Dataset Information

NetCRS: Network-based comorbidity risk score for prediction of myocardial infarction using biobank-scaled PheWAS data.

ABSTRACT: The polygenic risk score (PRS) can help to identify individuals' genetic susceptibility for various diseases by combining patient genetic profiles and identified single-nucleotide polymorphisms (SNPs) from genome-wide association studies. Although multiple diseases will usually afflict patients at once or in succession, conventional PRSs fail to consider genetic relationships across multiple diseases. Even multi-trait PRSs, which take into account genetic effects for more than one disease at a time, fail to consider a sufficient number of phenotypes to accurately reflect the state of disease comorbidity in a patient, or are biased in terms of the traits that are selected. Thus, we developed novel network-based comorbidity risk scores to quantify associations among multiple phenotypes from phenome-wide association studies (PheWAS). We first constructed a disease-SNP heterogeneous multi-layered network (DS-Net), which consists of a disease network (disease-layer) and SNP network (SNP-layer). The disease-layer describes the population-level interactome from PheWAS data. The SNP-layer was constructed according to linkage disequilibrium. Both layers were attached to transform the information from a population-level interactome to individual-level inferences. Then, graph-based semi-supervised learning was applied to predict possible comorbidity scores on disease-layer for each subject. The SNP-layer serves as receiving individual genotyping data in the scoring process, and the disease-layer serves as the propagated output for an individual's multiple disease comorbidity scores. The possible comorbidity scores were combined by logistic regression, and it is denoted as netCRS. The DS-Net was constructed from UK Biobank PheWAS data, and the individual genetic profiles were collected from the Penn Medicine Biobank. As a proof-of-concept study, myocardial infarction (MI) was selected to compare netCRS with the PRS with pruning and thresholding (PRS-PT). The combined model (netCRS + PRS-PT + covariates) achieved an AUC improvement of 6.26% compared to the (PRS-PT + covariates) model. In terms of risk stratification, the combined model was able to capture the risk of MI up to approximately eight-fold higher than that of the low-risk group. The netCRS and PRS-PT complement each other in predicting high-risk groups of patients with MI. We expect that using these risk prediction models will allow for the development of prevention strategies and reduction of MI morbidity and mortality.

SUBMITTER: Nam Y

PROVIDER: S-EPMC8682919 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BACKGROUND:Risk prediction after myocardial infarction is often complex in older patients. The Global Registry of Acute Coronary Events (GRACE) model includes clinical parameters and age, but not frailty. We hypothesised that frailty would enhance the prognostic properties of GRACE. METHODS:We performed a prospective observational cohort study in two independent cardiology units: the Royal Infirmary of Edinburgh, UK (primary cohort) and the South Yorkshire Cardiothoracic Centre, Sheffield, UK (external validation). The study sample included 198 patients ?65?years old hospitalised with type 1 myocardial infarction (primary cohort) and 96 patients ?65?years old undergoing cardiac catheterisation for myocardial infarction (external validation). Frailty was assessed using the Clinical Frailty Scale (CFS). The GRACE 2.0 estimated risk of 12-month mortality, Charlson comorbidity index and Karnofsky disability scale were also determined for each patient. RESULTS:Forty (20%) patients were frail (CFS ?5). These individuals had greater comorbidity, functional impairment and a higher risk of death at 12?months (49% vs. 9% in non-frail patients, p?<?0.001). The hazard of 12-month all-cause mortality nearly doubled per point increase in CFS after adjustment for age, sex and comorbidity (Hazard Ratio [HR] 1.90, 95% CI 1.47-2.44, p?<?0.001). The CFS had good discrimination for mortality by Receiver Operating Characteristic (ROC) curve analysis (Area Under the Curve [AUC] 0.81, 95% CI 0.72-0.89) and enhanced the GRACE estimate (AUC 0.86 vs. 0.80 without CFS, p?=?0.04). At existing GRACE thresholds, the CFS resulted in a Net Reclassification Improvement (NRI) of 0.44 (95% CI 0.28-0.60, p?<?0.001), largely through reductions in risk estimates amongst non-frail patients. Similar findings were observed in the external validation cohort (NRI 0.46, 95% CI 0.23-0.69, p?<?0.001). CONCLUSIONS:The GRACE score overestimated mortality risk after myocardial infarction in these cohorts of older patients. The CFS is a simple guided frailty tool that may enhance prediction in this setting. These findings merit evaluation in larger cohorts of unselected patients. TRIAL REGISTRATION:Clinicaltrials.gov; NCT02302014 (November 26th 2014, retrospectively registered).

Project description:Personality is a strong determinant for several health-related behaviours and has been linked to the development of cardiovascular diseases. However, the reports of personality's mediating role have been inconsistent with no data available from large population-based cohorts. The study aimed to create proxies for the Big Five personality traits, extraversion, agreeableness, conscientiousness, openness and neuroticism, to examine the longitudinal relationship between personality and myocardial infarction in the UK Biobank. The study sample comprised of 484,205 participants (55% female, 45% male, mean age 56.4 ± 8.1 years) from UK Biobank cohort with a mean follow-up of 7 years. The personality proxies sociability, warmth, diligence, curiosity and nervousness were created using self-reported data on psychological factors, mental health and social support, to match the facets of the Big Five traits. As neuroticism is the only Big Five personality trait available in the UK Biobank, it was included to validate the personality proxies. Myocardial infarction outcome information was collected from hospital records, death registries or was self-reported. Logistic regression and Cox proportional hazard regression were used to estimate odds ratio (OR) and hazard ratios (HR), respectively with 95% confidence intervals (CI) adjusted for demographics (age, sex, socioeconomic status, ethnicity), health-related factors (BMI, diabetes, systolic and diastolic blood pressure) and lifestyle factors (alcohol intake, smoking, and moderate-to-vigorous physical activity). Diligence was found to be significantly associated with lower prevalent myocardial infarction [OR: 0.87; (CI 0.84-0.89)] and lower incident myocardial infarction [HR: 0.88; (CI 0.85-0.92)]. Sociability was also protective against prevalent [OR: 0.89; (CI 0.87-0.92)] and incident [HR: 0.90; (CI 0.87-0.93)] myocardial infarction. Conversely, nervousness inferred a higher risk for both prevalent [OR: 1.10; (CI 1.08-1.12)] and incident [HR: 1.07; (CI 1.04-1.09)] myocardial infarction during follow-up. Sex-stratified analyses revealed that nervousness significantly increases the risk for incident myocardial infarction among women [HR: 1.13; (CI 1.08-1.19)] compared to men [HR: 1.05; (CI 1.02-1.08)]. By using our created proxies, we were able to investigate the impact of personality on the development of myocardial infarction. Persons with higher levels of diligence and sociability mimicking predominantly conscientiousness and extraversion personalities respectively are less likely to experience myocardial infarction, while personalities predominantly characterised by nervousness pose higher risk for developing myocardial infarction. These initial findings invite further validation of the use of the personality proxies in UK Biobank cohort.

Dataset Information

NetCRS: Network-based comorbidity risk score for prediction of myocardial infarction using biobank-scaled PheWAS data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets