Machine Learning Predicts Conversion from Normal Aging to Mild Cognitive Impairment Using Medical History, APOE Genotype, and Neuropsychological Assessment
Affiliations: [a] Center for Individualized Medicine, Mayo Clinic, Jacksonville, FL, USA
| [b] Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic, Rochester, MN, USA
| [c] Department of Psychiatry and Psychology, Mayo Clinic, Jacksonville, FL, USA
| [d] Department of Neurology, Mayo Clinic, Phoenix, AZ, USA
| [e] Department of Psychiatry and Psychology, Mayo Clinic, Rochester, MN, USA
Correspondence:
[*]
Correspondence to: Melanie J. Chandler, PhD, Associate Professor of Psychology, Vice Chair, Department of Psychiatry & Psychology, 4315 Pablo Oaks Ct, Jacksonville, FL 32224, USA. Tel.: +1 904 953 6600; E-mail: [email protected] and Arjun P. Athreya, PhD, Assistant Professor of Psychiatry, Assistant Professor of Pharmacology, 200 First Street SW, Rochester, MN 55901, USA. Tel.: +1 507 284 2511; E-mail: [email protected].
Note: [1] These authors contributed equally to this work.
Abstract: Background:Identifying individuals at risk for mild cognitive impairment (MCI) is of urgent clinical need. Objective:This study aimed to determine whether machine learning approaches could harness longitudinal neuropsychology measures, medical data, and APOE ɛ4 genotype to identify individuals at risk of MCI 1 to 2 years prior to diagnosis. Methods:Data from 676 individuals who participated in the ‘APOE in the Predisposition to, Protection from and Prevention of Alzheimer’s Disease’ longitudinal study (N = 66 who converted to MCI) were utilized in supervised machine learning algorithms to predict conversion to MCI. Results:A random forest algorithm predicted conversion 1–2 years prior to diagnosis with 97% accuracy (p = 0.0026). The global minima (each individual’s lowest score) of memory measures from the ‘Rey Auditory Verbal Learning Test’ and the ‘Selective Reminding Test’ were the strongest predictors. Conclusions:This study demonstrates the feasibility of using machine learning to identify individuals likely to convert from normal cognition to MCI.
