TY - JOUR
T1 - Structural brain changes versus self-report
T2 - machine-learning classification of chronic fatigue syndrome patients
AU - Sevel, Landrew S.
AU - Boissoneault, Jeff
AU - Letzen, Janelle E.
AU - Robinson, Michael E.
AU - Staud, Roland
N1 - Funding Information:
This research was supported by NIH (R01 NR014049).
Funding Information:
This research was supported by NIH (R01
Publisher Copyright:
© 2018, Springer-Verlag GmbH Germany, part of Springer Nature.
PY - 2018/8/1
Y1 - 2018/8/1
N2 - Chronic fatigue syndrome (CFS) is a disorder associated with fatigue, pain, and structural/functional abnormalities seen during magnetic resonance brain imaging (MRI). Therefore, we evaluated the performance of structural MRI (sMRI) abnormalities in the classification of CFS patients versus healthy controls and compared it to machine learning (ML) classification based upon self-report (SR). Participants included 18 CFS patients and 15 healthy controls (HC). All subjects underwent T1-weighted sMRI and provided visual analogue-scale ratings of fatigue, pain intensity, anxiety, depression, anger, and sleep quality. sMRI data were segmented using FreeSurfer and 61 regions based on functional and structural abnormalities previously reported in patients with CFS. Classification was performed in RapidMiner using a linear support vector machine and bootstrap optimism correction. We compared ML classifiers based on (1) 61 a priori sMRI regional estimates and (2) SR ratings. The sMRI model achieved 79.58% classification accuracy. The SR (accuracy = 95.95%) outperformed both sMRI models. Estimates from multiple brain areas related to cognition, emotion, and memory contributed strongly to group classification. This is the first ML-based group classification of CFS. Our findings suggest that sMRI abnormalities are useful for discriminating CFS patients from HC, but SR ratings remain most effective in classification tasks.
AB - Chronic fatigue syndrome (CFS) is a disorder associated with fatigue, pain, and structural/functional abnormalities seen during magnetic resonance brain imaging (MRI). Therefore, we evaluated the performance of structural MRI (sMRI) abnormalities in the classification of CFS patients versus healthy controls and compared it to machine learning (ML) classification based upon self-report (SR). Participants included 18 CFS patients and 15 healthy controls (HC). All subjects underwent T1-weighted sMRI and provided visual analogue-scale ratings of fatigue, pain intensity, anxiety, depression, anger, and sleep quality. sMRI data were segmented using FreeSurfer and 61 regions based on functional and structural abnormalities previously reported in patients with CFS. Classification was performed in RapidMiner using a linear support vector machine and bootstrap optimism correction. We compared ML classifiers based on (1) 61 a priori sMRI regional estimates and (2) SR ratings. The sMRI model achieved 79.58% classification accuracy. The SR (accuracy = 95.95%) outperformed both sMRI models. Estimates from multiple brain areas related to cognition, emotion, and memory contributed strongly to group classification. This is the first ML-based group classification of CFS. Our findings suggest that sMRI abnormalities are useful for discriminating CFS patients from HC, but SR ratings remain most effective in classification tasks.
KW - Chronic fatigue
KW - Classification
KW - Gray matter
KW - Machine learning
KW - Self-report
UR - http://www.scopus.com/inward/record.url?scp=85047840514&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85047840514&partnerID=8YFLogxK
U2 - 10.1007/s00221-018-5301-8
DO - 10.1007/s00221-018-5301-8
M3 - Article
C2 - 29846797
AN - SCOPUS:85047840514
SN - 0014-4819
VL - 236
SP - 2245
EP - 2253
JO - Experimental Brain Research
JF - Experimental Brain Research
IS - 8
ER -