Damaris Aschwanden1, Stephen Aichele2,3, Paolo Ghisletta2,4,5, Antonio Terracciano1, Matthias Kliegel2,5, Angelina R Sutin1, Justin Brown1, Mathias Allemand6,7. 1. Florida State University, Tallahassee, FL, USA. 2. Faculty of Psychology and Educational Sciences, University of Geneva, Switzerland. 3. Colorado State University, Fort Collins, CO, USA. 4. Swiss Distance University Institute, Switzerland. 5. Swiss National Centre of Competence in Research LIVES - Overcoming Vulnerability: Life Course Perspectives, Universities of Lausanne and of Geneva, Switzerland. 6. University of Zurich, Zurich, Switzerland. 7. University Research Priority Program Dynamics of Healthy Aging, University of Zurich, Switzerland.
Abstract
BACKGROUND: Efforts to identify important risk factors for cognitive impairment and dementia have to date mostly relied on meta-analytic strategies. A comprehensive empirical evaluation of these risk factors within a single study is currently lacking. OBJECTIVE: We used a combined methodology of machine learning and semi-parametric survival analysis to estimate the relative importance of 52 predictors in forecasting cognitive impairment and dementia in a large, population-representative sample of older adults. METHODS: Participants from the Health and Retirement Study (N = 9,979; aged 50-98 years) were followed for up to 10 years (M = 6.85 for cognitive impairment; M = 7.67 for dementia). Using a split-sample methodology, we first estimated the relative importance of predictors using machine learning (random forest survival analysis), and we then used semi-parametric survival analysis (Cox proportional hazards) to estimate effect sizes for the most important variables. RESULTS: African Americans and individuals who scored high on emotional distress were at relatively highest risk for developing cognitive impairment and dementia. Sociodemographic (lower education, Hispanic ethnicity) and health variables (worse subjective health, increasing BMI) were comparatively strong predictors for cognitive impairment. Cardiovascular factors (e.g., smoking, physical inactivity) and polygenic scores (with and without APOEɛ4) appeared less important than expected. Post-hoc sensitivity analyses underscored the robustness of these results. CONCLUSIONS: Higher-order factors (e.g., emotional distress, subjective health), which reflect complex interactions between various aspects of an individual, were more important than narrowly defined factors (e.g., clinical and behavioral indicators) when evaluated concurrently to predict cognitive impairment and dementia.
BACKGROUND: Efforts to identify important risk factors for cognitive impairment and dementia have to date mostly relied on meta-analytic strategies. A comprehensive empirical evaluation of these risk factors within a single study is currently lacking. OBJECTIVE: We used a combined methodology of machine learning and semi-parametric survival analysis to estimate the relative importance of 52 predictors in forecasting cognitive impairment and dementia in a large, population-representative sample of older adults. METHODS:Participants from the Health and Retirement Study (N = 9,979; aged 50-98 years) were followed for up to 10 years (M = 6.85 for cognitive impairment; M = 7.67 for dementia). Using a split-sample methodology, we first estimated the relative importance of predictors using machine learning (random forest survival analysis), and we then used semi-parametric survival analysis (Cox proportional hazards) to estimate effect sizes for the most important variables. RESULTS: African Americans and individuals who scored high on emotional distress were at relatively highest risk for developing cognitive impairment and dementia. Sociodemographic (lower education, Hispanic ethnicity) and health variables (worse subjective health, increasing BMI) were comparatively strong predictors for cognitive impairment. Cardiovascular factors (e.g., smoking, physical inactivity) and polygenic scores (with and without APOEɛ4) appeared less important than expected. Post-hoc sensitivity analyses underscored the robustness of these results. CONCLUSIONS: Higher-order factors (e.g., emotional distress, subjective health), which reflect complex interactions between various aspects of an individual, were more important than narrowly defined factors (e.g., clinical and behavioral indicators) when evaluated concurrently to predict cognitive impairment and dementia.
Authors: Teresa Jenica Filshtein; Brittany N Dugger; Lee-Way Jin; John M Olichney; Sarah T Farias; Luis Carvajal-Carmona; Paul Lott; Dan Mungas; Bruce Reed; Laurel A Beckett; Charles DeCarli Journal: J Alzheimers Dis Date: 2019 Impact factor: 4.472
Authors: Ramon Casanova; Sarah A Gaussoin; Robert Wallace; Laura D Baker; Jiu-Chiuan Chen; JoAnn E Manson; Victor W Henderson; Bonnie C Sachs; Jamie N Justice; Eric A Whitsel; Kathleen M Hayden; Stephen R Rapp Journal: J Alzheimers Dis Date: 2021 Impact factor: 4.472
Authors: Young Chul Youn; Jung-Min Pyun; Nayoung Ryu; Min Jae Baek; Jae-Won Jang; Young Ho Park; Suk-Won Ahn; Hae-Won Shin; Kwang-Yeol Park; Sang Yun Kim Journal: Alzheimers Res Ther Date: 2021-04-20 Impact factor: 6.982
Authors: Mohammad Nahid Hossain; Mohammad Helal Uddin; K Thapa; Md Abdullah Al Zubaer; Md Shafiqul Islam; Jiyun Lee; JongSu Park; S-H Yang Journal: J Healthc Eng Date: 2021-12-20 Impact factor: 2.682