Yichen Jia1, Chung-Chou H Chang1,2, Tiffany F Hughes3, Erin Jacobsen4, Shu Wang5, Sarah B Berman6, M Ilyas Kamboh7,8,4, Mary Ganguli8,4,6. 1. Departments of Biostatistics. 2. Departments of Medicine. 3. Department of Sociology, Anthropology, and Gerontology, Youngstown State University, Youngstown, OH. 4. Psychiatry. 5. Department of Biostatistics, University of Florida, Gainesville, FL. 6. Neurology, University of Pittsburgh School of Medicine Pittsburgh, PA. 7. Human Genetics. 8. Epidemiology, University of Pittsburgh Graduate School of Public Health.
Abstract
BACKGROUND: Incidence of dementia increases exponentially with age; little is known about its risk factors in the ninth and 10th decades of life. We identified predictors of dementia with onset after age 85 years in a longitudinal population-based cohort. METHODS: On the basis of annual assessments, incident cases of dementia were defined as those newly receiving Clinical Dementia Rating (CDR) ≥1. We used a machine learning method, Markov modeling with hybrid density-based and partition-based clustering, to identify variables associated with subsequent incident dementia. RESULTS: Of 1439 participants, 641 reached age 85 years during 10 years of follow-up and 45 of these became incident dementia cases. Using hybrid density-based and partition-based, among those aged 85+ years, probability of incident dementia was associated with worse self-rated health, more prescription drugs, subjective memory complaints, heart disease, cardiac arrhythmia, thyroid disease, arthritis, reported hypertension, higher systolic and diastolic blood pressure, and hearing impairment. In the subgroup aged 85 to 89 years, risk of dementia was also associated with depression symptoms, not currently smoking, and lacking confidantes. CONCLUSIONS: An atheoretical machine learning method revealed several factors associated with increased probability of dementia after age 85 years in a population-based cohort. If independently validated in other cohorts, these findings could help identify the oldest-old at the highest risk of dementia.
BACKGROUND: Incidence of dementia increases exponentially with age; little is known about its risk factors in the ninth and 10th decades of life. We identified predictors of dementia with onset after age 85 years in a longitudinal population-based cohort. METHODS: On the basis of annual assessments, incident cases of dementia were defined as those newly receiving Clinical Dementia Rating (CDR) ≥1. We used a machine learning method, Markov modeling with hybrid density-based and partition-based clustering, to identify variables associated with subsequent incident dementia. RESULTS: Of 1439 participants, 641 reached age 85 years during 10 years of follow-up and 45 of these became incident dementia cases. Using hybrid density-based and partition-based, among those aged 85+ years, probability of incident dementia was associated with worse self-rated health, more prescription drugs, subjective memory complaints, heart disease, cardiac arrhythmia, thyroid disease, arthritis, reported hypertension, higher systolic and diastolic blood pressure, and hearing impairment. In the subgroup aged 85 to 89 years, risk of dementia was also associated with depression symptoms, not currently smoking, and lacking confidantes. CONCLUSIONS: An atheoretical machine learning method revealed several factors associated with increased probability of dementia after age 85 years in a population-based cohort. If independently validated in other cohorts, these findings could help identify the oldest-old at the highest risk of dementia.
Authors: Mary Ganguli; Chung-Chou H Chang; Beth E Snitz; Judith A Saxton; Joni Vanderbilt; Ching-Wen Lee Journal: Am J Geriatr Psychiatry Date: 2010-08 Impact factor: 4.105
Authors: Mary Ganguli; Joni Vander Bilt; Ching-Wen Lee; Beth E Snitz; Chung-Chou H Chang; David A Loewenstein; Judith A Saxton Journal: J Int Neuropsychol Soc Date: 2010-07-08 Impact factor: 2.892
Authors: Mary Ganguli; Yichen Jia; Tiffany F Hughes; Beth E Snitz; Chung-Chou H Chang; Sarah B Berman; Kevin J Sullivan; M Ilyas Kamboh Journal: J Am Geriatr Soc Date: 2018-11-16 Impact factor: 5.562
Authors: Nienke Legdeur; Sven J van der Lee; Marcel de Wilde; Johan van der Lei; Majon Muller; Andrea B Maier; Pieter Jelle Visser Journal: Alzheimers Res Ther Date: 2019-05-17 Impact factor: 6.982