Abstract
It is increasingly recognized that Alzheimer’s disease (AD) exists before dementia is present and that shifts in amyloid beta occur long before clinical symptoms can be detected. Early detection of these molecular changes is a key aspect for the success of interventions aimed at slowing down rates of cognitive decline. Recent evidence indicates that of the two established methods for measuring amyloid, a decrease in cerebrospinal fluid (CSF) amyloid β 1−42 (Aβ 1−42 ) may be an earlier indicator of Alzheimer’s disease risk than measures of amyloid obtained from Positron Emission Tomography (PET). However, CSF collection is highly invasive and expensive. In contrast, blood collection is routinely performed, minimally invasive and cheap. In this work, we develop a blood-based signature that can provide a cheap and minimally invasive estimation of an individual’s CSF amyloid status using a machine learning approach. We show that a Random Forest model derived from plasma analytes can accurately predict subjects as having abnormal (low) CSF Aβ 1−42 levels indicative of AD risk (0.84 AUC, 0.78 sensitivity, and 0.73 specificity). Refinement of the modeling indicates that only APOEε4 carrier status and four plasma analytes (CGA, Aβ 1−42 , Eotaxin 3, APOE) are required to achieve a high level of accuracy. Furthermore, we show across an independent validation cohort that individuals with predicted abnormal CSF Aβ 1−42 levels transitioned to an AD diagnosis over 120 months significantly faster than those with predicted normal CSF Aβ 1−42 levels and that the resulting model also validates reasonably across PET Aβ 1−42 status (0.78 AUC). This is the first study to show that a machine learning approach, using plasma protein levels, age and APOEε4 carrier status, is able to predict CSF Aβ 1−42 status, the earliest risk indicator for AD, with high accuracy.
Original language | English (US) |
---|---|
Article number | 4163 |
Journal | Scientific Reports |
Volume | 9 |
Issue number | 1 |
DOIs | |
State | Published - Dec 1 2019 |
Externally published | Yes |
Fingerprint
ASJC Scopus subject areas
- General
Cite this
A blood-based signature of cerebrospinal fluid Aβ 1–42 status . / Alzheimer’s Disease Metabolomics Consortium; Alzheimer’s Disease Neuroimaging Initiative.
In: Scientific Reports, Vol. 9, No. 1, 4163, 01.12.2019.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - A blood-based signature of cerebrospinal fluid Aβ 1–42 status
AU - Alzheimer’s Disease Metabolomics Consortium
AU - Alzheimer’s Disease Neuroimaging Initiative
AU - Goudey, Benjamin
AU - Fung, Bowen J.
AU - Schieber, Christine
AU - Faux, Noel G.
AU - Weiner, Michael W.
AU - Aisen, Paul
AU - Petersen, Ronald
AU - Jack, Clifford R.
AU - Jagust, William
AU - Trojanowki, John Q.
AU - Toga, Arthur W.
AU - Beckett, Laurel
AU - Green, Robert C.
AU - Saykin, Andrew J.
AU - Morris, John
AU - Shaw, Leslie M.
AU - Kaye, Jeffrey
AU - Quinn, Joseph
AU - Silbert, Lisa
AU - Lind, Betty
AU - Carter, Raina
AU - Dolen, Sara
AU - Schneider, Lon S.
AU - Pawluczyk, Sonia
AU - Beccera, Mauricio
AU - Teodoro, Liberty
AU - Spann, Bryan M.
AU - Brewer, James
AU - Vanderswag, Helen
AU - Fleisher, Adam
AU - Heidebrink, Judith L.
AU - Lord, Joanne L.
AU - Mason, Sara S.
AU - Albers, Colleen S.
AU - Knopman, David
AU - Johnson, Kris
AU - Doody, Rachelle S.
AU - Villanueva-Meyer, Javier
AU - Chowdhury, Munir
AU - Rountree, Susan
AU - Dang, Mimi
AU - Stern, Yaakov
AU - Honig, Lawrence S.
AU - Bell, Karen L.
AU - Ances, Beau
AU - Morris, John C.
AU - Carroll, Maria
AU - Creech, Mary L.
AU - Franklin, Erin
AU - Quiceno, Mary
PY - 2019/12/1
Y1 - 2019/12/1
N2 - It is increasingly recognized that Alzheimer’s disease (AD) exists before dementia is present and that shifts in amyloid beta occur long before clinical symptoms can be detected. Early detection of these molecular changes is a key aspect for the success of interventions aimed at slowing down rates of cognitive decline. Recent evidence indicates that of the two established methods for measuring amyloid, a decrease in cerebrospinal fluid (CSF) amyloid β 1−42 (Aβ 1−42 ) may be an earlier indicator of Alzheimer’s disease risk than measures of amyloid obtained from Positron Emission Tomography (PET). However, CSF collection is highly invasive and expensive. In contrast, blood collection is routinely performed, minimally invasive and cheap. In this work, we develop a blood-based signature that can provide a cheap and minimally invasive estimation of an individual’s CSF amyloid status using a machine learning approach. We show that a Random Forest model derived from plasma analytes can accurately predict subjects as having abnormal (low) CSF Aβ 1−42 levels indicative of AD risk (0.84 AUC, 0.78 sensitivity, and 0.73 specificity). Refinement of the modeling indicates that only APOEε4 carrier status and four plasma analytes (CGA, Aβ 1−42 , Eotaxin 3, APOE) are required to achieve a high level of accuracy. Furthermore, we show across an independent validation cohort that individuals with predicted abnormal CSF Aβ 1−42 levels transitioned to an AD diagnosis over 120 months significantly faster than those with predicted normal CSF Aβ 1−42 levels and that the resulting model also validates reasonably across PET Aβ 1−42 status (0.78 AUC). This is the first study to show that a machine learning approach, using plasma protein levels, age and APOEε4 carrier status, is able to predict CSF Aβ 1−42 status, the earliest risk indicator for AD, with high accuracy.
AB - It is increasingly recognized that Alzheimer’s disease (AD) exists before dementia is present and that shifts in amyloid beta occur long before clinical symptoms can be detected. Early detection of these molecular changes is a key aspect for the success of interventions aimed at slowing down rates of cognitive decline. Recent evidence indicates that of the two established methods for measuring amyloid, a decrease in cerebrospinal fluid (CSF) amyloid β 1−42 (Aβ 1−42 ) may be an earlier indicator of Alzheimer’s disease risk than measures of amyloid obtained from Positron Emission Tomography (PET). However, CSF collection is highly invasive and expensive. In contrast, blood collection is routinely performed, minimally invasive and cheap. In this work, we develop a blood-based signature that can provide a cheap and minimally invasive estimation of an individual’s CSF amyloid status using a machine learning approach. We show that a Random Forest model derived from plasma analytes can accurately predict subjects as having abnormal (low) CSF Aβ 1−42 levels indicative of AD risk (0.84 AUC, 0.78 sensitivity, and 0.73 specificity). Refinement of the modeling indicates that only APOEε4 carrier status and four plasma analytes (CGA, Aβ 1−42 , Eotaxin 3, APOE) are required to achieve a high level of accuracy. Furthermore, we show across an independent validation cohort that individuals with predicted abnormal CSF Aβ 1−42 levels transitioned to an AD diagnosis over 120 months significantly faster than those with predicted normal CSF Aβ 1−42 levels and that the resulting model also validates reasonably across PET Aβ 1−42 status (0.78 AUC). This is the first study to show that a machine learning approach, using plasma protein levels, age and APOEε4 carrier status, is able to predict CSF Aβ 1−42 status, the earliest risk indicator for AD, with high accuracy.
UR - http://www.scopus.com/inward/record.url?scp=85062726457&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062726457&partnerID=8YFLogxK
U2 - 10.1038/s41598-018-37149-7
DO - 10.1038/s41598-018-37149-7
M3 - Article
C2 - 30853713
AN - SCOPUS:85062726457
VL - 9
JO - Scientific Reports
JF - Scientific Reports
SN - 2045-2322
IS - 1
M1 - 4163
ER -