Using machine learning to predict COVID-19 infection and severity risk among 4,510 aged adults: a UK Biobank cohort study.
Ontology highlight
ABSTRACT: Background
Many risk factors have emerged for novel 2019 coronavirus disease (COVID-19). It is relatively unknown how these factors collectively predict COVID-19 infection risk, as well as risk for a severe infection (i.e., hospitalization).Methods
Among aged adults (69.3 ± 8.6 years) in UK Biobank, COVID-19 data was downloaded for 4,510 participants with 7,539 test cases. We downloaded baseline data from 10-14 years ago, including demographics, biochemistry, body mass, and other factors, as well as antibody titers for 20 common to rare infectious diseases. Permutation-based linear discriminant analysis was used to predict COVID-19 risk and hospitalization risk. Probability and threshold metrics included receiver operating characteristic curves to derive area under the curve (AUC), specificity, sensitivity, and quadratic mean.Results
The "best-fit" model for predicting COVID-19 risk achieved excellent discrimination (AUC=0.969, 95% CI=0.934-1.000). Factors included age, immune markers, lipids, and serology titers to common pathogens like human cytomegalovirus. The hospitalization "best-fit" model was more modest (AUC=0.803, 95% CI=0.663-0.943) and included only serology titers.Conclusions
Accurate risk profiles can be created using standard self-report and biomedical data collected in public health and medical settings. It is also worthwhile to further investigate if prior host immunity predicts current host immunity to COVID-19.
SUBMITTER: Willette AA
PROVIDER: S-EPMC7302228 | biostudies-literature | 2021 Jan
REPOSITORIES: biostudies-literature
Publications
Using machine learning to predict COVID-19 infection and severity risk among 4,510 aged adults: a UK Biobank cohort study.
Willette Auriel A AA Willette Sara A SA Wang Qian Q Pappas Colleen C Klinedinst Brandon S BS Le Scott S Larsen Brittany B Pollpeter Amy A Li Tianqi T Brenner Nicole N Waterboer Tim T
medRxiv : the preprint server for health sciences 20210105
<h4>Background</h4>Many risk factors have emerged for novel 2019 coronavirus disease (COVID-19). It is relatively unknown how these factors collectively predict COVID-19 infection risk, as well as risk for a severe infection (i.e., hospitalization).<h4>Methods</h4>Among aged adults (69.3 ± 8.6 years) in UK Biobank, COVID-19 data was downloaded for 4,510 participants with 7,539 test cases. We downloaded baseline data from 10-14 years ago, including demographics, biochemistry, body mass, and other ...[more]
Similar Datasets
Project description:Many risk factors have emerged for novel 2019 coronavirus disease (COVID-19). It is relatively unknown how these factors collectively predict COVID-19 infection risk, as well as risk for a severe infection (i.e., hospitalization). Among aged adults (69.3 ± 8.6 years) in UK Biobank, COVID-19 data was downloaded for 4510 participants with 7539 test cases. We downloaded baseline data from 10 to 14 years ago, including demographics, biochemistry, body mass, and other factors, as well as antibody titers for 20 common to rare infectious diseases in a subset of 80 participants with 124 test cases. Permutation-based linear discriminant analysis was used to predict COVID-19 risk and hospitalization risk. Probability and threshold metrics included receiver operating characteristic curves to derive area under the curve (AUC), specificity, sensitivity, and quadratic mean. Model predictions using the full cohort were marginal. The "best-fit" model for predicting COVID-19 risk was found in the subset of participants with antibody titers, which achieved excellent discrimination (AUC 0.969, 95% CI 0.934-1.000). Factors included age, immune markers, lipids, and serology titers to common pathogens like human cytomegalovirus. The hospitalization "best-fit" model was more modest (AUC 0.803, 95% CI 0.663-0.943) and included only serology titers, again in the subset group. Accurate risk profiles can be created using standard self-report and biomedical data collected in public health and medical settings. It is also worthwhile to further investigate if prior host immunity predicts current host immunity to COVID-19.
| S-EPMC9092926 | biostudies-literature
Project description:BackgroundSuicidal behaviors, including suicide deaths and attempts, are major public health concerns. However, previous suicide models required a huge amount of input features, resulting in limited applicability in clinical practice.ObjectiveWe aimed to construct applicable models (ie, with limited features) for short- and long-term suicidal behavior prediction. We further validated these models among individuals with different genetic risks of suicide.MethodsBased on the prospective cohort of UK Biobank, we included 223 (0.06%) eligible cases of suicide attempts or deaths, according to hospital inpatient or death register data within 1 year from baseline and randomly selected 4460 (1.18%) controls (1:20) without such records. We similarly identified 833 (0.22%) cases of suicidal behaviors 1 to 6 years from baseline and 16,660 (4.42%) corresponding controls. Based on 143 input features, mainly including sociodemographic, environmental, and psychosocial factors; medical history; and polygenic risk scores (PRS) for suicidality, we applied a bagged balanced light gradient-boosting machine (LightGBM) with stratified 10-fold cross-validation and grid-search to construct the full prediction models for suicide attempts or deaths within 1 year or between 1 and 6 years. The Shapley Additive Explanations (SHAP) approach was used to quantify the importance of input features, and the top 20 features with the highest SHAP values were selected to train the applicable models. The external validity of the established models was assessed among 50,310 individuals who participated in UK Biobank repeated assessments both overall and by the level of PRS for suicidality.ResultsIndividuals with suicidal behaviors were on average 56 years old, with equal sex distribution. The application of these full models in the external validation data set demonstrated good model performance, with the area under the receiver operating characteristic (AUROC) curves of 0.919 and 0.892 within 1 year and between 1 and 6 years, respectively. Importantly, the applicable models with the top 20 most important features showed comparable external-validated performance (AUROC curves of 0.901 and 0.885) as the full models, based on which we found that individuals in the top quintile of predicted risk accounted for 91.7% (n=11) and 80.7% (n=25) of all suicidality cases within 1 year and during 1 to 6 years, respectively. We further obtained comparable prediction accuracy when applying these models to subpopulations with different genetic susceptibilities to suicidality. For example, for the 1-year risk prediction, the AUROC curves were 0.907 and 0.885 for the high (>2nd tertile of PRS) and low (<1st) genetic susceptibilities groups, respectively.ConclusionsWe established applicable machine learning-based models for predicting both the short- and long-term risk of suicidality with high accuracy across populations of varying genetic risk for suicide, highlighting a cost-effective method of identifying individuals with a high risk of suicidality.
| S-EPMC9989910 | biostudies-literature
Project description:BackgroundBetween 2013 and 2015, the UK Biobank collected accelerometer traces from 103,712 volunteers aged between 40 and 69 years using wrist-worn triaxial accelerometers for 1 week. This data set has been used in the past to verify that individuals with chronic diseases exhibit reduced activity levels compared with healthy populations. However, the data set is likely to be noisy, as the devices were allocated to participants without a set of inclusion criteria, and the traces reflect free-living conditions.ObjectiveThis study aims to determine the extent to which accelerometer traces can be used to distinguish individuals with type 2 diabetes (T2D) from normoglycemic controls and to quantify their limitations.MethodsMachine learning classifiers were trained using different feature sets to segregate individuals with T2D from normoglycemic individuals. Multiple criteria, based on a combination of self-assessment UK Biobank variables and primary care health records linked to UK Biobank participants, were used to identify 3103 individuals with T2D in this population. The remaining nondiabetic 19,852 participants were further scored on their physical activity impairment severity based on other conditions found in their primary care data, and those deemed likely physically impaired at the time were excluded. Physical activity features were first extracted from the raw accelerometer traces data set for each participant using an algorithm that extends the previously developed Biobank Accelerometry Analysis toolkit from Oxford University. These features were complemented by a selected collection of sociodemographic and lifestyle features available from UK Biobank.ResultsWe tested 3 types of classifiers, with an area under the receiver operating characteristic curve (AUC) close to 0.86 (95% CI 0.85-0.87) for all 3 classifiers and F1 scores in the range of 0.80-0.82 for T2D-positive individuals and 0.73-0.74 for T2D-negative controls. Results obtained using nonphysically impaired controls were compared with highly physically impaired controls to test the hypothesis that nondiabetic conditions reduce classifier performance. Models built using a training set that included highly impaired controls with other conditions had worse performance (AUC 0.75-0.77; 95% CI 0.74-0.78; F1 scores in the range of 0.76-0.77 for T2D positives and 0.63-0.65 for controls).ConclusionsGranular measures of free-living physical activity can be used to successfully train machine learning models that are able to discriminate between individuals with T2D and normoglycemic controls, although with limitations because of the intrinsic noise in the data sets. From a broader clinical perspective, these findings motivate further research into the use of physical activity traces as a means of screening individuals at risk of diabetes and for early detection, in conjunction with routinely used risk scores, provided that appropriate quality control is enforced on the data collection protocol.
| S-EPMC8080299 | biostudies-literature
Project description:IntroductionParkinson's disease (PD) is the most common movement disorder, and its prevalence is increasing rapidly worldwide with an ageing population. The UK Biobank is the world's largest and most comprehensive longitudinal study of ageing community volunteers. The cause of the common form of PD is multifactorial, but the degree of causal heterogeneity among patients or the relative importance of one risk factor over another is unclear. This is a major impediment to the discovery of disease-modifying therapies.MethodsWe used an integrated machine learning algorithm (IDEARS) to explore the relative effects of 1,753 measured non-genetic variables in 334,062 eligible UK Biobank participants, including 2,719 who had developed PD since their recruitment into the study.ResultsMale gender was the highest-ranked risk factor, followed by elevated serum insulin-like growth factor 1 (IGF-1), lymphocyte count, and neutrophil/lymphocyte ratio. A group of factors aligned with the symptoms of frailty also ranked highly. IGF-1 and neutrophil/lymphocyte ratio were also elevated in both sexes before PD diagnosis and at the point of diagnosis.DiscussionThe use of machine learning with the UK Biobank provides the best opportunity to explore the multidimensional nature of PD. Our results suggest that novel risk biomarkers, including elevated IGF-1 and NLR, may play a role in, or are indicative of PD pathomechanisms. In particular, our results are consistent with PD being a central manifestation of a systemic inflammatory disease. These biomarkers may be used clinically to predict future PD risk, improve early diagnosis and provide new therapeutic avenues.
| S-EPMC10168570 | biostudies-literature
Project description:BackgroundMachine learning (ML) models can be used to predict future frailty in the community setting. However, outcome variables for epidemiologic data sets such as frailty usually have an imbalance between categories, that is, there are far fewer individuals classified as frail than as nonfrail, adversely affecting the performance of ML models when predicting the syndrome.MethodsA retrospective cohort study with participants (50 years or older) from the English Longitudinal Study of Ageing who were nonfrail at baseline (2008-2009) and reassessed for the frailty phenotype at 4-year follow-up (2012-2013). Social, clinical, and psychosocial baseline predictors were selected to predict frailty at follow-up in ML models (Logistic Regression, Random Forest [RF], Support Vector Machine, Neural Network, K-nearest neighbor, and Naive Bayes classifier).ResultsOf all the 4 378 nonfrail participants at baseline, 347 became frail at follow-up. The proposed combined oversampling and undersampling method to adjust imbalanced data improved the performance of the models, and RF had the best performance, with areas under the receiver-operating characteristic curve and the precision-recall curve of 0.92 and 0.97, respectively, specificity of 0.83, sensitivity of 0.88, and balanced accuracy of 85.5% for balanced data. Age, chair-rise test, household wealth, balance problems, and self-rated health were the most important frailty predictors in most of the models trained with balanced data.ConclusionsML proved useful in identifying individuals who became frail over time, and this result was made possible by balancing the data set. This study highlighted factors that may be useful in the early detection of frailty.
| S-EPMC10613015 | biostudies-literature
Project description:BackgroundA possible role of vitamin D in the pathophysiology of depression is currently speculative, with more rigorous research needed to assess this association in large adult populations. The current study assesses prospective associations between vitamin D status and depression in middle-aged adults enrolled in the UK Biobank.MethodsWe assessed prospective associations between vitamin D status at the baseline assessment (2006-2010) and depression measured at the follow-up assessment (2016) in 139 128 adults registered with the UK Biobank.ResultsAmongst participants with no depression at baseline (n = 127 244), logistic regression revealed that those with vitamin D insufficiency [adjusted odds ratio (aOR) = 1.14, 95% confidence interval (CI) = 1.07-1.22] and those with vitamin D deficiency (aOR = 1.24, 95% CI 1.13-1.36) were more likely to develop new-onset depression at follow-up compared with those with optimal vitamin D levels after adjustment for a wide range of relevant covariates. Similar prospective associations were reported for those with depression at baseline (n = 11 884) (insufficiency: aOR = 1.11, 95% CI 1.00-1.23; deficiency: aOR = 1.30, 95% CI 1.13-1.50).ConclusionsThe prospective associations found between vitamin D status and depression suggest that both vitamin D deficiency and insufficiency might be risk factors for the development of new-onset depression in middle-aged adults. Moreover, vitamin D deficiency (and to a lesser extent insufficiency) might be a predictor of sustained depressive symptoms in those who are already depressed. Vitamin D deficiency and insufficiency is very common, meaning that these findings have significant implications for public health.
| S-EPMC9340850 | biostudies-literature
Project description:BackgroundThe atherosclerotic cardiovascular disease (ASCVD) is associated with dementia. However, the risk factors of dementia in patients with ASCVD remain unclear, necessitating the development of accurate prediction models.ObjectiveThe aim of the study is to develop a machine learning model for use in patients with ASCVD to predict dementia risk using available clinical and sociodemographic data.MethodsThis prognostic study included patients with ASCVD between 2006 and 2010, with registration of follow-up data ending on April 2023 based on the UK Biobank. We implemented a data-driven strategy, identifying predictors from 316 variables and developing a machine learning model to predict the risk of incident dementia, Alzheimer disease, and vascular dementia within 5, 10, and longer-term follow-up in patients with ASCVD.ResultsA total of 29,561 patients with ASCVD were included, and 1334 (4.51%) developed dementia during a median follow-up time of 10.3 (IQR 7.6-12.4) years. The best prediction model (UK Biobank ASCVD risk prediction model) was light gradient boosting machine, comprising 10 predictors including age, time to complete pairs matching tasks, mean time to correctly identify matches, mean sphered cell volume, glucose levels, forced expiratory volume in 1 second z score, C-reactive protein, forced vital capacity, time engaging in activities, and age first had sexual intercourse. This model achieved the following performance metrics for all incident dementia: area under the receiver operating characteristic curve: mean 0.866 (SD 0.027), accuracy: mean 0.883 (SD 0.010), sensitivity: mean 0.637 (SD 0.084), specificity: mean 0.914 (SD 0.012), precision: mean 0.479 (SD 0.031), and F1-score: mean 0.546 (SD 0.043). Meanwhile, this model was well-calibrated (Kolmogorov-Smirnov test showed goodness-of-fit P value>.99) and maintained robust performance across different temporal cohorts. Besides, the model had a beneficial potential in clinical practice with a decision curve analysis.ConclusionsThe findings of this study suggest that predictive modeling could inform patients and clinicians about ASCVD at risk for dementia.
| S-EPMC11904384 | biostudies-literature
Project description:Background Nonalcoholic fatty liver disease (NAFLD) is the most prevalent liver disease worldwide. Cardiovascular disease (CVD) is the leading cause of mortality among patients with NAFLD. The aim of our study was to develop a machine learning algorithm integrating clinical, lifestyle, and genetic risk factors to identify CVD in patients with NAFLD. Methods and Results We created a cohort of patients with NAFLD from the UK Biobank, diagnosed according to proton density fat fraction from magnetic resonance imaging data sets. A total of 400 patients with NAFLD with subclinical atherosclerosis or clinical CVD, defined by disease codes, constituted cases and 446 NAFLD cases with no CVD constituted controls. We evaluated 7 different supervised machine learning approaches on clinical, lifestyle, and genetic variables for identifying CVD in patients with NAFLD. The most significant clinical and lifestyle variables observed by the predictive modeling were age (59 years [54.00-63.00 years]), hypertension (145 mm Hg [134.0-156.0 mm Hg] and 85 mm Hg [79.00-93.00 mm Hg]), waist circumference (98 cm [95.00-105.00 cm]), and sedentary lifestyle, defined as time spent watching TV >4 h/d. In the genetic data, single-nucleotide polymorphisms in IL16 and ANKLE1 gene were most significant. Our proposed ensemble-based integrative machine learning model achieved an area under the curve of 0.849 using the random forest modeling for CVD prediction. Conclusions We propose a machine learning algorithm that identifies CVD in patients with NAFLD through integration of significant clinical, lifestyle, and genetic risk factors. These patients with NAFLD at higher risk of CVD should be flagged for screening and aggressive treatment of their cardiometabolic risk factors to prevent cardiovascular morbidity and mortality.
| S-EPMC9075189 | biostudies-literature
Project description:ObjectiveAtrial 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.MethodsTo 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.FindingsThe 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.ImplicationsThe 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.
| S-EPMC10987914 | biostudies-literature
Project description:BackgroundIt is now well recognised that the risk of severe COVID-19 increases with some long-term conditions (LTCs). However, prior research primarily focuses on individual LTCs and there is a lack of data on the influence of multimorbidity (≥2 LTCs) on the risk of COVID-19. Given the high prevalence of multimorbidity, more detailed understanding of the associations with multimorbidity and COVID-19 would improve risk stratification and help protect those most vulnerable to severe COVID-19. Here we examine the relationships between multimorbidity, polypharmacy (a proxy of multimorbidity), and COVID-19; and how these differ by sociodemographic, lifestyle, and physiological prognostic factors.Methods and findingsWe studied data from UK Biobank (428,199 participants; aged 37-73; recruited 2006-2010) on self-reported LTCs, medications, sociodemographic, lifestyle, and physiological measures which were linked to COVID-19 test data. Poisson regression models examined risk of COVID-19 by multimorbidity/polypharmacy and effect modification by COVID-19 prognostic factors (age/sex/ethnicity/socioeconomic status/smoking/physical activity/BMI/systolic blood pressure/renal function). 4,498 (1.05%) participants were tested; 1,324 (0.31%) tested positive for COVID-19. Compared with no LTCs, relative risk (RR) of COVID-19 in those with 1 LTC was no higher (RR 1.12 (CI 0.96-1.30)), whereas those with ≥2 LTCs had 48% higher risk; RR 1.48 (1.28-1.71). Compared with no cardiometabolic LTCs, having 1 and ≥2 cardiometabolic LTCs had a higher risk of COVID-19; RR 1.28 (1.12-1.46) and 1.77 (1.46-2.15), respectively. Polypharmacy was associated with a dose response higher risk of COVID-19. All prognostic factors were associated with a higher risk of COVID-19 infection in multimorbidity; being non-white, most socioeconomically deprived, BMI ≥40 kg/m2, and reduced renal function were associated with the highest risk of COVID-19 infection: RR 2.81 (2.09-3.78); 2.79 (2.00-3.90); 2.66 (1.88-3.76); 2.13 (1.46-3.12), respectively. No multiplicative interaction between multimorbidity and prognostic factors was identified. Important limitations include the low proportion of UK Biobank participants with COVID-19 test data (1.05%) and UK Biobank participants being more affluent, healthier and less ethnically diverse than the general population.ConclusionsIncreasing multimorbidity, especially cardiometabolic multimorbidity, and polypharmacy are associated with a higher risk of developing COVID-19. Those with multimorbidity and additional factors, such as non-white ethnicity, are at heightened risk of COVID-19.
| S-EPMC7440632 | biostudies-literature