Development and external validation of a novel dementia risk prediction score in the UK Biobank cohort

INTRODUCTION: Current prognostic models of dementia have had limited success in consistently identifying at-risk individuals. We aimed to develop and validate a novel dementia risk score (DRS) using the UK Biobank cohort.METHODS: After randomly dividing the sample into a training (n=166,487, 80%) and test set (n=41,621, 20%), logistic LASSO regression and standard logistic regression were used to develop the UKB-DRS.RESULTS: The score consisted of age, sex, education, apolipoprotein E4 genotype, a history of diabetes, stroke, and depression, and a family history of dementia. The UKB-DRS had good-to-strong discrimination accuracy in the UKB hold-out sample (AUC [95%CI]=0.79 [0.77, 0.82]) and in an external dataset (Whitehall II cohort, AUC [95%CI]=0.83 [0.79,0.87]). The UKB-DRS also significantly outperformed four published risk scores (i.e., Australian National University Alzheimer’s Disease Risk Index (ANU-ADRI), Cardiovascular Risk Factors, Aging, and Dementia score (CAIDE), Dementia Risk Score (DRS), and the Framingham Cardiovascular Risk Score (FRS) across both test sets.CONCLUSION: The UKB-DRS represents a novel easy-to-use tool that could be used for routine care or targeted selection of at-risk individuals into clinical trials.

Download Full-text

Comparison of prognostic models to predict the occurrence of colorectal cancer in asymptomatic individuals: a systematic literature review and external validation in the EPIC and UK Biobank prospective cohort studies

Gut ◽

10.1136/gutjnl-2017-315730 ◽

2018 ◽

Vol 68 (4) ◽

pp. 672-683 ◽

Cited By ~ 6

Author(s):

Todd Smith ◽

David C Muller ◽

Karel G M Moons ◽

Amanda J Cross ◽

Mattias Johansson ◽

...

Keyword(s):

Colorectal Cancer ◽

Systematic Review ◽

Prediction Models ◽

Large Population ◽

External Validation ◽

Population Based ◽

Prognostic Models ◽

Uk Biobank ◽

Asymptomatic Individuals ◽

The Uk

ObjectiveTo systematically identify and validate published colorectal cancer risk prediction models that do not require invasive testing in two large population-based prospective cohorts.DesignModels were identified through an update of a published systematic review and validated in the European Prospective Investigation into Cancer and Nutrition (EPIC) and the UK Biobank. The performance of the models to predict the occurrence of colorectal cancer within 5 or 10 years after study enrolment was assessed by discrimination (C-statistic) and calibration (plots of observed vs predicted probability).ResultsThe systematic review and its update identified 16 models from 8 publications (8 colorectal, 5 colon and 3 rectal). The number of participants included in each model validation ranged from 41 587 to 396 515, and the number of cases ranged from 115 to 1781. Eligible and ineligible participants across the models were largely comparable. Calibration of the models, where assessable, was very good and further improved by recalibration. The C-statistics of the models were largely similar between validation cohorts with the highest values achieved being 0.70 (95% CI 0.68 to 0.72) in the UK Biobank and 0.71 (95% CI 0.67 to 0.74) in EPIC.ConclusionSeveral of these non-invasive models exhibited good calibration and discrimination within both external validation populations and are therefore potentially suitable candidates for the facilitation of risk stratification in population-based colorectal screening programmes. Future work should both evaluate this potential, through modelling and impact studies, and ascertain if further enhancement in their performance can be obtained.

Download Full-text

Biomarker validation of a dementia risk prediction score

Nature Reviews Neurology ◽

10.1038/s41582-020-0316-8 ◽

2020 ◽

Vol 16 (3) ◽

pp. 135-136 ◽

Cited By ~ 1

Author(s):

Ruth Stephen ◽

Hilkka Soininen

Keyword(s):

Risk Prediction ◽

Prediction Score ◽

Dementia Risk ◽

Biomarker Validation

Download Full-text

Walking pace improves all-cause and cardiovascular mortality risk prediction: A UK Biobank prognostic study

European Journal of Preventive Cardiology ◽

10.1177/2047487319887281 ◽

2019 ◽

Vol 27 (10) ◽

pp. 1036-1044 ◽

Cited By ~ 1

Author(s):

Stavroula Argyridou ◽

Francesco Zaccardi ◽

Melanie J Davies ◽

Kamlesh Khunti ◽

Thomas Yates

Keyword(s):

Risk Factors ◽

Risk Prediction ◽

Cardiovascular Mortality ◽

Smoking Status ◽

Density Lipoprotein ◽

Uk Biobank ◽

All Cause Mortality ◽

Lifestyle Measures ◽

European Society Of Cardiology ◽

The Uk

Aims The purpose of this study was to quantify and rank the prognostic relevance of dietary, physical activity and physical function factors in predicting all-cause and cardiovascular mortality in comparison with the established risk factors included in the European Society of Cardiology Systematic COronary Risk Evaluation (SCORE). Methods We examined the predictive discrimination of lifestyle measures using C-index and R2 in sex-stratified analyses adjusted for: model 1, age; model 2, SCORE variables (age, smoking status, systolic blood pressure, total and high-density lipoprotein cholesterol). Results The sample comprised 298,829 adults (median age, 57 years; 53.5% women) from the UK Biobank free from cancer and cardiovascular disease at baseline. Over a median follow-up of 6.9 years, there were 2174 and 3522 all–cause and 286 and 796 cardiovascular deaths in women and men, respectively. When added to model 1, self-reported walking pace improved C-index in women and men by 0.013 (99% CI: 0.007–0.020) and 0.022 (0.017–0.028) respectively for all-cause mortality; and by 0.023 (0.005–0.042) and 0.034 (0.020–0.048) respectively for cardiovascular mortality. When added to model 2, corresponding values for women and men were: 0.008 (0.003–0.012) and 0.013 (0.009–0.017) for all-cause mortality; and 0.012 (–0.001–0.025) and 0.024 (0.013–0.035) for cardiovascular mortality. Other lifestyle factors did not consistently improve discrimination across models and outcomes. The pattern of results for R2 mirrored those for C-index. Conclusion A simple self-reported measure of walking pace was the only lifestyle variable found to improve risk prediction for all-cause and cardiovascular mortality when added to established risk factors.

Download Full-text

Genomic Risk Prediction of Recurrent Cardiovascular Diseases in the UK Biobank

SSRN Electronic Journal ◽

10.2139/ssrn.3942125 ◽

2021 ◽

Author(s):

Yixuan Ye ◽

Jiaqi Hu ◽

Fuyuan Pang ◽

Can Cui ◽

Hongyu Zhao

Keyword(s):

Cardiovascular Diseases ◽

Risk Prediction ◽

Uk Biobank ◽

The Uk ◽

Genomic Risk

Download Full-text

Development of breast cancer risk prediction models using the UK biobank dataset

Epidemiology Open Access ◽

10.4172/2161-1165-c1-020 ◽

2018 ◽

Vol 08 ◽

Author(s):

Kawthar Al-ajmi

Keyword(s):

Breast Cancer ◽

Breast Cancer Risk ◽

Cancer Risk ◽

Risk Prediction ◽

Prediction Models ◽

Uk Biobank ◽

Risk Prediction Models ◽

The Uk

Download Full-text

Correction: External validation of risk prediction models for incident colorectal cancer using UK Biobank

British Journal of Cancer ◽

10.1038/s41416-020-0767-0 ◽

2020 ◽

Vol 122 (10) ◽

pp. 1572-1575

Author(s):

J. A. Usher-Smith ◽

A. Harshfield ◽

C. L. Saunders ◽

S. J. Sharp ◽

J. Emery ◽

...

Keyword(s):

Colorectal Cancer ◽

Risk Prediction ◽

Prediction Models ◽

External Validation ◽

Uk Biobank ◽

Risk Prediction Models

Download Full-text

Sugary beverage intake and genetic risk in relation to brain structure and incident dementia: evidence from the UK Biobank

10.21203/rs.3.rs-882320/v2 ◽

2021 ◽

Author(s):

Hui Chen ◽

Jie Chen ◽

Yaying Cao ◽

Yuhao Sun ◽

Liyan Huang ◽

...

Keyword(s):

Brain Structure ◽

Genetic Risk ◽

Medical Records ◽

Uk Biobank ◽

Sweetened Beverages ◽

Dementia Risk ◽

Incident Dementia ◽

Genetic Risks ◽

The Uk ◽

Artificially Sweetened Beverages

Abstract IntroductionThis study investigated the relation of sugary beverage (SB) intake to brain structure and dementia risk.MethodsAmong 187,994 UK Biobank participants, intake of SBs (one unit=250 mL) and specific subtypes was assessed using repeated 24-hr dietary recalls. Multivariable-adjusted hazard rations (HR) was estimated for incident dementia identified through medical records and death registries.ResultsDuring 1,790,996 person-years, 1,351 dementia cases were identified. Higher intake (>2 units/d v. none) of sugar-sweetened beverages (SSB) (HR=1.47, 95%CI: 1.13~1.92) and artificially-sweetened beverages (ASB) (HR=1.41, 1.00~1.99) was associated with an elevated dementia risk. Conversely, moderate intake of natural sweet juices (NSJ) (>0 and <=1 unit/d v. none) was related to a decreased risk (HR=0.80, 0.71~0.90). The associations were consistent with related brain structural markers and modified by genetic risks (P-interaction<0.002).DiscussionThese findings underscored that SSB and ASB could be risk factors of dementia, while moderate NSJ intake could potentially reduce dementia risk.

Download Full-text