Using data science to diagnose and characterize heterogeneity of Alzheimer's disease

Ting F.A. Ang1,2,3, Ning An4, Huitong Ding1,4, Sherral Devine1,3, Sanford H. Auerbach3,5, Joseph Massaro3,6, Prajakta Joshi1,3, Xue Liu1,3, Yulin Liu1,3, Elizabeth Mahon1,3, Rhoda Au1,2,3,5, Honghuang Lin3,7
1Department of Anatomy and Neurobiology, Boston University School of Medicine, Boston, MA, USA
2Department of Epidemiology, Boston University School of Public Health, Boston, MA, USA
3the Framingham Heart Study, Framingham, MA, USA
4School of Computer and Information, Hefei University of Technology, Hefei, China
5Department of Neurology, Boston University School of Medicine, Boston, MA USA
6Department of Biostatistics, Boston University School of Public Health, Boston, MA, USA
7Section of Computational Biomedicine, Department of Medicine, Boston University School of Medicine, Boston, MA, USA

Tóm tắt

AbstractIntroductionDespite the availability of age‐ and education‐adjusted standardized scores for most neuropsychological tests, there is a lack of objective rules in how to interpret multiple concurrent neuropsychological test scores that characterize the heterogeneity of Alzheimer's disease.MethodsUsing neuropsychological test scores of 2091 participants from the Framingham Heart Study, we devised an automated algorithm that follows general diagnostic criteria and explores the heterogeneity of Alzheimer's disease.ResultsWe developed a series of stepwise diagnosis rules that evaluate information from multiple neuropsychological tests to produce an intuitive and objective Alzheimer's disease dementia diagnosis with more than 80% accuracy.DiscussionA data‐driven stepwise diagnosis system is useful for diagnosis of Alzheimer's disease from neuropsychological tests. It demonstrated better performance than the traditional dichotomization of individuals' performance into satisfactory and unsatisfactory outcomes, making it more reflective of dementia as a spectrum disorder. This algorithm can be applied to both within clinic and outside‐of‐clinic settings.

Tài liệu tham khảo

10.1136/bmj.b158 10.1186/alzrt155 2018, Towards a dementia plan: a WHO guide 10.1080/03610739508253991 10.1001/archneur.57.6.808 Au R., 2015, Back to the future: Alzheimer's disease heterogeneity revisited, Alzheimers Dement, 1, 368 10.1016/j.jagp.2017.03.008 10.1037/a0013421 10.1053/apnr.2000.9231 Brayne C., 1998, The mini‐mental state examination, will we be using it in 2001?, Int J Geriatr Psychiatry, 13, 285 10.1212/WNL.45.9.1707 10.1001/jama.1993.03500180078038 10.1111/j.1532-5415.2005.53269.x 10.1212/WNL.44.5.867 10.1016/S0022-510X(02)00159-4 10.1016/j.cogsys.2010.12.002 10.1016/j.jfs.2017.06.005 10.3389/fendo.2017.00025 10.3109/00365521.2010.536254 10.3233/JAD-150562 10.1037/0894-4105.17.1.82 10.1056/NEJMoa1504327 Farmer M.E., 1987, Neuropsychological test performance in Framingham: a descriptive study, Psychol Rep, 60, 1023, 10.1177/0033294187060003-201.1 10.1016/0022-3956(75)90026-6 10.1093/ije/dyv337 10.1001/archinte.163.13.1524 10.1016/S0140-6736(96)90608-X Wechsler D., 1948, Wechsler Memory Scale (WMS) Wechsler D., 1955, Wechsler Adult Intelligence Scale (WAIS) Kaplan E., 1983, Boston Naming Test American Psychiatric Association, 1994, Diagnostic and Statistical Manual of Mental Disorders 10.1016/j.jalz.2011.03.005 10.1016/j.jalz.2010.12.002 10.1016/j.is.2005.03.002 R.Kerber.Chimerge: Discretization of numeric attributes.In Proceedings of the tenth national conference on Artificial intelligence.1992;123–128 10.14358/PERS.73.2.197 10.1016/j.jpeds.2009.02.024 10.2200/S00240ED1V01Y200912DMK002 10.1162/153244303322753616 M.A.Hall.Correlation‐based feature selection of discrete and numeric class machine learning.2000 10.1201/9781315139470 10.1007/s10115-007-0114-2 10.1007/s40745-015-0040-1 10.1093/brain/awn275 10.1016/j.tics.2013.10.011 10.1080/13854040701339356 10.1161/01.CIR.97.18.1837 10.1161/CIRCULATIONAHA.107.699579 10.1161/CIRCULATIONAHA.115.021275