Massimiliano Grassi1, Giampaolo Perna1,2,3,4, Daniela Caldirola1, Koen Schruers2, Ranjan Duara5,6,7, David A Loewenstein3,6,8. 1. Department of Clinical Neurosciences, Hermanas Hospitalarias, Villa San Benedetto Menni Hospital, FoRiPsi, Albese con Cassano, Como, Italy. 2. Research Institute of Mental Health and Neuroscience and Department of Psychiatry and Neuropsychology, Faculty of Health, Medicine and Life Sciences, University of Maastricht, Maastricht, Netherlands. 3. Department of Psychiatry and Behavioral Sciences, Miller School of Medicine, University of Miami, Miami, FL, USA. 4. Mantovani Foundation, Arconate, Italy. 5. Department of Neurology, Herbert Wertheim College of Medicine, Florida International University of Miami, Miami, FL, USA. 6. Wien Center for Alzheimer's Disease and Memory Disorders, Mount Sinai Medical Center Miami Beach, FL, USA. 7. Courtesy Professor of Neurology, Department of Neurology, University of Florida College of Medicine, Gainesville Florida, USA. 8. Center on Aging, Miller School of Medicine, University of Miami, Miami, FL, USA.
Abstract
BACKGROUND: Available therapies for Alzheimer's disease (AD) can only alleviate and delay the advance of symptoms, with the greatest impact eventually achieved when provided at an early stage. Thus, early identification of which subjects at high risk, e.g., with MCI, will later develop AD is of key importance. Currently available machine learning algorithms achieve only limited predictive accuracy or they are based on expensive and hard-to-collect information. OBJECTIVE: The current study aims to develop an algorithm for a 3-year prediction of conversion to AD in MCI and PreMCI subjects based only on non-invasively and effectively collectable predictors. METHODS: A dataset of 123 MCI/PreMCI subjects was used to train different machine learning techniques. Baseline information regarding sociodemographic characteristics, clinical and neuropsychological test scores, cardiovascular risk indexes, and a visual rating scale for brain atrophy was used to extract 36 predictors. Leave-pair-out-cross-validation was employed as validation strategy and a recursive feature elimination procedure was applied to identify a relevant subset of predictors. RESULTS: 16 predictors were selected from all domains excluding sociodemographic information. The best model resulted a support vector machine with radial-basis function kernel (whole sample: AUC = 0.962, best balanced accuracy = 0.913; MCI sub-group alone: AUC = 0.914, best balanced accuracy = 0.874). CONCLUSIONS: Our algorithm shows very high cross-validated performances that outperform the vast majority of the currently available algorithms, and all those which use only non-invasive and effectively assessable predictors. Further testing and optimization in independent samples will warrant its application in both clinical practice and clinical trials.
BACKGROUND: Available therapies for Alzheimer's disease (AD) can only alleviate and delay the advance of symptoms, with the greatest impact eventually achieved when provided at an early stage. Thus, early identification of which subjects at high risk, e.g., with MCI, will later develop AD is of key importance. Currently available machine learning algorithms achieve only limited predictive accuracy or they are based on expensive and hard-to-collect information. OBJECTIVE: The current study aims to develop an algorithm for a 3-year prediction of conversion to AD in MCI and PreMCI subjects based only on non-invasively and effectively collectable predictors. METHODS: A dataset of 123 MCI/PreMCI subjects was used to train different machine learning techniques. Baseline information regarding sociodemographic characteristics, clinical and neuropsychological test scores, cardiovascular risk indexes, and a visual rating scale for brain atrophy was used to extract 36 predictors. Leave-pair-out-cross-validation was employed as validation strategy and a recursive feature elimination procedure was applied to identify a relevant subset of predictors. RESULTS: 16 predictors were selected from all domains excluding sociodemographic information. The best model resulted a support vector machine with radial-basis function kernel (whole sample: AUC = 0.962, best balanced accuracy = 0.913; MCI sub-group alone: AUC = 0.914, best balanced accuracy = 0.874). CONCLUSIONS: Our algorithm shows very high cross-validated performances that outperform the vast majority of the currently available algorithms, and all those which use only non-invasive and effectively assessable predictors. Further testing and optimization in independent samples will warrant its application in both clinical practice and clinical trials.
Authors: Stephen D Ginsberg; Michael H Malek-Ahmadi; Melissa J Alldred; Yinghua Chen; Kewei Chen; Moses V Chao; Scott E Counts; Elliott J Mufson Journal: Neurobiol Dis Date: 2019-07-23 Impact factor: 5.996
Authors: Sascha Gill; Pauline Mouches; Sophie Hu; Deepthi Rajashekar; Frank P MacMaster; Eric E Smith; Nils D Forkert; Zahinoor Ismail Journal: J Alzheimers Dis Date: 2020 Impact factor: 4.472
Authors: Jorge I Vélez; Luiggi A Samper; Mauricio Arcos-Holzinger; Lady G Espinosa; Mario A Isaza-Ruget; Francisco Lopera; Mauricio Arcos-Burgos Journal: Diagnostics (Basel) Date: 2021-05-17