Dataset Information

Development of an accessible 10-year Digital CArdioVAscular (DiCAVA) risk assessment: a UK Biobank study.

ABSTRACT:

Aims

Cardiovascular diseases (CVDs) are among the leading causes of death worldwide. Predictive scores providing personalized risk of developing CVD are increasingly used in clinical practice. Most scores, however, utilize a homogenous set of features and require the presence of a physician. The aim was to develop a new risk model (DiCAVA) using statistical and machine learning techniques that could be applied in a remote setting. A secondary goal was to identify new patient-centric variables that could be incorporated into CVD risk assessments.

Methods and results

Across 466 052 participants, Cox proportional hazards (CPH) and DeepSurv models were trained using 608 variables derived from the UK Biobank to investigate the 10-year risk of developing a CVD. Data-driven feature selection reduced the number of features to 47, after which reduced models were trained. Both models were compared to the Framingham score. The reduced CPH model achieved a c-index of 0.7443, whereas DeepSurv achieved a c-index of 0.7446. Both CPH and DeepSurv were superior in determining the CVD risk compared to Framingham score. Minimal difference was observed when cholesterol and blood pressure were excluded from the models (CPH: 0.741, DeepSurv: 0.739). The models show very good calibration and discrimination on the test data.

Conclusion

We developed a cardiovascular risk model that has very good predictive capacity and encompasses new variables. The score could be incorporated into clinical practice and utilized in a remote setting, without the need of including cholesterol. Future studies will focus on external validation across heterogeneous samples.

SUBMITTER: Dolezalova N

PROVIDER: S-EPMC9707906 | biostudies-literature | 2021 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development of an accessible 10-year Digital CArdioVAscular (DiCAVA) risk assessment: a UK Biobank study.

Dolezalova Nikola N Reed Angus B AB Despotovic Aleksa A Obika Bernard Dillon BD Morelli Davide D Aral Mert M Plans David D

European heart journal. Digital health 20210626 3

<h4>Aims</h4>Cardiovascular diseases (CVDs) are among the leading causes of death worldwide. Predictive scores providing personalized risk of developing CVD are increasingly used in clinical practice. Most scores, however, utilize a homogenous set of features and require the presence of a physician. The aim was to develop a new risk model (DiCAVA) using statistical and machine learning techniques that could be applied in a remote setting. A secondary goal was to identify new patient-centric vari ...[more]

PMID: 36713604

Similar Datasets

Project description:This study was designed to develop a risk assessment chart for the clinical management and prevention of the risk of cardiovascular disease (CVD) in Iranian population, which is vital for developing national prevention programs. The Isfahan Cohort Study (ICS) is a population-based prospective study of 6504 Iranian adults ≥35 years old, followed-up for ten years, from 2001 to 2010. Behavioral and cardiometabolic risk factors were examined every five years, while biennial follow-ups for the occurrence of the events was performed by phone calls or by verbal autopsy. Among these participants, 5432 (2784 women, 51.3%) were CVD free at baseline examination and had at least one follow-up. Cox proportional hazard regression was used to predict the risk of ischemic CVD events, including sudden cardiac death due to unstable angina, myocardial infarction, and stroke. The model fit statistics such as area under the receiver-operating characteristic (AUROC), calibration chi-square and the overall bias were used to assess the model performance. We also tested the Framingham model for comparison. Seven hundred and five CVD events occurred during 49452.8 person-years of follow-up. The event probabilities were calculated and presented color-coded on each gender-specific PARS chart. The AUROC and Harrell's C indices were 0.74 (95% CI, 0.72-0.76) and 0.73, respectively. In the calibration, the Nam-D'Agostino χ2 was 10.82 (p = 0.29). The overall bias of the proposed model was 95.60%. PARS model was also internally validated using cross-validation. The Android app and the Web-based risk assessment tool were also developed as to have an impact on public health. In comparison, the refitted and recalibrated Framingham models, estimated the CVD incidence with the overall bias of 149.60% and 128.23% for men, and 222.70% and 176.07% for women, respectively. In conclusion, the PARS risk assessment chart is a simple, accurate, and well-calibrated tool for predicting a 10-year risk of CVD occurrence in Iranian population and can be used in an attempt to develop national guidelines for the CVD management.

Project description:BackgroundCardiovascular preventive strategies are guided by risk scores with unknown validity in cancer cohorts.ObjectivesThis study aimed to evaluate the predictive performance of 7 established cardiovascular risk scores in cancer survivors from the UK Biobank.MethodsThe predictive performance of QRISK3, Systematic Coronary Risk Evaluation 2 (SCORE2)/Systematic Coronary Risk Evaluation for Older Persons (SCORE-OP), Framingham Risk Score, Pooled Cohort equations to Prevent Heart Failure (PCP-HF), CHARGE-AF, QStroke, and CHA2DS2-VASc was calculated in participants with and without a history of cancer. Participants were propensity matched on age, sex, deprivation, health behaviors, family history, and metabolic conditions. Analyses were stratified into any cancer, breast, lung, prostate, brain/central nervous system, hematologic malignancies, Hodgkin lymphoma, and non-Hodgkin lymphoma. Incident cardiovascular events were tracked through health record linkage over 10 years of follow-up. The area under the receiver operating curve, balanced accuracy, and sensitivity were reported.ResultsThe analysis included 31,534 cancer survivors and 126,136 covariate-matched controls. Risk score distributions were near identical in cases and controls. Participants with any cancer had a significantly higher incidence of all cardiovascular outcomes than matched controls. Performance metrics were significantly worse for all risk scores in cancer cases than in matched controls. The most notable differences were among participants with a history of hematologic malignancies who had significantly higher outcome rates and poorer risk score performance than their matched controls. The performance of risk scores for predicting stroke in participants with brain/central nervous system cancer was very poor, with predictive accuracy more than 30% lower than noncancer controls.ConclusionsExisting cardiovascular risk scores have significantly worse predictive accuracy in cancer survivors compared with noncancer comparators, leading to an underestimation of risk in this cohort.

Project description:BackgroundEmerging evidence supports a link between circadian disruption as measured by higher night-to-night variation in sleep duration and increased risk of cardiovascular disease (CVD). It remains unclear whether this association varies by CVD types or may be modified by average sleep duration and genetic risk for CVD.MethodsOur prospective analysis included 86,219 UK Biobank participants who were free from CVD when completing 7 days of accelerometer measurement in 2013-2016. Sleep irregularity was evaluated by the standard deviation (SD) of accelerometer-measured sleep duration over 7 days. Incident major CVD events, defined as fatal or nonfatal myocardial infarction (MI) and stroke, were identified through linkage to Hospital Episode Statistics data until May 31, 2022. Multivariable-adjusted Cox proportional hazard models were used to estimate hazard ratios (HRs) and 95% CIs for associations of sleep duration SD with risk for major CVD events overall and for MI and stroke separately.ResultsWe documented 2,310 incident cases of major CVD events (MI: 1,183, stroke: 1,175) over 636,258 person-years of follow-up. After adjusting for sociodemographic factors and family history of CVD, the HR (95% CI) associated with a 1-hour increase in sleep duration SD was 1.19 (1.10, 1.27) for CVD (p-trend<0.0001), 1.23 (1.11, 1.35) for MI (p-trend<0.0001), and 1.17 (1.05, 1.29) for stroke (p-trend=0.003). Additional adjustment for lifestyle factors, co-morbidities and sleep-related factors modestly attenuated these associations. Higher sleep irregularity was associated with higher CVD risk irrespective of genetic risk (p-interaction=0.43), but this association was stronger among individuals with longer average sleep duration >8 hours (p-interaction=0.006).ConclusionsHigher night-to-night variation in accelerometer-measured sleep duration was associated with consistently higher risks for major CVD events. The association did not seem to be modified by genetic risk for CVD and was more pronounced in long sleepers.

Project description:In the large UK Biobank population-based cohort, we found that amongst men, but not women, prior fragility fracture was associated with increased risk of admission with ischaemic heart disease.IntroductionWe aimed to investigate the relationship between prior fracture and risk of incident ischaemic cardiovascular events in a UK population-based cohort.MethodsUK Biobank is a large prospective cohort comprising 502,637 men and women aged 40-69 years, with detailed baseline assessment. History of fracture was self-reported, and details of hospital admissions for ischaemic heart disease (IHD) (ICD-10:I20-I25) were obtained through linkage to UK Hospital Episode Statistics. Cox proportional hazards models were used to investigate the prospective relationships between prior fracture and hospital admission for men and women, controlling for age, BMI, smoking, alcohol, educational level, physical activity, systolic blood pressure, calcium and vitamin D use, ankle spacing-width, heel BUA and HRT use (women).ResultsAmongst men, a fragility fracture (hip, spine, wrist or arm fracture resulting from a simple fall) within the previous 5 years was associated with a 35% increased risk of IHD admission (fully adjusted HR 1.35; 95%CI 1.00, 1.82; p = 0.047), with the relationship predominantly driven by wrist fractures. Associations with hospitalisation for angina in men were similar in age-adjusted models [HR1.54; 95%CI: 1.03, 2.30), p = 0.037], but did not remain statistical significant after full adjustment [HR 1.64; 95%CI: 0.88, 3.07); p = 0.121]. HRs for admission with angina were lower in women, and neither age- nor fully adjusted relationships attained statistical significance.ConclusionsPrior fragility fracture is an independent risk factor for incident ischaemic cardiovascular events in men. Further work may clarify whether this association is causal or represents shared risk factors, but these findings are likely to be of value in risk assessment of both osteoporosis and cardiovascular disease.

Project description:Cardiovascular magnetic resonance (CMR) radiomics is a novel technique for advanced cardiac image phenotyping by analyzing multiple quantifiers of shape and tissue texture. In this paper, we assess, in the largest sample published to date, the performance of CMR radiomics models for identifying changes in cardiac structure and tissue texture due to cardiovascular risk factors. We evaluated five risk factor groups from the first 5,065 UK Biobank participants: hypertension (n = 1,394), diabetes (n = 243), high cholesterol (n = 779), current smoker (n = 320), and previous smoker (n = 1,394). Each group was randomly matched with an equal number of healthy comparators (without known cardiovascular disease or risk factors). Radiomics analysis was applied to short axis images of the left and right ventricles at end-diastole and end-systole, yielding a total of 684 features per study. Sequential forward feature selection in combination with machine learning (ML) algorithms (support vector machine, random forest, and logistic regression) were used to build radiomics signatures for each specific risk group. We evaluated the degree of separation achieved by the identified radiomics signatures using area under curve (AUC), receiver operating characteristic (ROC), and statistical testing. Logistic regression with L1-regularization was the optimal ML model. Compared to conventional imaging indices, radiomics signatures improved the discrimination of risk factor vs. healthy subgroups as assessed by AUC [diabetes: 0.80 vs. 0.70, hypertension: 0.72 vs. 0.69, high cholesterol: 0.71 vs. 0.65, current smoker: 0.68 vs. 0.65, previous smoker: 0.63 vs. 0.60]. Furthermore, we considered clinical interpretation of risk-specific radiomics signatures. For hypertensive individuals and previous smokers, the surface area to volume ratio was smaller in the risk factor vs. healthy subjects; perhaps reflecting a pattern of global concentric hypertrophy in these conditions. In the diabetes subgroup, the most discriminatory radiomics feature was the median intensity of the myocardium at end-systole, which suggests a global alteration at the myocardial tissue level. This study confirms the feasibility and potential of CMR radiomics for deeper image phenotyping of cardiovascular health and disease. We demonstrate such analysis may have utility beyond conventional CMR metrics for improved detection and understanding of the early effects of cardiovascular risk factors on cardiac structure and tissue.

Dataset Information

Development of an accessible 10-year Digital CArdioVAscular (DiCAVA) risk assessment: a UK Biobank study.

Aims

Methods and results

Conclusion

Publications

Development of an accessible 10-year Digital CArdioVAscular (DiCAVA) risk assessment: a UK Biobank study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets