Forecasting the progression of Alzheimer's disease using neural networks and a novel preprocessing algorithm

Jack Albright1
1The Nueva School, San Mateo, CA

Tóm tắt

AbstractIntroductionThere is a 99.6% failure rate of clinical trials for drugs to treat Alzheimer's disease, likely because Alzheimer's disease (AD) patients cannot be easily identified at early stages. This study investigated machine learning approaches to use clinical data to predict the progression of AD in future years.MethodsData from 1737 patients were processed using the “All‐Pairs” technique, a novel methodology created for this study involving the comparison of all possible pairs of temporal data points for each patient. Machine learning models were trained on these processed data and evaluated using a separate testing data set (110 patients).ResultsA neural network model was effective (mAUC = 0.866) at predicting the progression of AD, both in patients who were initially cognitively normal and in patients suffering from mild cognitive impairment.DiscussionSuch a model could be used to identify patients at early stages of AD and who are therefore good candidates for clinical trials for AD therapeutics.

Tài liệu tham khảo

Selkoe D.J., 1999, Basic Neurochemistry: Molecular, Cellular and Medical Aspects 10.1016/j.neurobiolaging.2017.06.027 10.1007/978-1-4612-5174-3_3 10.1016/j.tibtech.2010.09.007 10.1038/nrneurol.2012.263 10.1186/1750-1326-6-85 10.1093/gerona/50A.1.M49 Moore P., 2019, Random forest prediction of Alzheimer's disease using pairwise selection from time series data, PLoS One, 14, e0211558, 10.1371/journal.pone.0211558 10.1002/msj.20279 R.V.Marinescu N.P.Oxtoby A.L.Young E.E.Bron A.W.Toga andM.W.Weiner et al.TADPOLE Challenge: Prediction of Longitudinal Evolution in Alzheimer's Disease.2018 arXiv: 1805.03909 [q‐bio.PE] Singanamalli A., 2017, Cascaded multi‐view canonical correlation (CaMCCo) for early diagnosis of Alzheimer's disease via fusion of clinical, imaging and omic features, Scientific Rep, 7, 8137, 10.1038/s41598-017-03925-0 Gamberger D., 2017, Identification of clusters of rapid and slow decliners among subjects at risk for Alzheimer's disease, Scientific Rep, 7, 6763, 10.1038/s41598-017-06624-y 2016, The need for early detection and treatment in Alzheimer's disease, EBioMedicine, 9, 1, 10.1016/j.ebiom.2016.07.001 Alzheimer's Association.What we know today about Alzheimer's disease.https://www.actionalz.org/research/science/alzheimers_disease_treatments.asp 2010 Accessed September 10 2019 10.1186/alzrt269 I.Mumal.Poor results prompt Takeda and Zinfandel to end phase 3 Alzheimer's therapy trial early.https://alzheimersnewstoday.com/2018/01/31/takeda‐and‐zinfandel‐bring‐early‐end‐to‐phase‐3‐trial‐of‐alzheimers‐therapy‐pioglitazone/ 2018 Accessed September 10 2019 M.Cortez.Merck will end Alzheimer's trial as alternative approach fails.https://www.bloomberg.com/news/articles/2018‐02‐13/merck‐will‐end‐alzheimer‐s‐trial‐as‐alternative‐approach‐fails 2018 Accessed September 10 2019 U.S. Food and Drug Administration.https://www.fda.gov/downloads/Drugs/GuidanceComplianceRegulatoryInformation/Guidances/UCM596728.pdf 2018 Accessed September 10 2019 S.Gottlieb.Statement from FDA commissioner Scott Gottlieb M.D. on advancing the development of novel treatments for neurological conditions; part of broader effort on modernizing FDA's new drug review programs.https://www.fda.gov/NewsEvents/Newsroom/PressAnnouncements/ucm596897.htm 2018 Accessed September 10 2019 10.1016/S1474-4422(15)00093-9 10.1097/WCO.0000000000000460 10.1093/brain/awn146 ADNI Staff.ADNI general procedures manual.https://adni.loni.usc.edu/wp‐content/uploads/2010/09/ADNI_GeneralProceduresManual.pdf 2010 Accessed September 10 2019 10.3233/JAD-170991 10.1109/TMI.2014.2314712 10.1097/00019442-200102000-00013 10.1080/13854046.2015.1119312 Boone K.B., 2005, Comparison of various RAVLT scores in the detection of noncredible memory performance, Arch Clin Neuropsychol, 20, 301, 10.1016/j.acn.2004.08.001 10.1093/geronj/37.3.323 S.Esmaeilzadeh D.I.Belivanis K.M.Pohl andE.Adeli.End‐to‐end Alzheimer's Disease Diagnosis and Biomarker Identification.2018 arXiv: 1810.00523 [cs.CV] 10.1371/journal.pone.0189990 10.1016/j.neuroimage.2011.01.008 10.1023/A:1010920819831 M.M.Ghazi M.Nielsen A.Pai M.J.Cardoso M.Modat andS.Ourselin et al.Robust Training of Recurrent Neural Networks to Handle Missing Data for Disease Progression Modeling.2018 arXiv: 1808.05500 [cs.CV] 10.1109/PRNI.2018.8423955 10.1016/j.neuroimage.2012.10.065