Ming Lin1, Pinghua Gong1, Tao Yang1, Jieping Ye1, Roger L Albin2,3, Hiroko H Dodge2,4. 1. Department of Computational Medicine and Bioinformatics. 2. Department of Neurology and Michigan Alzheimer's Disease Center, University of Michigan. 3. Neurology Service & GRECC, VAAAHS, Ann Arbor, MI. 4. Department of Neurology and Layton Aging and Alzheimer's Disease Center, Oregon Health & Science University, Portland, OR.
Abstract
BACKGROUND: Clinical trials increasingly aim to retard disease progression during presymptomatic phases of Mild Cognitive Impairment (MCI) and thus recruiting study participants at high risk for developing MCI is critical for cost-effective prevention trials. However, accurately identifying those who are destined to develop MCI is difficult. Collecting biomarkers is often expensive. METHODS: We used only noninvasive clinical variables collected in the National Alzheimer's Coordinating Center (NACC) Uniform Data Sets version 2.0 and applied machine learning techniques to build a low-cost and accurate Mild Cognitive Impairment (MCI) conversion prediction calculator. Cross-validation and bootstrap were used to select as few variables as possible accurately predicting MCI conversion within 4 years. RESULTS: A total of 31,872 unique subjects, 748 clinical variables, and additional 128 derived variables in NACC data sets were used. About 15 noninvasive clinical variables are identified for predicting MCI/aMCI/naMCI converters, respectively. Over 75% Receiver Operating Characteristic Area Under the Curves (ROC AUC) was achieved. By bootstrap we created a simple spreadsheet calculator which estimates the probability of developing MCI within 4 years with a 95% confidence interval. CONCLUSIONS: We achieved reasonably high prediction accuracy using only clinical variables. The approach used here could be useful for study enrichment in preclinical trials where enrolling participants at risk of cognitive decline is critical for proving study efficacy, and also for developing a shorter assessment battery.
BACKGROUND: Clinical trials increasingly aim to retard disease progression during presymptomatic phases of Mild Cognitive Impairment (MCI) and thus recruiting study participants at high risk for developing MCI is critical for cost-effective prevention trials. However, accurately identifying those who are destined to develop MCI is difficult. Collecting biomarkers is often expensive. METHODS: We used only noninvasive clinical variables collected in the National Alzheimer's Coordinating Center (NACC) Uniform Data Sets version 2.0 and applied machine learning techniques to build a low-cost and accurate Mild Cognitive Impairment (MCI) conversion prediction calculator. Cross-validation and bootstrap were used to select as few variables as possible accurately predicting MCI conversion within 4 years. RESULTS: A total of 31,872 unique subjects, 748 clinical variables, and additional 128 derived variables in NACC data sets were used. About 15 noninvasive clinical variables are identified for predicting MCI/aMCI/naMCI converters, respectively. Over 75% Receiver Operating Characteristic Area Under the Curves (ROC AUC) was achieved. By bootstrap we created a simple spreadsheet calculator which estimates the probability of developing MCI within 4 years with a 95% confidence interval. CONCLUSIONS: We achieved reasonably high prediction accuracy using only clinical variables. The approach used here could be useful for study enrichment in preclinical trials where enrolling participants at risk of cognitive decline is critical for proving study efficacy, and also for developing a shorter assessment battery.
Authors: Sarah E Monsell; Hiroko H Dodge; Xiao-Hua Zhou; Yunqi Bu; Lilah M Besser; Charles Mock; Stephen E Hawes; Walter A Kukull; Sandra Weintraub Journal: Alzheimer Dis Assoc Disord Date: 2016 Apr-Jun Impact factor: 2.703
Authors: Jeannie-Marie S Leoutsakos; Alexandra L Bartlett; Sarah N Forrester; Constantine G Lyketsos Journal: Alzheimers Dement Date: 2013-08-15 Impact factor: 21.566
Authors: Michael Ewers; Matthias Brendel; Angela Rizk-Jackson; Axel Rominger; Peter Bartenstein; Norbert Schuff; Michael W Weiner Journal: Neuroimage Clin Date: 2013-11-04 Impact factor: 4.881
Authors: Nikki H Stricker; Emily S Lundt; Sabrina M Albertson; Mary M Machulda; Shehroo B Pudumjee; Walter K Kremers; Clifford R Jack; David S Knopman; Ronald C Petersen; Michelle M Mielke Journal: J Alzheimers Dis Date: 2020 Impact factor: 4.472
Authors: Katherine E Dorociak; Nora Mattek; John E Ferguson; Zachary T Beattie; Nicole Sharma; Jeffrey A Kaye; Mira I Leese; Bridget M Doane; Adriana M Hughes Journal: Alzheimer Dis Assoc Disord Date: 2021 Jul-Sep 01 Impact factor: 2.703
Authors: D P Devanand; Howard Andrews; William C Kreisl; Qolamreza Razlighi; Anne Gershon; Yaakov Stern; Akiva Mintz; Thomas Wisniewski; Edward Acosta; Julianna Pollina; Mariasofia Katsikoumbas; Karen L Bell; Gregory H Pelton; Deborah Deliyannides; K M Prasad; Edward D Huey Journal: BMJ Open Date: 2020-02-06 Impact factor: 2.692
Authors: Hiroko H Dodge; Felicia C Goldstein; Nicole I Wakim; Tamar Gefen; Merilee Teylan; Kwun C G Chan; Walter A Kukull; Lisa L Barnes; Bruno Giordani; Timothy M Hughes; Joel H Kramer; David A Loewenstein; Daniel C Marson; Dan M Mungas; Nora Mattek; Bonnie C Sachs; David P Salmon; Monica Willis-Parker; Kathleen A Welsh-Bohmer; Katherine V Wild; John C Morris; Sandra Weintraub Journal: Alzheimers Dement (N Y) Date: 2020-11-24
Authors: Lilah Besser; Walter Kukull; David S Knopman; Helena Chui; Douglas Galasko; Sandra Weintraub; Gregory Jicha; Cynthia Carlsson; Jeffrey Burns; Joseph Quinn; Robert A Sweet; Katya Rascovsky; Merilee Teylan; Duane Beekly; George Thomas; Mark Bollenbeck; Sarah Monsell; Charles Mock; Xiao Hua Zhou; Nicole Thomas; Elizabeth Robichaud; Margaret Dean; Janene Hubbard; Mary Jacka; Kristen Schwabe-Fry; Joylee Wu; Creighton Phelps; John C Morris Journal: Alzheimer Dis Assoc Disord Date: 2018 Oct-Dec Impact factor: 2.703