Identifying Defining Aspects of Chronic Fatigue Syndrome


Note: You can read the full text of this study HERE.

Editor’s Comment: This is a highly technical study which may prove challenging for a lay audience. However, the implications are profound.This research group has applied a computer algorithm used for data mining and clustering in order to sort symptoms of ME/CFS by frequency and severity.The method used to gather information was the DePaul Symptom Questionnaire (DSQ), developed by Leonard Jason.The study found that 11 symptoms relating to fatigue, post-exertional malaise, sleep dysfunction, neurocognitive problems, and general pain were highly predictive of ME/CFS. “This indicates that fatigue, post-exertional malaise, and neurocognitive disorders are the most predictive symptom categories of CFS,” concluded the authors. “As such, a CFS case definition should place particular emphasis on these factors.” What is most significant about this study is that not only was the application of the algorithm to the DSQ more accurate as a diagnostic tool than any existing case definition, it can be used by any researcher to identify a patient cohort.


Identifying Defining Aspects of Chronic Fatigue Syndrome via Unsupervised Machine Learning and Feature Selection

By Samuel P. Watson at al.

In this work we propose an unsupervised machine learning method of predicting chronic fatigue syndrome (CFS) based on the k-means algorithm using self-reported questionnaire responses.

We first suggest a method of determining the presence of a symptom based on its frequency and severity using an unsupervised dynamic thresholding approach. This threshold is used to diagnose subjects with 54 symptoms related to CFS.

Based on these diagnoses, k-means is used to predict the presence of CFS. We find that k-means does not have significantly worse predictive diagnostic accuracy than commonly used CFS case definitions.

After applying supervised feature selection, k-means achieves significantly better diagnostic accuracy than any of the case definitions examined. We use these results to suggest the basis for an empirically founded CFS case definition.

Source: Samuel P. Watson, Amy S. Ruskin, Valerie Simonis, Leonard A. Jason, Madison Sunnquist, and Jacob D. Furst, “Identifying Defining Aspects of Chronic Fatigue Syndrome via Unsupervised Machine Learning and Feature Selection,” International Journal of Machine Learning and Computing vol.4, no. 2, pp. 133-138, 2014.


S. P. Watson is with the Carleton College, Northfield, MN 55057 USA (e-mail:
A. S. Ruskin is with Pomona College, Claremont, CA 91711 USA (e-mail:
J. D. Furst and V. Simonis are with the College of Computing and Digital Media, DePaul University, Chicago, IL 60604 USA.
L.A. Jason and M. Sunnquist are with the College of Science and Health, DePaul University, Chicago, IL 60614 USA.

1 Star2 Stars3 Stars4 Stars5 Stars (No Ratings Yet)

Leave a Reply