Machine Learning Detects Pattern of Differences in (fMRI) Data between (CFS) and (GWI), 2020, Baraniuk et al

Andy · Jul 28, 2020

Full title: Machine Learning Detects Pattern of Differences in Functional Magnetic Resonance Imaging (fMRI) Data between Chronic Fatigue Syndrome (CFS) and Gulf War Illness (GWI)

Background: Gulf War Illness (GWI) and Chronic Fatigue Syndrome (CFS) are two debilitating disorders that share similar symptoms of chronic pain, fatigue, and exertional exhaustion after exercise. Many physicians continue to believe that both are psychosomatic disorders and to date no underlying etiology has been discovered. As such, uncovering objective biomarkers is important to lend credibility to criteria for diagnosis and to help differentiate the two disorders.

Methods: We assessed cognitive differences in 80 subjects with GWI and 38 with CFS by comparing corresponding fMRI scans during 2-back working memory tasks before and after exercise to model brain activation during normal activity and after exertional exhaustion, respectively. Voxels were grouped by the count of total activity into the Automated Anatomical Labeling (AAL) atlas and used in an “ensemble” series of machine learning algorithms to assess if a multi-regional pattern of differences in the fMRI scans could be detected.

Results: A K-Nearest Neighbor (70%/81%), Linear Support Vector Machine (SVM) (70%/77%), Decision Tree (82%/82%), Random Forest (77%/78%), AdaBoost (69%/81%), Naïve Bayes (74%/78%), Quadratic Discriminant Analysis (QDA) (73%/75%), Logistic Regression model (82%/82%), and Neural Net (76%/77%) were able to differentiate CFS from GWI before and after exercise with an average of 75% accuracy in predictions across all models before exercise and 79% after exercise. An iterative feature selection and removal process based on Recursive Feature Elimination (RFE) and Random Forest importance selected 30 regions before exercise and 33 regions after exercise that differentiated CFS from GWI across all models, and produced the ultimate best accuracies of 82% before exercise and 82% after exercise by Logistic Regression or Decision Tree by a single model, and 100% before and after exercise when selected by any six or more models. Differential activation on both days included the right anterior insula, left putamen, and bilateral orbital frontal, ventrolateral prefrontal cortex, superior, inferior, and precuneus (medial) parietal, and lateral temporal regions. Day 2 had the cerebellum, left supplementary motor area and bilateral pre- and post-central gyri. Changes between days included the right Rolandic operculum switching to the left on Day 2, and the bilateral midcingulum switching to the left anterior cingulum.

Conclusion: We concluded that CFS and GWI are significantly differentiable using a pattern of fMRI activity based on an ensemble machine learning model.
Click to expand...

Open access, https://www.mdpi.com/2076-3425/10/7/456/htm

This is a follow-on from A Machine Learning Approach to the Differentiation of Functional Magnetic Resonance Imaging Data of CFS. Baraniuk et al. 2020

Hutan · Jul 29, 2020

I'm a bit sceptical about the conclusion, but then my set point for fMRI studies for now is scepticism.

As expected, the two samples are quite different in terms of gender:

The CFS sample was pretty small and the Fukuda criteria were applied - so PEM wasn't required.

The Automatic Anatomical Labeling (AAL) atlas was selected due to its widespread use, easy generalizability and accessibility across multiple types of software and platforms,
Click to expand...

I wonder how that atlas performs in samples with very different gender percentages. Differences in the education and gender of the two samples might account for the differences identified.

The subjects spanned a similar age range, however, they had different distributions of gender and BMI. Thus, age, gender, and BMI were controlled for in the final model build.
Click to expand...

'Controlled for' - An opportunity for data manipulation that produces a desired result. Not to say that that is what happened.

However, the insula, parietal, somatosensory strip, and other regions of the “pain matrix” that differentiated GWI and CFS from a sedentary control in our previous studies were not consistently part of the models
Click to expand...

So, it sounds as though the results found here were not consistent with what was found in earlier studies comparing each of the conditions with sedentary controls.

Therefore, it can be easy to overinterpret speculations of functional connectivity mapped to AAL regions.
Click to expand...

Thanks to the researchers for acknowledging this and not engaging in poorly founded speculation about the deficiencies of people with GWI and CFS.

If further studies are done, I'd like to see samples matched on gender and educational attainment.

Log in or Sign up

Machine Learning Detects Pattern of Differences in (fMRI) Data between (CFS) and (GWI), 2020, Baraniuk et al

Andy Committee Member

Hutan Moderator Staff Member

Share This Page

Log in or Sign up

Machine Learning Detects Pattern of Differences in (fMRI) Data between (CFS) and (GWI), 2020, Baraniuk et al

Andy Committee Member

Hutan Moderator Staff Member

Share This Page

Useful Searches