Liana G Apostolova1, Kristy S Hwang2, David Avila2, David Elashoff2, Omid Kohannim2, Edmond Teng2, Sophie Sokolow2, Clifford R Jack2, William J Jagust2, Leslie Shaw2, John Q Trojanowski2, Michael W Weiner2, Paul M Thompson2. 1. From the Departments of Neurology (L.G.A., K.S.H., D.A., O.K., E.T., P.M.T.), Medicine Statistics Core (D.E.), and School of Nursing (S.S.), David Geffen School of Medicine at University of California, Los Angeles; Institute for Neuroinformatics (P.M.T.), Keck School of Medicine, University of Southern California, Los Angeles; Veterans Affairs Greater Los Angeles Healthcare System (E.T.); Department of Diagnostic Radiology (C.R.J.), Mayo Clinic, Rochester, MN; Department of Public Health and Neuroscience (W.J.J.), University of California, Berkeley; Department of Pathology and Laboratory Medicine (L.S., J.Q.T.), University of Pennsylvania School of Medicine, Philadelphia; Department of Radiology (M.W.W.), University of California, San Francisco; and Department of Veterans Affairs Medical Center (M.W.W.), San Francisco, CA. lapostolova@mednet.ucla.edu. 2. From the Departments of Neurology (L.G.A., K.S.H., D.A., O.K., E.T., P.M.T.), Medicine Statistics Core (D.E.), and School of Nursing (S.S.), David Geffen School of Medicine at University of California, Los Angeles; Institute for Neuroinformatics (P.M.T.), Keck School of Medicine, University of Southern California, Los Angeles; Veterans Affairs Greater Los Angeles Healthcare System (E.T.); Department of Diagnostic Radiology (C.R.J.), Mayo Clinic, Rochester, MN; Department of Public Health and Neuroscience (W.J.J.), University of California, Berkeley; Department of Pathology and Laboratory Medicine (L.S., J.Q.T.), University of Pennsylvania School of Medicine, Philadelphia; Department of Radiology (M.W.W.), University of California, San Francisco; and Department of Veterans Affairs Medical Center (M.W.W.), San Francisco, CA.
Abstract
BACKGROUND: The goal of this study was to identify a clinical biomarker signature of brain amyloidosis in the Alzheimer's Disease Neuroimaging Initiative 1 (ADNI1) mild cognitive impairment (MCI) cohort. METHODS: We developed a multimodal biomarker classifier for predicting brain amyloidosis using cognitive, imaging, and peripheral blood protein ADNI1 MCI data. We used CSF β-amyloid 1-42 (Aβ42) ≤ 192 pg/mL as proxy measure for Pittsburgh compound B (PiB)-PET standard uptake value ratio ≥ 1.5. We trained our classifier in the subcohort with CSF Aβ42 but no PiB-PET data and tested its performance in the subcohort with PiB-PET but no CSF Aβ42 data. We also examined the utility of our biomarker signature for predicting disease progression from MCI to Alzheimer dementia. RESULTS: The CSF training classifier selected Mini-Mental State Examination, Trails B, Auditory Verbal Learning Test delayed recall, education, APOE genotype, interleukin 6 receptor, clusterin, and ApoE protein, and achieved leave-one-out accuracy of 85% (area under the curve [AUC] = 0.8). The PiB testing classifier achieved an AUC of 0.72, and when classifier self-tuning was allowed, AUC = 0.74. The 36-month disease-progression classifier achieved AUC = 0.75 and accuracy = 71%. CONCLUSIONS: Automated classifiers based on cognitive and peripheral blood protein variables can identify the presence of brain amyloidosis with a modest level of accuracy. Such methods could have implications for clinical trial design and enrollment in the near future. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that a classification algorithm based on cognitive, imaging, and peripheral blood protein measures identifies patients with brain amyloid on PiB-PET with moderate accuracy (sensitivity 68%, specificity 78%).
BACKGROUND: The goal of this study was to identify a clinical biomarker signature of brain amyloidosis in the Alzheimer's Disease Neuroimaging Initiative 1 (ADNI1) mild cognitive impairment (MCI) cohort. METHODS: We developed a multimodal biomarker classifier for predicting brain amyloidosis using cognitive, imaging, and peripheral blood protein ADNI1 MCI data. We used CSF β-amyloid 1-42 (Aβ42) ≤ 192 pg/mL as proxy measure for Pittsburgh compound B (PiB)-PET standard uptake value ratio ≥ 1.5. We trained our classifier in the subcohort with CSF Aβ42 but no PiB-PET data and tested its performance in the subcohort with PiB-PET but no CSF Aβ42 data. We also examined the utility of our biomarker signature for predicting disease progression from MCI to Alzheimer dementia. RESULTS: The CSF training classifier selected Mini-Mental State Examination, Trails B, Auditory Verbal Learning Test delayed recall, education, APOE genotype, interleukin 6 receptor, clusterin, and ApoE protein, and achieved leave-one-out accuracy of 85% (area under the curve [AUC] = 0.8). The PiB testing classifier achieved an AUC of 0.72, and when classifier self-tuning was allowed, AUC = 0.74. The 36-month disease-progression classifier achieved AUC = 0.75 and accuracy = 71%. CONCLUSIONS: Automated classifiers based on cognitive and peripheral blood protein variables can identify the presence of brain amyloidosis with a modest level of accuracy. Such methods could have implications for clinical trial design and enrollment in the near future. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that a classification algorithm based on cognitive, imaging, and peripheral blood protein measures identifies patients with brain amyloid on PiB-PET with moderate accuracy (sensitivity 68%, specificity 78%).
Authors: Stephen D Weigand; Prashanthi Vemuri; Heather J Wiste; Matthew L Senjem; Vernon S Pankratz; Paul S Aisen; Michael W Weiner; Ronald C Petersen; Leslie M Shaw; John Q Trojanowski; David S Knopman; Clifford R Jack Journal: Alzheimers Dement Date: 2011-02-01 Impact factor: 21.566
Authors: Sid E O'Bryant; Valerie L Hobson; James R Hall; Robert C Barber; Song Zhang; Leigh Johnson; Ramon Diaz-Arrastia Journal: Dement Geriatr Cogn Disord Date: 2010-12-07 Impact factor: 2.959
Authors: Shabnam Baig; Laura E Palmer; Michael J Owen; Julie Williams; Patrick G Kehoe; Seth Love Journal: J Alzheimers Dis Date: 2012 Impact factor: 4.472
Authors: Clifford R Jack; Heather J Wiste; Prashanthi Vemuri; Stephen D Weigand; Matthew L Senjem; Guang Zeng; Matt A Bernstein; Jeffrey L Gunter; Vernon S Pankratz; Paul S Aisen; Michael W Weiner; Ronald C Petersen; Leslie M Shaw; John Q Trojanowski; David S Knopman Journal: Brain Date: 2010-10-08 Impact factor: 13.501
Authors: Burcu F Darst; Rebecca L Koscik; Annie M Racine; Jennifer M Oh; Rachel A Krause; Cynthia M Carlsson; Henrik Zetterberg; Kaj Blennow; Bradley T Christian; Barbara B Bendlin; Ozioma C Okonkwo; Kirk J Hogan; Bruce P Hermann; Mark A Sager; Sanjay Asthana; Sterling C Johnson; Corinne D Engelman Journal: J Alzheimers Dis Date: 2017 Impact factor: 4.472
Authors: Manja Koch; Steven T DeKosky; Matthew Goodman; Jiehuan Sun; Jeremy D Furtado; Annette L Fitzpatrick; Rachel H Mackey; Tianxi Cai; Oscar L Lopez; Lewis H Kuller; Kenneth J Mukamal; Majken K Jensen Journal: J Lipid Res Date: 2019-12-31 Impact factor: 5.922
Authors: Dallas P Veitch; Michael W Weiner; Paul S Aisen; Laurel A Beckett; Charles DeCarli; Robert C Green; Danielle Harvey; Clifford R Jack; William Jagust; Susan M Landau; John C Morris; Ozioma Okonkwo; Richard J Perrin; Ronald C Petersen; Monica Rivera-Mindt; Andrew J Saykin; Leslie M Shaw; Arthur W Toga; Duygu Tosun; John Q Trojanowski Journal: Alzheimers Dement Date: 2021-09-28 Impact factor: 16.655
Authors: Robert A Stern; Yorghos Tripodis; Christine M Baugh; Nathan G Fritts; Brett M Martin; Christine Chaisson; Robert C Cantu; James A Joyce; Sahil Shah; Tsuneya Ikezu; Jing Zhang; Cicek Gercel-Taylor; Douglas D Taylor Journal: J Alzheimers Dis Date: 2016 Impact factor: 4.472