodes' positions, the generated ECGs demonstrate strong consistency with in silico simulations, providing insights into the relationship between cardiac anatomy and ECG morphology. Furthermore, our CVD risk prediction model achieves a C-index of 0.65, indicating that ECG signals, together with demographic and anatomical information, contain valuable prognostic information for stratifying subjects based on future cardiovascular risk.

Conclusion

This work marks a significant advancement in ECG analysis by providing a conditional VAE framework that not only improves ECG generation but also enriches our understanding of the relationship between ECG patterns and subject-specific information. Importantly, our approach enables clinically significant information to be extracted from 12-lead ECGs, providing valuable insights for predicting future CVD risks.

The genetic architecture of and evolutionary constraints on the human pelvic form

Human pelvic evolution following the human-chimpanzee divergence is thought to result in an obstetrical dilemma, a mismatch between large infant brains and narrowed female birth canals, but empirical evidence has been equivocal. By using deep learning on 31,115 dual-energy x-ray absorptiometry scans from UK Biobank, we identified 180 loci associated with seven highly heritable pelvic phenotypes. Birth canal phenotypes showed sex-specific genetic architecture, aligning with reproductive function. Larger birth canals were linked to slower walking pace and reduced back pain but increased hip osteoarthritis risk, whereas narrower birth canals were associated with reduced pelvic floor disorder risk but increased obstructed labor risk. Lastly, genetic correlation between birth canal and head widths provides evidence of coevolution between the human pelvis and brain, partially mitigating the dilemma.

A microbiota pattern associated with cardiovascular events in secondary prevention: the CORDIOPREV study

BACKGROUND AND AIMS

Preventing new cardiovascular events in patients with established cardiovascular disease (CVD) is a daunting task for clinicians. Intestinal microbiota may help identify patients at risk, thus improving the strategies of secondary prevention. The aim of this study was to evaluate the baseline differences between the gut microbiota from coronary heart disease (CHD) patients suffering new major adverse cardiovascular events (MACEs) in the following 7 years, compared with CHD patients who did not undergo new MACE in this period, and to build a score associated with the risk of suffering new MACE.

METHODS

Within the framework of the CORDIOPREV study, a clinical trial that involved 1002 patients with CHD, intestinal microbiota was examined in patients with available faecal samples (n = 679, 132 MACE), through 16S metagenomics on the Illumina MiSeq and Quiime2 software. Lipopolysaccharide (LPS) was measured using limulus amoebocyte lysate test.

RESULTS

Random survival forest identified 10 bacterial taxa with a higher predictive power for MACE incidence. Receiver operating characteristic curves yielded an area under the curve of 65.2% (59.1%-71.3%) in the training set and 68.6% (59.3%-77.9%) in the validation set. The intestinal microbiota risk score was associated with a MACE incidence hazard ratio of 2.01 (95% confidence interval 1.37-3.22). Lipopolysaccharide analysis showed a greater LPS post-prandial fold change in the MACE group (P = .005).

CONCLUSIONS

These results reinforce the relationship between intestinal microbiota and CVD and suggest that a microbiota profile is associated with MACE in CHD patients, in addition to higher endotoxaemia.

Machine learning-based models to predict type 2 diabetes combined with coronary heart disease and feature analysis-based on interpretable SHAP

BACKGROUND

Type 2 diabetes and coronary heart disease exhibit heightened prevalence in the Chinese population, posing as leading causes of mortality. The combination of diabetes and coronary heart disease, due to its challenging diagnosis and poor prognosis, imposes a significant disease burden. In recent years, machine learning has frequently been employed in diagnostic applications within medical fields; however, predictive models for type 2 diabetes complicated by coronary heart disease have been confronted with issues such as lower predictive performance and interference from other comorbidities during prediction.

METHODS

This study enhances the predictive accuracy, sensitivity, specificity, F1 score, and AUC of models forecasting the coexistence of diabetes and coronary heart disease. We developed an advanced prediction model using XGBoost combined with SHAP for feature analysis. Through comparative feature selection, hyperparameter optimization, and computational efficiency analysis, we identified optimal conditions for model performance. External validation with independent datasets confirmed the model's robustness and generalizability, supporting its potential implementation in clinical practice.

RESULTS

This study compared three models-Random Forest, LightGBM, and XGBoost-and found that XGBoost exhibited superior performance in both efficacy and computational efficiency. The accuracy (Acc) of the XGBoost model was 0.8910, which improved to 0.8942 after hyperparameter tuning. External validation using datasets from Pingyang Hospital and Heji Hospital in Shanxi Province, China, yielded an AUC of 0.7897, demonstrating robust generalizability. By integrating SHAP (SHapley Additive exPlanations) for interpretability, our study identified bilirubin levels, basophil count, cholesterol levels, and age as key features for predicting the coexistence of type 2 diabetes mellitus (T2DM) and coronary heart disease (CHD). These findings are seamlessly consistent with the feature importance rankings determined by the XGBoost algorithm. The model demonstrates moderate predictive performance (AUC = 0.7879 in external validation) with practical interpretability, offering potential utility in improving diagnostic efficiency for T2DM-CHD comorbidity in resource-limited settings. However, its clinical implementation requires further validation in diverse populations.

Harnessing Electronic Health Records and Artificial Intelligence for Enhanced Cardiovascular Risk Prediction: A Comprehensive Review

Electronic health records (EHR) have revolutionized cardiovascular disease (CVD) research by enabling comprehensive, large-scale, and dynamic data collection. Integrating EHR data with advanced analytical methods, including artificial intelligence (AI), transforms CVD risk prediction and management methodologies. This review examines the advancements and challenges of using EHR in developing CVD prediction models, covering traditional and AI-based approaches. While EHR-based CVD risk prediction has greatly improved, moving from models that integrate real-world data on medication use and imaging, challenges persist regarding data quality, standardization across health care systems, and geographic variability. The complexity of EHR data requires sophisticated computational methods and multidisciplinary approaches for effective CVD risk modeling. AI's deep learning enhances prediction performance but faces limitations in interpretability and the need for validation and recalibration for diverse populations. The future of CVD risk prediction and management increasingly depends on using EHR and AI technologies effectively. Addressing data quality issues and overcoming limitations from retrospective data analysis are critical for improving the reliability and applicability of risk prediction models. Integrating multidimensional data, including environmental, lifestyle, social, and genomic factors, could significantly enhance risk assessment. These models require continuous validation and recalibration to ensure their adaptability to diverse populations and evolving health care environments, providing reassurance about their reliability.

Pathways to chronic disease detection and prediction: Mapping the potential of machine learning to the pathophysiological processes while navigating ethical challenges

Chronic diseases such as heart disease, cancer, and diabetes are leading drivers of mortality worldwide, underscoring the need for improved efforts around early detection and prediction. The pathophysiology and management of chronic diseases have benefitted from emerging fields in molecular biology like genomics, transcriptomics, proteomics, glycomics, and lipidomics. The complex biomarker and mechanistic data from these "omics" studies present analytical and interpretive challenges, especially for traditional statistical methods. Machine learning (ML) techniques offer considerable promise in unlocking new pathways for data-driven chronic disease risk assessment and prognosis. This review provides a comprehensive overview of state-of-the-art applications of ML algorithms for chronic disease detection and prediction across datasets, including medical imaging, genomics, wearables, and electronic health records. Specifically, we review and synthesize key studies leveraging major ML approaches ranging from traditional techniques such as logistic regression and random forests to modern deep learning neural network architectures. We consolidate existing literature to date around ML for chronic disease prediction to synthesize major trends and trajectories that may inform both future research and clinical translation efforts in this growing field. While highlighting the critical innovations and successes emerging in this space, we identify the key challenges and limitations that remain to be addressed. Finally, we discuss pathways forward toward scalable, equitable, and clinically implementable ML solutions for transforming chronic disease screening and prevention.

Adaptable graph neural networks design to support generalizability for clinical event prediction

OBJECTIVE

While many machine learning and deep learning-based models for clinical event prediction leverage various data elements from electronic healthcare records such as patient demographics and billing codes, such models face severe challenges when tested outside of their institution of training. These challenges are rooted not only in differences in patient population characteristics, but medical practice patterns of different institutions.

METHOD

We propose a solution to this problem through systematically adaptable design of graph-based convolutional neural networks (GCNN) for clinical event prediction. Our solution relies on the unique property of GCNN where data encoded as graph edges is only implicitly used during the prediction process and can be adapted after model training without requiring model re-training.

RESULTS

Our adaptable GCNN-based prediction models outperformed all comparative models during external validation for two different clinical problems, while supporting multimodal data integration. For prediction of hospital discharge and mortality, the comparative fusion baseline model achieved 0.58 [0.52-0.59] and 0.81[0.80-0.82] AUROC on the external dataset while the GCNN achieved 0.70 [0.68-0.70] and 0.91 [0.90-0.92] respectively. For prediction of future unplanned transfusion, we observed even more gaps in performance due to missing/incomplete data in the external dataset - late fusion achieved 0.44[0.31-0.56] while the GCNN model achieved 0.70 [0.62-0.84].

CONCLUSION

These results support our hypothesis that carefully designed GCNN-based models can overcome generalization challenges faced by prediction models.

Machine Learning-Driven discovery of immunogenic cell Death-Related biomarkers and molecular classification for diabetic ulcers

In this study, we redefine the diagnostic landscape of diabetic ulcers (DUs), a major diabetes complication. Our research uncovers new biomarkers linked to immunogenic cell death (ICD) in DUs by utilizing RNA-sequencing data of Gene Expression Omnibus (GEO) analysis combined with a comprehensive database interrogation. Employing a random forest algorithm, we have developed a diagnostic model that demonstrates improved accuracy in distinguishing DUs from normal tissue, with satisfactory results from ROC analysis. Beyond mere diagnosis, our model categorizes DUs into novel molecular classifications, which may enhance our comprehension of their underlying pathophysiology. This study bridges the gap between molecular insights and clinical practice. It sets the stage for transformative strategies in DUs management, marking a significant step forward in personalized medicine for diabetic patients.

Comparison of cardiovascular risk prediction models developed using machine learning based on data from a Sri Lankan cohort with World Health Organization risk charts for predicting cardiovascular risk among Sri Lankans: a cohort study

INTRODUCTION

Models derived from non-Sri Lankan cohorts are used for cardiovascular (CV) risk stratification of Sri Lankans.

OBJECTIVE

To develop a CV risk prediction model using machine learning (ML) based on data from a Sri Lankan cohort followed up for 10 years, and to compare the predictions with WHO risk charts.

DESIGN

Cohort study.

SETTING

The Ragama Health Study (RHS), an ongoing, prospective, population-based cohort study of patients randomly selected from the Ragama Medical Office of Heath area, Sri Lanka, focusing on the epidemiology of non-communicable diseases, was used to develop the model. The external validation cohort included patients admitted to Colombo North Teaching Hospital (CNTH), a tertiary care hospital in Sri Lanka, from January 2019 through August 2020.

PARTICIPANTS

All RHS participants, aged 40-64 years in 2007, without cardiovascular disease (CVD) at baseline, who had complete data of 10-year outcome by 2017, were used for model development. Patients aged 40-74 years admitted to CNTH during the study period with incident CV events or a disease other than an acute CV event (CVE) with complete data for CVD risk calculation were used for external validation of the model.

METHODS

Using the follow-up data of the cohort, we developed two ML models for predicting 10-year CV risk using six conventional CV risk variables (age, gender, smoking status, systolic blood pressure, history of diabetes, and total cholesterol level) and all available variables (n=75). The ML models were derived using classification algorithms of the supervised learning technique. We compared the predictive performance of our ML models with WHO risk charts (2019, Southeast Asia) using area under the receiver operating characteristic curves (AUC-ROC) and calibration plots. We validated the 6-variable model in an external hospital-based cohort.

RESULTS

Of the 2596 participants in the baseline cohort, 179 incident CVEs were observed over 10 years. WHO risk charts predicted only 10 CVEs (AUC-ROC: 0.51, 95% CI 0.42 to 0.60), while the new 6-variable ML model predicted 125 CVEs (AUC-ROC: 0.72, 95% CI 0.66 to 0.78) and the 75-variable ML model predicted 124 CVEs (AUC-ROC: 0.74, 95% CI 0.68 to 0.80). Calibration results (Hosmer-Lemeshow test) for the 6-variable ML model and the WHO risk charts were χ2=12.85 (p=0.12) and χ2=15.58 (p=0.05), respectively. In the external validation cohort, the sensitivity, specificity, positive predictive value, negative predictive value, and calibration of the 6-variable ML model and the WHO risk charts, respectively, were: 70.3%, 94.9%, 87.3%, 86.6%, χ2=8.22, p=0.41 and 23.7%, 79.0%, 35.8%, 67.7%, χ2=81.94, p<0.0001.

CONCLUSIONS

ML-based models derived from a cohort of Sri Lankans improved the overall accuracy of CV-risk prediction compared with the WHO risk charts for this cohort of Southeast Asians.

A prediction study on the occurrence risk of heart disease in older hypertensive patients based on machine learning

OBJECTIVE

Constructing a predictive model for the occurrence of heart disease in elderly hypertensive individuals, aiming to provide early risk identification.

METHODS

A total of 934 participants aged 60 and above from the China Health and Retirement Longitudinal Study with a 7-year follow-up (2011-2018) were included. Machine learning methods (logistic regression, XGBoost, DNN) were employed to build a model predicting heart disease risk in hypertensive patients. Model performance was comprehensively assessed using discrimination, calibration, and clinical decision curves.

RESULTS

After a 7-year follow-up of 934 older hypertensive patients, 243 individuals (26.03%) developed heart disease. Older hypertensive patients with baseline comorbid dyslipidemia, chronic pulmonary diseases, arthritis or rheumatic diseases faced a higher risk of future heart disease. Feature selection significantly improved predictive performance compared to the original variable set. The ROC-AUC for logistic regression, XGBoost, and DNN were 0.60 (95% CI: 0.53-0.68), 0.64 (95% CI: 0.57-0.71), and 0.67 (95% CI: 0.60-0.73), respectively, with logistic regression achieving optimal calibration. XGBoost demonstrated the most noticeable clinical benefit as the threshold increased.

CONCLUSION

Machine learning effectively identifies the risk of heart disease in older hypertensive patients based on data from the CHARLS cohort. The results suggest that older hypertensive patients with comorbid dyslipidemia, chronic pulmonary diseases, and arthritis or rheumatic diseases have a higher risk of developing heart disease. This information could facilitate early risk identification for future heart disease in older hypertensive patients.

A multitask deep learning model utilizing electrocardiograms for major cardiovascular adverse events prediction

Deep learning analysis of electrocardiography (ECG) may predict cardiovascular outcomes. We present a novel multi-task deep learning model, the ECG-MACE, which predicts the one-year first-ever major adverse cardiovascular events (MACE) using 2,821,889 standard 12-lead ECGs, including training (n = 984,895), validation (n = 422,061), and test (n = 1,414,933) sets, from Chang Gung Memorial Hospital database in Taiwan. Data from another independent medical center (n = 113,224) was retrieved for external validation. The model's performance achieves AUROCs of 0.90 for heart failure (HF), 0.85 for myocardial infarction (MI), 0.76 for ischemic stroke (IS), and 0.89 for mortality. Furthermore, it outperforms the Framingham risk score at 5-year MACEs and 10-year mortality prediction. Over 10-year follow-ups, the model-predicted-positive group exhibits significantly higher MACE incidences than the model-predicted-negative group (relative incidence ratio: HF: 15.28; MI: 7.87; IS: 4.74; mortality: 13.18). Using solely ECGs, ECG-MACE effectively predicts one-year events and exhibits long-term anticipation. It provides potential applications in preventive medicine.

A machine learning model utilizing Delphian lymph node characteristics to predict contralateral central lymph node metastasis in papillary thyroid carcinoma: a prospective multicenter study

BACKGROUND

This study aimed to use artificial intelligence (AI) to integrate various radiological and clinical pathological data to identify effective predictors of contralateral central lymph node metastasis (CCLNM) in patients with papillary thyroid carcinoma (PTC) and to establish a clinically applicable model to guide the extent of surgery.

METHODS

This prospective cohort study included 603 patients with PTC from three centers. Clinical, pathological, and ultrasonographic data were collected and utilized to develop a machine learning (ML) model for predicting CCLNM. Model development at the internal center utilized logistic regression along with other ML algorithms. Diagnostic efficacy was compared among these methods, leading to the adoption of the final model (random forest). This model was subject to AI interpretation and externally validated at other centers.

RESULTS

CCLNM was associated with multiple pathological factors. The Delphian lymph node metastasis ratio, ipsilateral central lymph node metastasis number, and presence of ipsilateral central lymph node metastasis were independent risk factors for CCLNM. Following feature selection, a Delphian lymph node-CCLNM (D-CCLNM) model was established using the Random forest algorithm based on five attributes. The D-CCLNM model demonstrated the highest area under the curve (AUC; 0.9273) in the training cohort and exhibited high predictive accuracy, with AUCs of 0.8907 and 0.9247 in the external and validation cohorts, respectively.

CONCLUSIONS

The authors developed a new, effective method that uses ML to predict CCLNM in patients with PTC. This approach integrates data from Delphian lymph nodes and clinical characteristics, offering a foundation for guiding surgical decisions, and is conveniently applicable in clinical settings.

Predicting rapid progression in knee osteoarthritis: a novel and interpretable automated machine learning approach, with specific focus on young patients and early disease

OBJECTIVES

To facilitate the stratification of patients with osteoarthritis (OA) for new treatment development and clinical trial recruitment, we created an automated machine learning (autoML) tool predicting the rapid progression of knee OA over a 2-year period.

METHODS

We developed autoML models integrating clinical, biochemical, X-ray and MRI data. Using two data sets within the OA Initiative-the Foundation for the National Institutes of Health OA Biomarker Consortium for training and hold-out validation, and the Pivotal Osteoarthritis Initiative MRI Analyses study for external validation-we employed two distinct definitions of clinical outcomes: Multiclass (categorising OA progression into pain and/or radiographic) and binary. Key predictors of progression were identified through advanced interpretability techniques, and subgroup analyses were conducted by age, sex and ethnicity with a focus on early-stage disease.

RESULTS

Although the most reliable models incorporated all available features, simpler models including only clinical variables achieved robust external validation performance, with area under the precision-recall curve (AUC-PRC) 0.727 (95% CI: 0.726 to 0.728) for multiclass predictions; and AUC-PRC 0.764 (95% CI: 0.762 to 0.766) for binary predictions. Multiclass models performed best in patients with early-stage OA (AUC-PRC 0.724-0.806) whereas binary models were more reliable in patients younger than 60 (AUC-PRC 0.617-0.693). Patient-reported outcomes and MRI features emerged as key predictors of progression, though subgroup differences were noted. Finally, we developed web-based applications to visualise our personalised predictions.

CONCLUSIONS

Our novel tool's transparency and reliability in predicting rapid knee OA progression distinguish it from conventional 'black-box' methods and are more likely to facilitate its acceptance by clinicians and patients, enabling effective implementation in clinical practice.

Machine learning based prediction models for cardiovascular disease risk using electronic health records data: systematic review and meta-analysis

Cardiovascular disease (CVD) remains a major cause of mortality in the UK, prompting the need for improved risk predictive models for primary prevention. Machine learning (ML) models utilizing electronic health records (EHRs) offer potential enhancements over traditional risk scores like QRISK3 and ASCVD. To systematically evaluate and compare the efficacy of ML models against conventional CVD risk prediction algorithms using EHR data for medium to long-term (5-10 years) CVD risk prediction. A systematic review and random-effect meta-analysis were conducted according to preferred reporting items for systematic reviews and meta-analyses guidelines, assessing studies from 2010 to 2024. We retrieved 32 ML models and 26 conventional statistical models from 20 selected studies, focusing on performance metrics such as area under the curve (AUC) and heterogeneity across models. ML models, particularly random forest and deep learning, demonstrated superior performance, with the highest recorded pooled AUCs of 0.865 (95% CI: 0.812-0.917) and 0.847 (95% CI: 0.766-0.927), respectively. These significantly outperformed the conventional risk score of 0.765 (95% CI: 0.734-0.796). However, significant heterogeneity (I² > 99%) and potential publication bias were noted across the studies. While ML models show enhanced calibration for CVD risk, substantial variability and methodological concerns limit their current clinical applicability. Future research should address these issues by enhancing methodological transparency and standardization to improve the reliability and utility of these models in clinical settings. This study highlights the advanced capabilities of ML models in CVD risk prediction and emphasizes the need for rigorous validation to facilitate their integration into clinical practice.

Triglyceride to high density lipoprotein cholesterol ratio and major adverse cardiovascular events in ACS patients undergoing PCI

The triglyceride to high density lipoprotein cholesterol (TG/HDL-C) ratio has been consistently linked with the risk of coronary heart disease (CHD). Nevertheless, there is a paucity of studies focusing on acute coronary syndrome (ACS) patients undergoing percutaneous coronary intervention (PCI) or experiencing bleeding events. The study encompassed 17,643 ACS participants who underwent PCI. Survival analysis, Cox regression analysis and restricted cubic spline (RCS) were employed to assess the associations between TG/HDL-C ratio and the risk of major adverse cardiovascular events (MACE), all-cause death, cardiac death and all-cause bleeding events. Over a 12-month follow-up period, 638 (3.9%) patients experienced MACE while 2837 (16.1%) patients experienced bleeding events. The TG/HDL-C ratio exhibited significant positive correlations with the incidence of MACE, all-cause death and cardiac death; conversely it displayed significant negative correlations with the incidence of all-cause bleeding. Patients in the high quartile TG/HDL-C category demonstrated significantly higher risks for MACE compared to those in the low quartile category, with hazard ratio (HR) [95%confidence interval (CI)] of 1.46 (1.17-1.83); conversely, they showed significantly lower risks for all-cause bleeding compared to their counterparts in the low quartile group, with HR (95%CI) of 0.72 (0.65-0.81). The structure of subgroup analyses remained robust and consistent, with gender being the sole factor interacting with TG/HDL-C specifically in relation to MACE events (P for interaction = 0.037). A higher baseline TG/HDL-C ratio was associated with an elevated risk of MACE but a reduced risk of bleeding events in ACS patients undergoing PCI.

Bias in machine learning applications to address non-communicable diseases at a population-level: a scoping review

BACKGROUND

Machine learning (ML) is increasingly used in population and public health to support epidemiological studies, surveillance, and evaluation. Our objective was to conduct a scoping review to identify studies that use ML in population health, with a focus on its use in non-communicable diseases (NCDs). We also examine potential algorithmic biases in model design, training, and implementation, as well as efforts to mitigate these biases.

METHODS

We searched the peer-reviewed, indexed literature using Medline, Embase, Cochrane Central Register of Controlled Trials and Cochrane Database of Systematic Reviews, CINAHL, Scopus, ACM Digital Library, Inspec, Web of Science's Science Citation Index, Social Sciences Citation Index, and the Emerging Sources Citation Index, up to March 2022.

RESULTS

The search identified 27 310 studies and 65 were included. Study aims were separated into algorithm comparison (n = 13, 20%) or disease modelling for population-health-related outputs (n = 52, 80%). We extracted data on NCD type, data sources, technical approach, possible algorithmic bias, and jurisdiction. Type 2 diabetes was the most studied NCD. The most common use of ML was for risk modeling. Mitigating bias was not extensively addressed, with most methods focused on mitigating sex-related bias.

CONCLUSION

This review examines current applications of ML in NCDs, highlighting potential biases and strategies for mitigation. Future research should focus on communicable diseases and the transferability of ML models in low and middle-income settings. Our findings can guide the development of guidelines for the equitable use of ML to improve population health outcomes.

Detecting cardiovascular diseases using unsupervised machine learning clustering based on electronic medical records

BACKGROUND

Electronic medical records (EMR)-trained machine learning models have the potential in CVD risk prediction by integrating a range of medical data from patients, facilitate timely diagnosis and classification of CVDs. We tested the hypothesis that unsupervised ML approach utilizing EMR could be used to develop a new model for detecting prevalent CVD in clinical settings.

METHODS

We included 155,894 patients (aged ≥ 18 years) discharged between January 2014 and July 2022, from Xuhui Hospital, Shanghai, China, including 64,916 CVD cases and 90,979 non-CVD cases. K-means clustering was used to generate the clustering models with k = 2, 4, and 8 as predetermined number of clusters k = 2, 4, and 8. Bayesian theorem was used to estimate the models' predictive accuracy.

RESULTS

The overall predictive accuracy of the 2-, 4-, and 8-classification clustering models in the training set was 0.856, 0.8634, and 0.8506, respectively. Similarly, the predictive accuracy of the 2-, 4-, and 8-classification clustering models in the testing set was 0.8598, 0.8659, and 0.8525, respectively. After reducing from 19 dimensions to 2 dimensions by principal component analysis, significant separation was observed for CVD cases and non-CVD cases in both training and testing sets.

CONCLUSION

Our findings indicate that the utilization of EMR data can support the development of a robust model for CVD detection through an unsupervised ML approach. Further investigation using longitudinal design is needed to refine the model for its applications in clinical settings.

Development of a recommendation system and data analysis in personalized medicine: an approach towards healthy vascular ageing

Purpose

Understanding early vascular ageing has become crucial for preventing adverse cardiovascular events. To this respect, recent AI-based risk clustering models offer early detection strategies focused on healthy populations, yet their complexity limits clinical use. This work introduces a novel recommendation system embedded in a web app to assess and mitigate early vascular ageing risk, leading patients towards improved cardiovascular health.

Methods

This system employs a methodology that calculates distances within multidimensional spaces and integrates cost functions to obtain personalized optimisation of recommendations. It also incorporates a classification system for determining the intensity levels of the clinical interventions.

Results

The recommendation system showed high efficiency in identifying and visualizing individuals at high risk of early vascular ageing among healthy patients. Additionally, the system corroborated its consistency and reliability in generating personalized recommendations among different levels of granularity, emphasizing its focus on moderate or low-intensity recommendations, which could improve patient adherence to the intervention.

Conclusion

This tool might significantly aid healthcare professionals in their daily analysis, improving the prevention and management of cardiovascular diseases.

AI-CADR: Artificial Intelligence Based Risk Stratification of Coronary Artery Disease Using Novel Non-Invasive Biomarkers

Coronary artery disease (CAD) is one of the most common causes of sudden cardiac arrest, accounting for a large percentage of global mortality. A timely diagnosis and detection may save a person's life. The research suggests a methodological framework for non-invasive risk stratification based on information only possible after invasive coronary angiography. Novel clinical, chemical, and molecular cardiac biomarkers were used as input features from an especially collected dataset. Following a thorough evaluative search in the biomarker feature space, the optimum parameters for classifier or regression technique (regressor) were selected using K-fold cross-validation. Ten machine learning (ML) classifiers were employed in classification tasks to determine the number of affected cardiac vessels, the Gensini group, and the severity of CAD with 82.58%, 86.26%, and 90.91% accuracy, respectively. Eleven approaches were used in regression tasks to calculate stenosis percentage and Gensini score, with R-squared values of 0.58 and 0.56, respectively. Following a thorough evaluative search in the biomarkers feature space, the optimum feature and classifier or regressor set were selected using K-fold cross-validation. The biomarkers and classifier or regressor combinations serve as the foundation for the proposed risk stratification framework, incorporating clinical protocol. Finally, our proposed framework is compared to state-of-the-art studies, offering a robust, well-rounded, early detection capable, and novel 'biomarkers-ML combination' approach to risk stratification.

Mitigating Algorithmic Bias in AI-Driven Cardiovascular Imaging for Fairer Diagnostics

Background/Objectives: The research addresses algorithmic bias in deep learning models for cardiovascular risk prediction, focusing on fairness across demographic and socioeconomic groups to mitigate health disparities. It integrates fairness-aware algorithms, susceptible carrier-infected-recovered (SCIR) models, and interpretability frameworks to combine fairness with actionable AI insights supported by robust segmentation and classification metrics. Methods: The research utilised quantitative 3D/4D heart magnetic resonance imaging and tabular datasets from the Cardiac Atlas Project's (CAP) open challenges to explore AI-driven methodologies for mitigating algorithmic bias in cardiac imaging. The SCIR model, known for its robustness, was adapted with the Capuchin algorithm, adversarial debiasing, Fairlearn, and post-processing with equalised odds. The robustness of the SCIR model was further demonstrated in the fairness evaluation metrics, which included demographic parity, equal opportunity difference (0.037), equalised odds difference (0.026), disparate impact (1.081), and Theil Index (0.249). For interpretability, YOLOv5, Mask R-CNN, and ResNet18 were implemented with LIME and SHAP. Bias mitigation improved disparate impact (0.80 to 0.95), reduced equal opportunity difference (0.20 to 0.05), and decreased false favourable rates for males (0.0059 to 0.0033) and females (0.0096 to 0.0064) through balanced probability adjustment. Results: The SCIR model outperformed the SIR model (recovery rate: 1.38 vs 0.83) with a -10% transmission bias impact. Parameters (β=0.5, δ=0.2, γ=0.15) reduced susceptible counts to 2.53×10-12 and increased recovered counts to 9.98 by t=50. YOLOv5 achieved high Intersection over Union (IoU) scores (94.8%, 93.7%, 80.6% for normal, severe, and abnormal cases). Mask R-CNN showed 82.5% peak confidence, while ResNet demonstrated a 10.4% accuracy drop under noise. Performance metrics (IoU: 0.91-0.96, Dice: 0.941-0.980, Kappa: 0.95) highlighted strong predictive accuracy and reliability. Conclusions: The findings validate the effectiveness of fairness-aware algorithms in addressing cardiovascular predictive model biases. The integration of fairness and explainable AI not only promotes equitable diagnostic precision but also significantly reduces diagnostic disparities across vulnerable populations. This reduction in disparities is a key outcome of the research, enhancing clinical trust in AI-driven systems. The promising results of this study pave the way for future work that will explore scalability in real-world clinical settings and address limitations such as computational complexity in large-scale data processing.

Machine learning-based prediction model for brain metastasis in patients with extensive-stage small cell lung cancer

Brain metastases (BMs) in extensive-stage small cell lung cancer (ES-SCLC) are often associated with poor survival rates and quality of life, making the timely identification of high-risk patients for BMs in ES-SCLC crucial. Patients diagnosed with ES-SCLC between 2010 and 2018 were screened from the Surveillance, Epidemiology, and End Results (SEER) database. Four different machine learning (ML) algorithms were used to create prediction models for BMs in ES-SCLC patients. The accuracy, sensitivity, specificity, AUROC, and AUPRC were compared among these models and traditional logistic regression (LR). The random forest (RF) model demonstrated the best performance and was chosen for further analysis. The AUROC and AUPRC were calculated and compared. The findings from the RF model were utilized to identify the risk factors linked to BMs in patients diagnosed with ES-SCLC. Examining 4,716 instances of ES-SCLC, the research conducted an analysis, with brain metastases arising in 1,900 cases. Through evaluation of the ROC curve and PRC concerning the RF Model, results depicted an AUROC of 0.896 (95% CI: 0.889-0.899) and AUPRC of 0.900 (95% CI: 0.895-0.904). Test accuracy measured at 0.810 (95% CI: 0.784-0.833), sensitivity at 0.797 (95% CI: 0.756-0.841), and specificity at 0.819 (95% CI: 0.754-0.879). Based on the SHAP analysis of the RF predictive model, the top 10 most relevant features were identified and ranked in order of relative importance: bone metastasis, liver metastasis, radiation, age, tumor size, primary tumor location, N-stage, race, T-stage, and chemotherapy. The research developed and validated a predictive RF model using clinical and pathological data to predict the risk of BMs in patients with ES-SCLC. This model may assist physicians in making clinical decisions that could delay the onset of BMs and improve patient survival rates.

Risk management of patients with multiple CVDs: what are the best practices?

INTRODUCTION

Managing patients with multiple risk factors for CVDs can present distinct challenges for healthcare providers, therefore addressing them can be paramount to optimize patient care.

AREAS COVERED

This narrative review explores the burden that CVDs place on healthcare systems as well as how we can best optimize the risk management of these patients. Through a comprehensive review of literature, guidelines and clinical studies, this paper explores various approaches to risk management, lifestyle modifications and pharmacological interventions utilized in the management of CVDs. Furthermore, emerging technologies such as machine learning (ML) are discussed, highlighting potential opportunities for future research. By reviewing existing recommendations and evidence, this paper aims to provide insight into optimizing strategies and improving the outcomes for patients with multiple CVDs.

EXPERT OPINION

Optimizing risk factors can have a significant impact on patient outcomes, as such each patient should have a clear plan on how to manage these risk factors to minimize adverse healthcare results.

A machine learning model for early diagnosis of type 1 Gaucher disease using real-life data

OBJECTIVE

The diagnosis of Gaucher disease (GD) presents a major challenge due to the high variability and low specificity of its clinical characteristics, along with limited physician awareness of the disease's early symptoms. Early and accurate diagnosis is important to enable effective treatment decisions, prevent unnecessary testing, and facilitate genetic counseling. This study aimed to develop a machine learning (ML) model for GD screening and GD early diagnosis based on real-world clinical data using the Maccabi Healthcare Services electronic database, which contains 20 years of longitudinal data on approximately 2.6 million patients.

STUDY DESIGN AND SETTING

We screened the Maccabi Healthcare Services database for patients with GD between January 1998 and May 2022. Eligible controls were matched by year of birth, sex, and socioeconomic status in a 1:13 ratio. The data were partitioned into 75% training and 25% test sets and trained to predict GD using features obtained from medical and laboratory records. Model performances were evaluated using the area under the receiver operating characteristic curve and the area under the precision-recall curve.

RESULTS

We detected 264 confirmed patients with GD to which we matched 3,429 controls. The best model performance (which included known GD signs and symptoms, previously unknown clinical features, and administrative codes) on the test set had an area under the receiver operating characteristic curve = 0.95 ± 0.03 and area under the precision-recall curve = 0.80 ± 0.08, which yielded a median GD identification of 2.78 years earlier than the clinical diagnosis (25th-75th percentile: 1.29-4.53).

CONCLUSION

Using an ML approach on real-world data led to excellent discrimination between GD patients and controls, with the ability to detect GD significantly earlier than the time of actual diagnosis. Hence, this approach might be useful as a screening tool for GD and lead to earlier diagnosis and treatment. Furthermore, advanced ML analytics may highlight previously unrecognized features associated with GD, including clinical diagnoses and health-seeking behaviors.

Development and validation of a cardiovascular risk prediction model for Sri Lankans using machine learning

INTRODUCTION AND OBJECTIVES

Sri Lankans do not have a specific cardiovascular (CV) risk prediction model and therefore, World Health Organization(WHO) risk charts developed for the Southeast Asia Region are being used. We aimed to develop a CV risk prediction model specific for Sri Lankans using machine learning (ML) of data of a population-based, randomly selected cohort of Sri Lankans followed up for 10 years and to validate it in an external cohort.

MATERIAL AND METHODS

The cohort consisted of 2596 individuals between 40-65 years of age in 2007, who were followed up for 10 years. Of them, 179 developed hard CV diseases (CVD) by 2017. We developed three CV risk prediction models named model 1, 2 and 3 using ML. We compared predictive performances between models and the WHO risk charts using receiver operating characteristic curves (ROC). The most predictive and practical model for use in primary care, model 3 was named "SLCVD score" which used age, sex, smoking status, systolic blood pressure, history of diabetes, and total cholesterol level in the calculation. We developed an online platform to calculate the SLCVD score. Predictions of SLCVD score were validated in an external hospital-based cohort.

RESULTS

Model 1, 2, SLCVD score and the WHO risk charts predicted 173, 162, 169 and 10 of 179 observed events and the area under the ROC (AUC) were 0.98, 0.98, 0.98 and 0.52 respectively. During external validation, the SLCVD score and WHO risk charts predicted 56 and 18 respectively of 119 total events and AUCs were 0.64 and 0.54 respectively.

CONCLUSIONS

SLCVD score is the first and only CV risk prediction model specific for Sri Lankans. It predicts the 10-year risk of developing a hard CVD in Sri Lankans. SLCVD score was more effective in predicting Sri Lankans at high CV risk than WHO risk charts.

Assessing the relative importance of vitamin D deficiency in cardiovascular health

Previous research has suggested a potential link between vitamin D (VD) deficiency and adverse cardiovascular health outcomes, although the findings have been inconsistent. This study investigates the association between VD deficiency and cardiovascular disease (CVD) within the context of established CVD risk factors. We utilized a Random Forest model to predict both CVD and VD deficiency risks, using a dataset of 1,078 observations from a rural Chinese population. Feature importance was evaluated using SHapley Additive exPlanations (SHAP) to discern the impact of various risk factors on the model's output. The results showed that the model for CVD prediction achieved a high accuracy of 87%, demonstrating robust performance across precision, recall, and F1 score metrics. Conversely, the VD deficiency prediction model exhibited suboptimal performance, with an accuracy of 52% and lower precision, recall, and F1 scores. Feature importance analysis indicated that traditional risk factors such as systolic blood pressure, diastolic blood pressure, age, body mass index, and waist-to-hip ratio significantly influenced CVD risk, collectively contributing to 70% of the model's predictive power. Although VD deficiency was associated with an increased risk of CVD, its importance in predicting CVD risk was notably low. Similarly, for VD deficiency prediction, CVD risk factors such as systolic blood pressure, glucose levels, diastolic blood pressure, and body mass index emerged as influential features. However, the overall predictive performance of the VD deficiency prediction model was weak (52%), indicating the absence of VD deficiency-related risk factors. Ablation experiments confirmed the relatively lower importance of VD deficiency in predicting CVD risk. Furthermore, the SHAP partial dependence plot revealed a nonlinear relationship between VD levels and CVD risk. In conclusion, while VD deficiency appears directly or indirectly associated with increased CVD risk, its relative importance within predictive models is considerably lower when compared to other risk factors. These findings suggest that VD deficiency may not warrant primary focus in CVD risk assessment and prevention strategies, however, further research is needed to explore the causal relationship between VD deficiency and CVD risk.

Is cardiovascular risk profiling from UK Biobank retinal images using explicit deep learning estimates of traditional risk factors equivalent to actual risk measurements? A prospective cohort study design

OBJECTIVE

Despite extensive exploration of potential biomarkers of cardiovascular diseases (CVDs) derived from retinal images, it remains unclear how retinal images contribute to CVD risk profiling and how the results can inform lifestyle modifications. Therefore, we aimed to determine the performance of cardiovascular risk prediction model from retinal images via explicitly estimating 10 traditional CVD risk factors and compared with the model based on actual risk measurements.

DESIGN

A prospective cohort study design.

SETTING

The UK Biobank (UKBB), a prospective cohort study, following the health conditions including CVD outcomes of adults recruited between 2006 and 2010.

PARTICIPANTS

A subset of data from the UKBB which contains 52 297 entries with retinal images and 5-year cumulative incidence of major adverse cardiovascular events (MACE) was used. Our dataset is split into 3:1:1 as training set (n=31 403), validation set (n=10 420) and testing set (n=10 474). We developed a deep learning (DL) model to predict 5-year MACE using a two-stage DL neural network.

PRIMARY AND SECONDARY OUTCOME MEASURES

We computed accuracy, area under the receiver operating characteristic curve (AUC) and compared variations in the risk prediction models combining CVD risk factors and retinal images.

RESULTS

The first-stage DL model demonstrated that the 10 CVD risk factors can be estimated from a given retinal image with an accuracy ranging between 65.2% and 89.8% (overall AUC of 0.738 with 95% CI: 0.710 to 0.766). In MACE prediction, our model outperformed the traditional score-based models, with 8.2% higher AUC than Systematic COronary Risk Evaluation (SCORE), 3.5% for SCORE 2 and 7.1% for the Framingham Risk Score (with p value<0.05 for all three comparisons).

CONCLUSIONS

Our algorithm estimates the 5-year risk of MACE based on retinal images, while explicitly presenting which risk factors should be checked and intervened. This two-stage approach provides human interpretable information between stages, which helps clinicians gain insights into the screening process copiloting with the DL model.

Building Digital Twins for Cardiovascular Health: From Principles to Clinical Impact

The past several decades have seen rapid advances in diagnosis and treatment of cardiovascular diseases and stroke, enabled by technological breakthroughs in imaging, genomics, and physiological monitoring, coupled with therapeutic interventions. We now face the challenge of how to (1) rapidly process large, complex multimodal and multiscale medical measurements; (2) map all available data streams to the trajectories of disease states over the patient's lifetime; and (3) apply this information for optimal clinical interventions and outcomes. Here we review new advances that may address these challenges using digital twin technology to fulfill the promise of personalized cardiovascular medical practice. Rooted in engineering mechanics and manufacturing, the digital twin is a virtual representation engineered to model and simulate its physical counterpart. Recent breakthroughs in scientific computation, artificial intelligence, and sensor technology have enabled rapid bidirectional interactions between the virtual-physical counterparts with measurements of the physical twin that inform and improve its virtual twin, which in turn provide updated virtual projections of disease trajectories and anticipated clinical outcomes. Verification, validation, and uncertainty quantification builds confidence and trust by clinicians and patients in the digital twin and establishes boundaries for the use of simulations in cardiovascular medicine. Mechanistic physiological models form the fundamental building blocks of the personalized digital twin that continuously forecast optimal management of cardiovascular health using individualized data streams. We present exemplars from the existing body of literature pertaining to mechanistic model development for cardiovascular dynamics and summarize existing technical challenges and opportunities pertaining to the foundation of a digital twin.

Detection of cardiovascular disease cases using advanced tree-based machine learning algorithms

Cardiovascular disease (CVD) can often lead to serious consequences such as death or disability. This study aims to identify a tree-based machine learning method with the best performance criteria for the detection of CVD. This study analyzed data collected from 9,499 participants, with a focus on 38 different variables. The target variable was the presence of cardiovascular disease (CVD) and the villages were considered as the cluster variable. The standard tree, random forest, Generalized Linear Mixed Model tree (GLMM tree), and Generalized Mixed Effect random forest (GMERF) were fitted to the data and the estimated prediction power indices were compared to identify the best approach. According to the analysis of important variables in all models, five variables (age, LDL, history of cardiac disease in first-degree relatives, physical activity level, and presence of hypertension) were identified as the most influential in predicting CVD. Fitting the decision tree, random forest, GLMM tree, and GMERF, respectively, resulted in an area under the ROC curve of 0.56, 0.73, 0.78, and 0.80. The GMERF model demonstrated the best predictive performance among the fitted models based on evaluation criteria. Regarding the clustered structure of the data, using relevant machine-learning approaches that account for this clustering may result in more accurate predicting indices and targeted prevention frameworks.

Feasibility of multiorgan risk prediction with routinely collected diagnostics: a prospective cohort study in the UK Biobank

OBJECTIVES

Despite rising rates of multimorbidity, existing risk assessment tools are mostly limited to a single outcome of interest. This study tests the feasibility of producing multiple disease risk estimates with at least 70% discrimination (area under the receiver operating curve, AUROC) within the time and information constraints of the existing primary care health check framework.

DESIGN

Observational prospective cohort study SETTING: UK Biobank.

PARTICIPANTS

228 240 adults from the UK population.

INTERVENTIONS

None.

MAIN OUTCOME MEASURES

Myocardial infarction, atrial fibrillation, heart failure, stroke, all-cause dementia, chronic kidney disease, fatty liver disease, alcoholic liver disease, liver cirrhosis and liver failure.

RESULTS

Using a set of predictors easily gathered at the standard primary care health check (such as the National Health Service Health Check), we demonstrate that it is feasible to simultaneously produce risk estimates for multiple disease outcomes with AUROC of 70% or greater. These predictors can be entered once into a single form and produce risk scores for stroke (AUROC 0.727, 95% CI 0.713 to 0.740), all-cause dementia (0.823, 95% CI 0.810 to 0.836), myocardial infarction (0.785, 95% CI 0.775 to 0.795), atrial fibrillation (0.777, 95% CI 0.768 to 0.785), heart failure (0.828, 95% CI 0.818 to 0.838), chronic kidney disease (0.774, 95% CI 0.765 to 0.783), fatty liver disease (0.766, 95% CI 0.753 to 0.779), alcoholic liver disease (0.864, 95% CI 0.835 to 0.894), liver cirrhosis (0.763, 95% CI 0.734 to 0.793) and liver failure (0.746, 95% CI 0.695 to 0.796).

CONCLUSIONS

Easily collected diagnostics can be used to assess 10-year risk across multiple disease outcomes, without the need for specialist computing or invasive biomarkers. Such an approach could increase the utility of existing data and place multiorgan risk information at the fingertips of primary care providers, thus creating opportunities for longer-term multimorbidity prevention. Additional work is needed to validate whether these findings would hold in a larger, more representative cohort outside the UK Biobank.

An interpretable machine learning method for risk stratification of patients with acute coronary syndrome

Backgrounds

Risk stratification for major adverse cardiovascular events (MACE) within one year in patients with acute coronary syndrome (ACS) undergoing percutaneous coronary intervention (PCI) remains a challenge. Although several predictive models based on machine learning have emerged, they are difficult to understand. This study aimed to develop a machine learning prediction model that is easy to understand and trustworthy by lay people to assess the risk of MACE in ACS patients undergoing PCI within one year of the procedure.

Methods

This retrospective cohort study used medical data from 1105 patients to construct a machine-learning model. To ensure thoroughness and multidimensionality of model parsing, Shapley Additive explanations (SHAP) analysis and Local interpretable model-agnostic explanations (LIME) interpretation techniques were used to systematically and deeply interpret the constructed models from a global to a detailed level.

Results

The study assessed 12 machine learning methods' prediction models and found that the Random Forest model was the most effective in predicting the risk of MACE in ACS patients after undergoing PCI. The model achieved an AUC value of 0.807 in the validation set, with an accuracy of 0.82, and a stable F1 score of 0.51. SHAP analysis ranked eight key feature variables, such as LVEF, in global importance. The weights of each feature range in the prediction model were revealed using LIME analysis.

Conclusion

The machine learning prediction model we developed is capable of accurately predicting the likelihood of patients with ACS experiencing a MACE within one year of surgery.

Development and validation of 10-year risk prediction models of cardiovascular disease in Chinese type 2 diabetes mellitus patients in primary care using interpretable machine learning-based methods

AIM

To develop 10-year cardiovascular disease (CVD) risk prediction models in Chinese patients with type 2 diabetes mellitus (T2DM) managed in primary care using machine learning (ML) methods.

METHODS

In this 10-year population-based retrospective cohort study, 141 516 Chinese T2DM patients aged 18 years or above, without history of CVD or end-stage renal disease and managed in public primary care clinics in 2008, were included and followed up until December 2017. Two-thirds of the patients were randomly selected to develop sex-specific CVD risk prediction models. The remaining one-third of patients were used as the validation sample to evaluate the discrimination and calibration of the models. ML-based methods were applied to missing data imputation, predictor selection, risk prediction modelling, model interpretation, and model evaluation. Cox regression was used to develop the statistical models in parallel for comparison.

RESULTS

During a median follow-up of 9.75 years, 32 445 patients (22.9%) developed CVD. Age, T2DM duration, urine albumin-to-creatinine ratio (ACR), estimated glomerular filtration rate (eGFR), systolic blood pressure variability and glycated haemoglobin (HbA1c) variability were the most important predictors. ML models also identified nonlinear effects of several predictors, particularly the U-shaped effects of eGFR and body mass index. The ML models showed a Harrell's C statistic of >0.80 and good calibration. The ML models performed significantly better than the Cox regression models in CVD risk prediction and achieved better risk stratification for individual patients.

CONCLUSION

Using routinely available predictors and ML-based algorithms, this study established 10-year CVD risk prediction models for Chinese T2DM patients in primary care. The findings highlight the importance of renal function indicators, and variability in both blood pressure and HbA1c as CVD predictors, which deserve more clinical attention. The derived risk prediction tools have the potential to support clinical decision making and encourage patients towards self-care, subject to further research confirming the models' feasibility, acceptability and applicability at the point of care.

Machine learning and statistical models to predict all-cause mortality in type 2 diabetes: Results from the UK Biobank study

AIMS

This study aims to compare the performance of contemporary machine learning models with statistical models in predicting all-cause mortality in patients with type 2 diabetes mellitus and to develop a user-friendly mortality risk prediction tool.

METHODS

A prospective cohort study was conducted including 22,579 people with diabetes from the UK Biobank. Models evaluated include Cox proportional hazards, random survival forests (RSF), gradient boosting (GB) survival, DeepSurv, and DeepHit.

RESULTS

Over a median follow-up period of 9 years, 2,665 patients died. Machine learning models outperformed the Cox model in the validation dataset, with C-index values of 0.72-0.73 vs. 0.71 for Cox (p < 0.01). Deep learning models, particularly DeepHit, demonstrated superior calibration and achieved lower Brier scores (0.09 vs. 0.10 for Cox, p < 0.05). An online prediction tool based on the DeepHit was developed for patient care: http://123.57.42.89:6006/.

CONCLUSIONS

Machine learning models performed better than statistical models, highlighting the potential of machine learning techniques for predicting all-cause mortality risk and facilitating personalized healthcare management for individuals with diabetes.

The essential role of dual-energy x-ray absorptiometry in the prediction of subclinical cardiovascular disease

Subclinical cardiovascular disease (Sub-CVD) is an early stage of cardiovascular disease and is often asymptomatic. Risk factors, including hypertension, diabetes, obesity, and lifestyle, significantly affect Sub-CVD. Progress in imaging technology has facilitated the timely identification of disease phenotypes and risk categorization. The critical function of dual-energy x-ray absorptiometry (DXA) in predicting Sub-CVD was the subject of this research. Initially used to evaluate bone mineral density, DXA has now evolved into an indispensable tool for assessing body composition, which is a pivotal determinant in estimating cardiovascular risk. DXA offers precise measurements of body fat, lean muscle mass, bone density, and abdominal aortic calcification, rendering it an essential tool for Sub-CVD evaluation. This study examined the efficacy of DXA in integrating various risk factors into a comprehensive assessment and how the application of machine learning could enhance the early discovery and control of cardiovascular risks. DXA exhibits distinct advantages and constraints compared to alternative imaging modalities such as ultrasound, computed tomography, magnetic resonance imaging, and positron emission tomography. This review advocates DXA incorporation into cardiovascular health assessments, emphasizing its crucial role in the early identification and management of Sub-CVD.

Cardiovascular Disease Risk Stratification Using Hybrid Deep Learning Paradigm: First of Its Kind on Canadian Trial Data

BACKGROUND

The risk of cardiovascular disease (CVD) has traditionally been predicted via the assessment of carotid plaques. In the proposed study, AtheroEdge™ 3.0HDL (AtheroPoint™, Roseville, CA, USA) was designed to demonstrate how well the features obtained from carotid plaques determine the risk of CVD. We hypothesize that hybrid deep learning (HDL) will outperform unidirectional deep learning, bidirectional deep learning, and machine learning (ML) paradigms.

METHODOLOGY

500 people who had undergone targeted carotid B-mode ultrasonography and coronary angiography were included in the proposed study. ML feature selection was carried out using three different methods, namely principal component analysis (PCA) pooling, the chi-square test (CST), and the random forest regression (RFR) test. The unidirectional and bidirectional deep learning models were trained, and then six types of novel HDL-based models were designed for CVD risk stratification. The AtheroEdge™ 3.0HDL was scientifically validated using seen and unseen datasets while the reliability and statistical tests were conducted using CST along with p-value significance. The performance of AtheroEdge™ 3.0HDL was evaluated by measuring the p-value and area-under-the-curve for both seen and unseen data.

RESULTS

The HDL system showed an improvement of 30.20% (0.954 vs. 0.702) over the ML system using the seen datasets. The ML feature extraction analysis showed 70% of common features among all three methods. The generalization of AtheroEdge™ 3.0HDL showed less than 1% (p-value < 0.001) difference between seen and unseen data, complying with regulatory standards.

CONCLUSIONS

The hypothesis for AtheroEdge™ 3.0HDL was scientifically validated, and the model was tested for reliability and stability and is further adaptable clinically.

Deep learning-derived splenic radiomics, genomics, and coronary artery disease

Background

Despite advances in managing traditional risk factors, coronary artery disease (CAD) remains the leading cause of mortality. Circulating hematopoietic cells influence risk for CAD, but the role of a key regulating organ, spleen, is unknown. The understudied spleen is a 3-dimensional structure of the hematopoietic system optimally suited for unbiased radiologic investigations toward novel mechanistic insights.

Methods

Deep learning-based image segmentation and radiomics techniques were utilized to extract splenic radiomic features from abdominal MRIs of 42,059 UK Biobank participants. Regression analysis was used to identify splenic radiomics features associated with CAD. Genome-wide association analyses were applied to identify loci associated with these radiomics features. Overlap between loci associated with CAD and the splenic radiomics features was explored to understand the underlying genetic mechanisms of the role of the spleen in CAD.

Results

We extracted 107 splenic radiomics features from abdominal MRIs, and of these, 10 features were associated with CAD. Genome-wide association analysis of CAD-associated features identified 219 loci, including 35 previously reported CAD loci, 7 of which were not associated with conventional CAD risk factors. Notably, variants at 9p21 were associated with splenic features such as run length non-uniformity.

Conclusions

Our study, combining deep learning with genomics, presents a new framework to uncover the splenic axis of CAD. Notably, our study provides evidence for the underlying genetic connection between the spleen as a candidate causal tissue-type and CAD with insight into the mechanisms of 9p21, whose mechanism is still elusive despite its initial discovery in 2007. More broadly, our study provides a unique application of deep learning radiomics to non-invasively find associations between imaging, genetics, and clinical outcomes.

Improving cardiovascular risk prediction with machine learning: a focus on perivascular adipose tissue characteristics

BACKGROUND

Timely prevention of major adverse cardiovascular events (MACEs) is imperative for reducing cardiovascular diseases-related mortality. Perivascular adipose tissue (PVAT), the adipose tissue surrounding coronary arteries, has attracted increased amounts of attention. Developing a model for predicting the incidence of MACE utilizing machine learning (ML) integrating clinical and PVAT features may facilitate targeted preventive interventions and improve patient outcomes.

METHODS

From January 2017 to December 2019, we analyzed a cohort of 1077 individuals who underwent coronary CT scanning at our facility. Clinical features were collected alongside imaging features, such as coronary artery calcium (CAC) scores and perivascular adipose tissue (PVAT) characteristics. Logistic regression (LR), Framingham Risk Score, and ML algorithms were employed for MACE prediction.

RESULTS

We screened seven critical features to improve the practicability of the model. MACE patients tended to be older, smokers, and hypertensive. Imaging biomarkers such as CAC scores and PVAT characteristics differed significantly between patients with and without a 3-year MACE risk in a population that did not exhibit disparities in laboratory results. The ensemble model, which leverages multiple ML algorithms, demonstrated superior predictive performance compared with the other models. Finally, the ensemble model was used for risk stratification prediction to explore its clinical application value.

CONCLUSIONS

The developed ensemble model effectively predicted MACE incidence based on clinical and imaging features, highlighting the potential of ML algorithms in cardiovascular risk prediction and personalized medicine. Early identification of high-risk patients may facilitate targeted preventive interventions and improve patient outcomes.

Advancements in risk stratification and management strategies in primary cardiovascular prevention

Atherosclerotic cardiovascular disease (ASCVD) remains a leading cause of morbidity and mortality worldwide, highlighting the urgent need for advancements in risk assessment and management strategies. Although significant progress has been made recently, identifying and managing apparently healthy individuals at a higher risk of developing atherosclerosis and those with subclinical atherosclerosis still poses significant challenges. Traditional risk assessment tools have limitations in accurately predicting future events and fail to encompass the complexity of the atherosclerosis trajectory. In this review, we describe novel approaches in biomarkers, genetics, advanced imaging techniques, and artificial intelligence that have emerged to address this gap. Moreover, polygenic risk scores and imaging modalities such as coronary artery calcium scoring, and coronary computed tomography angiography offer promising avenues for enhancing primary cardiovascular risk stratification and personalised intervention strategies. On the other hand, interventions aiming against atherosclerosis development or promoting plaque regression have gained attention in primary ASCVD prevention. Therefore, the potential role of drugs like statins, ezetimibe, proprotein convertase subtilisin/kexin type 9 (PCSK9) inhibitors, omega-3 fatty acids, antihypertensive agents, as well as glucose-lowering and anti-inflammatory drugs are also discussed. Since findings regarding the efficacy of these interventions vary, further research is still required to elucidate their mechanisms of action, optimize treatment regimens, and determine their long-term effects on ASCVD outcomes. In conclusion, advancements in strategies addressing atherosclerosis prevention and plaque regression present promising avenues for enhancing primary ASCVD prevention through personalised approaches tailored to individual risk profiles. Nevertheless, ongoing research efforts are imperative to refine these strategies further and maximise their effectiveness in safeguarding cardiovascular health.

Pitfalls in Developing Machine Learning Models for Predicting Cardiovascular Diseases: Challenge and Solutions

In recent years, there has been explosive development in artificial intelligence (AI), which has been widely applied in the health care field. As a typical AI technology, machine learning models have emerged with great potential in predicting cardiovascular diseases by leveraging large amounts of medical data for training and optimization, which are expected to play a crucial role in reducing the incidence and mortality rates of cardiovascular diseases. Although the field has become a research hot spot, there are still many pitfalls that researchers need to pay close attention to. These pitfalls may affect the predictive performance, credibility, reliability, and reproducibility of the studied models, ultimately reducing the value of the research and affecting the prospects for clinical application. Therefore, identifying and avoiding these pitfalls is a crucial task before implementing the research. However, there is currently a lack of a comprehensive summary on this topic. This viewpoint aims to analyze the existing problems in terms of data quality, data set characteristics, model design, and statistical methods, as well as clinical implications, and provide possible solutions to these problems, such as gathering objective data, improving training, repeating measurements, increasing sample size, preventing overfitting using statistical methods, using specific AI algorithms to address targeted issues, standardizing outcomes and evaluation criteria, and enhancing fairness and replicability, with the goal of offering reference and assistance to researchers, algorithm developers, policy makers, and clinical practitioners.

Artificial Intelligence in Cardiovascular Disease Prevention: Is it Ready for Prime Time?

PURPOSE OF REVIEW

This review evaluates how Artificial Intelligence (AI) enhances atherosclerotic cardiovascular disease (ASCVD) risk assessment, allows for opportunistic screening, and improves adherence to guidelines through the analysis of unstructured clinical data and patient-generated data. Additionally, it discusses strategies for integrating AI into clinical practice in preventive cardiology.

RECENT FINDINGS

AI models have shown superior performance in personalized ASCVD risk evaluations compared to traditional risk scores. These models now support automated detection of ASCVD risk markers, including coronary artery calcium (CAC), across various imaging modalities such as dedicated ECG-gated CT scans, chest X-rays, mammograms, coronary angiography, and non-gated chest CT scans. Moreover, large language model (LLM) pipelines are effective in identifying and addressing gaps and disparities in ASCVD preventive care, and can also enhance patient education. AI applications are proving invaluable in preventing and managing ASCVD and are primed for clinical use, provided they are implemented within well-regulated, iterative clinical pathways.

Implementation of a machine learning model in acute coronary syndrome and stroke risk assessment for patients with lower urinary tract symptoms

OBJECTIVE

The global population is aging and the burden of lower urinary tract symptoms (LUTS) is expected to increase. According to the National Health Insurance Research Database, our previous studies have showed LUTS may predispose patients to cardiovascular disease. However, it is difficult to provide a personalized risk assessment in the context of "having acute coronary syndrome (ACS) and stroke." This study aimed to develop an artificial intelligence (AI)-based prediction model for patients with LUTS.

MATERIAL AND METHODS

We retrospectively reviewed the electronic medical records of 1799 patients with LUTS at Chi Mei Medical Center between January 1, 2001 and December, 31, 2018. Features with >10 cases and high correlations with outcomes were imported into six machine learning algorithms. The study outcomes included ACS and stroke. Model performances was evaluated using the area under the receiver operating characteristic curve (AUC). The model with the highest AUC was used to implement the clinical risk prediction application.

RESULTS

Age, systemic blood pressure, diastolic blood pressure, creatinine, glycated hemoglobin, hypertension, diabetes mellitus and hyperlipidemia were the most relevant features that affect the outcomes. Based on the AUC, our optimal model was built using multilayer perception (AUC = 0.803) to predict ACS and stroke events within 3 years.

CONCLUSION

We successfully built an AI-based prediction system that can be used as a prediction model to achieve time-saving, precise, personalized risk evaluation; it can also be used to offer warning, enhance patient adherence, early intervention and better health care outcomes.

Predicting Cardiovascular Disease Risk in Tobacco Users Using Machine Learning Algorithms

Cardiovascular Diseases (CVDs) present a substantial global health burden, with tobacco use as a major risk factor. While extensive research has identified several risk factors for CVDs, there is a gap in predictive models that account for a combination of clinical factors, lifestyle factors, and other determinants in order to predict CVD risk. In addition, existing studies tend to overlook the interactions among risk factors within high-risk populations, such as tobacco users. In this study, we examined phenotype data from over 15,000 tobacco users from the UK Biobank dataset to investigate which additional phenotype factors in the population showed predictive power for CVD. We explored the application of multiple Machine Learning (ML) algorithms, including Decision Trees (DT), Gradient Boosting (GB), Logistic Regression (LR), Random Forest (RF), and Support Vector Classification (SVC) in predicting CVD risk and individual phenotype feature importance. By analyzing the rich phenotype data in the UK Biobank via various algorithms, we were able to understand factors related to risk prediction and offer insights into the interplay of risk factors that contribute to cardiovascular events in this high-risk population.

A machine learning model predicts stroke associated with blood cadmium level

Stroke is the leading cause of death and disability worldwide. Cadmium is a prevalent environmental toxicant that may contribute to cardiovascular disease, including stroke. We aimed to build an effective and interpretable machine learning (ML) model that links blood cadmium to the identification of stroke. Our data exploring the association between blood cadmium and stroke came from the National Health and Nutrition Examination Survey (NHANES, 2013-2014). In total, 2664 participants were eligible for this study. We divided these data into a training set (80%) and a test set (20%). To analyze the relationship between blood cadmium and stroke, a multivariate logistic regression analysis was performed. We constructed and tested five ML algorithms including K-nearest neighbor (KNN), decision tree (DT), logistic regression (LR), multilayer perceptron (MLP), and random forest (RF). The best-performing model was selected to identify stroke in US adults. Finally, the features were interpreted using the Shapley Additive exPlanations (SHAP) tool. In the total population, participants in the second, third, and fourth quartiles had an odds ratio of 1.32 (95% CI 0.55, 3.14), 1.65 (95% CI 0.71, 3.83), and 2.67 (95% CI 1.10, 6.49) for stroke compared with the lowest reference group for blood cadmium, respectively. This blood cadmium-based LR approach demonstrated the greatest performance in identifying stroke (area under the operator curve: 0.800, accuracy: 0.966). Employing interpretable methods, we found blood cadmium to be a notable contributor to the predictive model. We found that blood cadmium was positively correlated with stroke risk and that stroke risk from cadmium exposure could be effectively predicted by using ML modeling.

Causal Associations of Environmental Pollution and Cardiovascular Disease: A Two-Sample Mendelian Randomization Study

Background

There is growing evidence that concentrations of environmental pollutants are previously associated with cardiovascular disease; however, it is unclear whether this association reflects a causal relationship.

Methods

We utilized a two-sample Mendelian randomization (MR) approach to investigate how environmental pollution affects the likelihood of developing cardiovascular disease. We primarily employed the inverse variance weighted (IVW) method. Additionally, to ensure the robustness of our findings, we conducted several sensitivity analyses using alternative methodologies. These included maximum likelihood, MR-Egger regression, weighted median method and weighted model methods.

Results

Inverse variance weighted estimates suggested that an SD increase in PM2.5 exposure increased the risk of heart failure (OR = 1.40, 95% CI 1.02-1.93, p = 0.0386). We found that an SD increase in PM10 exposure increased the risk of hypertension (OR = 1.45, 95% CI 1.02-2.05, p = 0.03598) and atrial fibrillation (OR = 1.41, 95% CI 1.03-1.94, p = 0.03461). Exposure to chemical or other fumes in a workplace was found to increase the risk of hypertension (OR = 3.08, 95% CI 1.40-6.78, p = 0.005218), coronary artery disease (OR = 1.81, 95% CI 1.00-3.26, p = 0.04861), coronary heart disease (OR = 3.15, 95% CI 1.21-8.16, p = 0.0183) and myocardial infarction (OR = 3.03, 95% CI 1.13-8.17, p = 0.02802).

Conclusion

This study reveals the causal relationship between air pollutants and cardiovascular diseases, providing new insights into the protection of cardiovascular diseases.

The China Hypertrophic Cardiomyopathy Project (CHCMP): The Rationale and Design of a Multicenter, Prospective, Registry Cohort Study

Hypertrophic cardiomyopathy (HCM) is associated with adverse outcomes, such as heart failure, arrhythmia, and mortality. Sudden cardiac death (SCD) is a common cause of death in HCM patients, and identification of patients at a high risk of SCD is crucial in clinical practice. The China Hypertrophic Cardiomyopathy Project is a hospital-based, multicenter, prospective, registry cohort study of HCM patients, covering a total of 3000 participants and with a 5-year follow-up plan. A large number of demographic characteristics and clinical data will be fully collected to identify prognostic factors in Chinese HCM patients. Furthermore, the main purpose of this study is to integrate demographic and clinical characteristics to establish new 5-year SCD risk predictive equations for Chinese HCM patients by the use of machine learning technologies. The project has crucial clinical significance for risk stratification and determination of HCM patients with high risk of adverse outcomes. CLINICAL TRIALS REGISTRATION: ChiCTR2300070909.