Prediction of atrial fibrillation and stroke using machine learning models in UK Biobank.

Objective: Atrial fibrillation (AF) is the most common cardiac arrythmia, and it is associated with increased risk for ischemic stroke, which is underestimated, as AF can be asymptomatic. The aim of this study was to develop optimal ML models for prediction of AF in the population, and secondly for ischemic stroke in AF patients. Methods: To develop ML models for prediction of 1) AF in the general population and 2) ischemic stroke in patients with AF we constructed XGBoost, LightGBM, Random Forest, Deep Neural Network, Support Vector Machine and Lasso penalised logistic regression models using UK-Biobank's extensive real-world clinical data, questionnaires, as well as biochemical and genetic data, and their predictive performances were compared. Ranking and contribution of the different features was assessed by SHapley Additive exPlanations (SHAP) analysis. The clinical tool CHA2DS2-VASc for prediction of ischemic stroke among AF patients, was used for comparison to the best performing ML model. Findings: The best performing model for AF prediction was LightGBM, with an area-under-the-roc-curve (AUROC) of 0.729 (95% confidence intervals (CI): 0.719, 0.738). The best performing model for ischemic stroke prediction in AF patients was XGBoost with AUROC of 0.631 (95% CI: 0.604, 0.657). The improved AUROC in the XGBoost model compared to CHA2DS2-VASc was statistically significant based on DeLong's test (p-value = 2.20E-06). In addition, the SHAP analysis showed that several peripheral blood biomarkers (e.g. creatinine, glycated haemoglobin, monocytes) were associated with ischemic stroke, which are not considered by CHA2DS2-VASc. Implications: The best performing ML models presented have the potential for clinical use, but further validation in independent studies is required. Our results endorse the incorporation of some routinely measured blood biomarkers for ischemic stroke prediction in AF patients.

Height, Autoimmune Thyroid Disease, and Thyroid Cancer: A Mendelian Randomization Study.

Background: Increased height has been associated with increased risk of hypothyroidism or thyroid cancer in epidemiological studies. However, the potential causal association between height and hypothyroidism or thyroid cancer has not been thoroughly explored. Autoimmune thyroid disease (AITD) mainly presents as hypothyroidism, thus we aim to evaluate the causal relationship between height as exposure and its association with AITD or thyroid cancer. Methods: Mendelian randomization (MR) analyses were performed by using genetic instruments associated with height, which were selected from the largest genome-wide association meta-analysis for height in up to 5.4 million individuals. Summary-level data for AITD and thyroid cancer (including 30,234 and 3001 cases, respectively) were collected from the large number of available genome-wide association studies. Bidirectional MR was performed to test for reverse causal association between AITD and adult height. Results: MR analyses showed that increased genetically predicted height was associated with a 4% increased risk of AITD ([CI 1.02 to 1.07], p-value = 1.99E-03) per 1-standard deviation (SD) increase in genetically predicted height. The bidirectional MR did not show any causal association between AITD and adult height. Additionally, increased genetically predicted height was associated with 15% increased risk of thyroid cancer ([CI 1.07 to 1.23], p-value = 2.32E-04) per 1-SD increase in height. Sensitivity analysis confirmed the main results. Conclusions: This MR study showed that 1-SD increase in genetically predicted height was associated with increased risk of AITD and thyroid cancer. In contrast, there was no evidence of a causal association of genetically predicted AITD with height. These results could further aid in investigation of height-related pathways as a means of gaining new mechanistic insights into AITD and thyroid cancer.

The interplay between inflammatory cytokines and cardiometabolic disease: bi-directional mendelian randomisation study.

Objective: To leverage large scale genetic association data to investigate the interplay between circulating cytokines and cardiometabolic traits, and thus identifying potential therapeutic targets. Design: Bi-directional Mendelian randomisation study. Setting: Genome-wide association studies from three Finnish cohorts (Northern Finland Birth Cohort 1966, Young Finns Study, or FINRISK study), and genetic association summary statistics pooled from observational studies for expression quantitative trait loci and cardiometabolic traits. Participants: Data for 47 circulating cytokines in 13 365 individuals from genome-wide association studies, summary statistic data for up to 21 735 individuals on circulating cytokines, summary statistic gene expression data across 49 tissues in 838 individuals, and summary statistic data for up to 1 320 016 individuals on cardiometabolic traits. Interventions: Relations between circulating cytokines and cardiovascular, anthropometric, lipid, or glycaemic traits (coronary artery disease, stroke, type 2 diabetes mellitus, body mass index, waist circumference, waist to hip ratio, systolic blood pressure, glycated haemoglobin, high density lipoprotein cholesterol, low density lipoprotein cholesterol, total cholesterol, triglycerides, C reactive protein, glucose, fasting insulin, and lifetime smoking). Main outcome methods: Genetic instrumental variables that are biologically plausible for the circulating cytokines were generated. The effects of cardiometabolic risk factors on concentrations of circulating cytokines, circulating cytokines on other circulating cytokines, and circulating cytokines on cardiometabolic outcomes were investigated. Results: Genetic evidence (mendelian randomisation P<0.0011) suggests that higher body mass index, waist circumference, smoking, higher concentrations of lipids, and systolic blood pressure increase circulating concentrations of several inflammatory cytokines and C reactive protein. Evidence for causal relations (mendelian randomisation P<0.0011) were noted between circulating cytokines, including a key role of vascular endothelial growth factor on influencing the concentrations of 10 other cytokines. Both mendelian randomisation (P<0.05) and colocalisation (posterior probability >0.5) suggested that coronary artery disease risk is increased by higher concentrations of circulating tumour necrosis factor related apoptosis-inducing ligand (TRAIL), interleukin-1 receptor antagonist (IL1RA), and macrophage colony-stimulating factor (MCSF). Conclusion: This study offers insight into inflammatory mediators of cardiometabolic risk factors, cytokine signalling cascades, and effects of circulating cytokines on different cardiometabolic outcomes.

A Prospective Diet-Wide Association Study for Risk of Colorectal Cancer in EPIC.

BACKGROUND & AIMS: Evidence regarding the association of dietary exposures with colorectal cancer (CRC) risk is not consistent with a few exceptions. Therefore, we conducted a diet-wide association study (DWAS) in the European Prospective Investigation into Cancer and Nutrition (EPIC) to evaluate the associations between several dietary exposures with CRC risk. METHODS: The association of 92 food and nutrient intakes with CRC risk was assessed in 386,792 participants, 5069 of whom developed incident CRC. Correction for multiple comparisons was performed using the false discovery rate, and emerging associations were examined in the Netherlands Cohort Study (NLCS). Multiplicative gene-nutrient interactions were also tested in EPIC based on known CRC-associated loci. RESULTS: In EPIC, alcohol, liquor/spirits, wine, beer/cider, soft drinks, and pork were positively associated with CRC, whereas milk, cheese, calcium, phosphorus, magnesium, potassium, riboflavin, vitamin B6, beta carotene, fruit, fiber, nonwhite bread, banana, and total protein intakes were inversely associated. Of these 20 associations, 13 were replicated in the NLCS, for which a meta-analysis was performed, namely alcohol (summary hazard ratio [HR] per 1-SD increment in intake: 1.07; 95% confidence interval [CI], 1.04-1.09), liquor/spirits (HR per 1-SD increment in intake, 1.04; 95% CI, 1.02-1.06), wine (HR per 1-SD increment in intake, 1.04; 95% CI, 1.02-1.07), beer/cider (HR per 1-SD increment in intake, 1.06; 95% CI, 1.04-1.08), milk (HR per 1-SD increment in intake, 0.95; 95% CI, 0.93-0.98), cheese (HR per 1-SD increment in intake, 0.96; 95% CI, 0.94-0.99), calcium (HR per 1-SD increment in intake, 0.93; 95% CI, 0.90-0.95), phosphorus (HR per 1-SD increment in intake, 0.92; 95% CI, 0.90-0.95), magnesium (HR per 1-SD increment in intake, 0.95; 95% CI, 0.92-0.98), potassium (HR per 1-SD increment in intake, 0.96; 95% CI, 0.94-0.99), riboflavin (HR per 1-SD increment in intake, 0.94; 95% CI, 0.92-0.97), beta carotene (HR per 1-SD increment in intake, 0.96; 95% CI, 0.93-0.98), and total protein (HR per 1-SD increment in intake, 0.94; 95% CI, 0.92-0.97). None of the gene-nutrient interactions were significant after adjustment for multiple comparisons. CONCLUSIONS: Our findings confirm a positive association for alcohol and an inverse association for dairy products and calcium with CRC risk, and also suggest a lower risk at higher dietary intakes of phosphorus, magnesium, potassium, riboflavin, beta carotene, and total protein.

COVID-19 susceptibility variants associate with blood clots, thrombophlebitis and circulatory diseases.

Epidemiological studies suggest that individuals with comorbid conditions including diabetes, chronic lung, inflammatory and vascular disease, are at higher risk of adverse COVID-19 outcomes. Genome-wide association studies have identified several loci associated with increased susceptibility and severity for COVID-19. However, it is not clear whether these associations are genetically determined or not. We used a Phenome-Wide Association (PheWAS) approach to investigate the role of genetically determined COVID-19 susceptibility on disease related outcomes. PheWAS analyses were performed in order to identify traits and diseases related to COVID-19 susceptibility and severity, evaluated through a predictive COVID-19 risk score. We utilised phenotypic data in up to 400,000 individuals from the UK Biobank, including Hospital Episode Statistics and General Practice data. We identified a spectrum of associations between both genetically determined COVID-19 susceptibility and severity with a number of traits. COVID-19 risk was associated with increased risk for phlebitis and thrombophlebitis (OR = 1.11, p = 5.36e-08). We also identified significant signals between COVID-19 susceptibility with blood clots in the leg (OR = 1.1, p = 1.66e-16) and with increased risk for blood clots in the lung (OR = 1.12, p = 1.45 e-10). Our study identifies significant association of genetically determined COVID-19 with increased blood clot events in leg and lungs. The reported associations between both COVID-19 susceptibility and severity and other diseases adds to the identification and stratification of individuals at increased risk, adverse outcomes and long-term effects.

An umbrella review of the evidence associating diet and cancer risk at 11 anatomical sites.

There is evidence that diet and nutrition are modifiable risk factors for several cancers, but associations may be flawed due to inherent biases. Nutritional epidemiology studies have largely relied on a single assessment of diet using food frequency questionnaires. We conduct an umbrella review of meta-analyses of observational studies to evaluate the strength and validity of the evidence for the association between food/nutrient intake and risk of developing or dying from 11 primary cancers. It is estimated that only few single food/nutrient and cancer associations are supported by strong or highly suggestive meta-analytic evidence, and future similar research is unlikely to change this evidence. Alcohol consumption is positively associated with risk of postmenopausal breast, colorectal, esophageal, head & neck and liver cancer. Consumption of dairy products, milk, calcium and wholegrains are inversely associated with colorectal cancer risk. Coffee consumption is inversely associated with risk of liver cancer and skin basal cell carcinoma.

Thyroid function, sex hormones and sexual function: a Mendelian randomization study.

Hypothyroidism and hyperthyroidism are observationally associated with sex hormone concentrations and sexual dysfunction, but causality is unclear. We investigated whether TSH, fT4, hypo- and hyperthyroidism are causally associated with sex hormones and sexual function. We used publicly available summary statistics from genome-wide association studies on TSH and fT4 and hypo- and hyperthyroidism from the ThyroidOmics Consortium (N ≤ 54,288). Outcomes from UK Biobank (women ≤ 194,174/men ≤ 167,020) and ReproGen (women ≤ 252,514) were sex hormones (sex hormone binding globulin [SHBG], testosterone, estradiol, free androgen index [FAI]) and sexual function (ovulatory function in women: duration of menstrual period, age at menarche and menopause, reproductive lifespan, and erectile dysfunction in men). We performed two-sample Mendelian randomization (MR) analyses on summary level, and unweighted genetic risk score (GRS) analysis on individual level data. One SD increase in TSH was associated with a 1.332 nmol/L lower (95% CI: - 0.717,- 1.946; p = 2 × 10-5) SHBG and a 0.103 nmol/l lower (- 0.051,V0.154; p = 9 × 10-5) testosterone in two-sample MR, supported by the GRS approach. Genetic predisposition to hypothyroidism was associated with decreased and genetic predisposition to hyperthyroidism with increased SHBG and testosterone in both approaches. The GRS for fT4 was associated with increased testosterone and estradiol in women only. The GRS for TSH and hypothyroidism were associated with increased and the GRS for hyperthyroidism with decreased FAI in men only. While genetically predicted thyroid function was associated with sex hormones, we found no association with sexual function.

Sex and sport-related differences in satisfaction among Greek swimmers.

The purpose was to test the applicability of the Scale of Athlete Satisfaction for Greek swimmers and to assess sex and sport-related differences for swimers' mean satisfaction. The sample of 351 Greek swimmers comprised 186 males and 165 females competing in five categories of the National Swimming Championhip in Greece. Their mean age was 16 yr. (SD=2; range 13 to 28 years). A confirmatory factor analysis supported the factorial validity of the scale. Analysis indicated that sex, weekly practice schedule, and sport experience differentiated facets of satisfaction among these swimmers. This scale is reliable and valid for measuring athletes' satisfaction with individual sports.