Wei Ying Tan, Carol Anne Hargreaves, Gavin S Dawe, Wynne Hsu, Mong Li Lee, Ashwati Vipin, Nagaendran Kandiah, Saima Hilal
{"title":"Incremental Value of Multidomain Risk Factors for Dementia Prediction: A Machine Learning Approach.","authors":"Wei Ying Tan, Carol Anne Hargreaves, Gavin S Dawe, Wynne Hsu, Mong Li Lee, Ashwati Vipin, Nagaendran Kandiah, Saima Hilal","doi":"10.1016/j.jagp.2024.07.016","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>The current evidence regarding how different predictor domains contributes to predicting incident dementia remains unclear. This study aims to assess the incremental value of five predictor domains when added to a simple dementia risk prediction model (DRPM) for predicting incident dementia in older adults.</p><p><strong>Design: </strong>Population-based, prospective cohort study.</p><p><strong>Setting: </strong>UK Biobank study.</p><p><strong>Participants: </strong>Individuals aged 60 or older without dementia.</p><p><strong>Measurements: </strong>Fifty-five dementia-related predictors were gathered and categorized into clinical and medical history, questionnaire, cognition, polygenetic risk, and neuroimaging domains. Incident dementia (all-cause) and the subtypes, Alzheimer's disease (AD) and vascular dementia (VaD), were determined through hospital and death registries. Ensemble machine learning (ML) DRPMs were employed for prediction. The incremental values of risk predictors were assessed using the percent change in Area Under the Curve (∆AUC%) and the net reclassification index (NRI).</p><p><strong>Results: </strong>The simple DRPM which included age, body mass index, sex, education, diabetes, hyperlipidaemia, hypertension, depression, smoking, and alcohol consumption yielded an AUC of 0.711 (± 0.008 SD). The five predictor domains exhibited varying levels of incremental value over the basic model when predicting all-cause dementia and the two subtypes. Neuroimaging markers provided the highest incremental value in predicting all-cause dementia (∆AUC% +9.6%) and AD (∆AUC% +16.5%) while clinical and medical history data performed the best at predicting VaD (∆AUC% +12.2%). Combining clinical and medical history, and questionnaire data synergistically enhanced ML DRPM performance.</p><p><strong>Conclusion: </strong>Combining predictors from different domains generally results in better predictive performance. Selecting predictors involves trade-offs, and while neuroimaging markers can significantly enhance predictive accuracy, they may pose challenges in terms of cost or accessibility.</p>","PeriodicalId":55534,"journal":{"name":"American Journal of Geriatric Psychiatry","volume":null,"pages":null},"PeriodicalIF":4.4000,"publicationDate":"2024-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"American Journal of Geriatric Psychiatry","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.jagp.2024.07.016","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GERIATRICS & GERONTOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Objective: The current evidence regarding how different predictor domains contributes to predicting incident dementia remains unclear. This study aims to assess the incremental value of five predictor domains when added to a simple dementia risk prediction model (DRPM) for predicting incident dementia in older adults.
Participants: Individuals aged 60 or older without dementia.
Measurements: Fifty-five dementia-related predictors were gathered and categorized into clinical and medical history, questionnaire, cognition, polygenetic risk, and neuroimaging domains. Incident dementia (all-cause) and the subtypes, Alzheimer's disease (AD) and vascular dementia (VaD), were determined through hospital and death registries. Ensemble machine learning (ML) DRPMs were employed for prediction. The incremental values of risk predictors were assessed using the percent change in Area Under the Curve (∆AUC%) and the net reclassification index (NRI).
Results: The simple DRPM which included age, body mass index, sex, education, diabetes, hyperlipidaemia, hypertension, depression, smoking, and alcohol consumption yielded an AUC of 0.711 (± 0.008 SD). The five predictor domains exhibited varying levels of incremental value over the basic model when predicting all-cause dementia and the two subtypes. Neuroimaging markers provided the highest incremental value in predicting all-cause dementia (∆AUC% +9.6%) and AD (∆AUC% +16.5%) while clinical and medical history data performed the best at predicting VaD (∆AUC% +12.2%). Combining clinical and medical history, and questionnaire data synergistically enhanced ML DRPM performance.
Conclusion: Combining predictors from different domains generally results in better predictive performance. Selecting predictors involves trade-offs, and while neuroimaging markers can significantly enhance predictive accuracy, they may pose challenges in terms of cost or accessibility.
期刊介绍:
The American Journal of Geriatric Psychiatry is the leading source of information in the rapidly evolving field of geriatric psychiatry. This esteemed journal features peer-reviewed articles covering topics such as the diagnosis and classification of psychiatric disorders in older adults, epidemiological and biological correlates of mental health in the elderly, and psychopharmacology and other somatic treatments. Published twelve times a year, the journal serves as an authoritative resource for professionals in the field.