Linder, R, Dinser, R, Wagner, M et al. · In vivo (Athens, Greece) · 2002
Researchers tested whether a computer program called an artificial neural network could help doctors better identify ME/CFS by looking at patient symptoms and comparing them to two other conditions that also cause fatigue: lupus and fibromyalgia. The computer program was very accurate—correctly identifying ME/CFS about 95% of the time—and worked better than traditional statistical methods for creating diagnostic rules.
Establishing reliable classification criteria is essential for ME/CFS diagnosis and research enrollment. This study demonstrates that computational methods may identify complex symptom patterns that distinguish ME/CFS from phenotypically similar conditions, potentially improving diagnostic accuracy and reducing misclassification in both clinical and research settings.
This study does not prove that ANN-derived criteria should immediately replace clinical judgment or be used in clinical practice without further validation in independent populations. The findings are limited to distinguishing ME/CFS from SLE and FMA specifically; applicability to other fatigue disorders is unknown. The small validation sample (n=40) means the reported sensitivity and specificity require confirmation in larger, prospective studies.
About the PEM badge: “PEM required” means post-exertional malaise was an explicit required diagnostic criterion for participant inclusion in this study — not that PEM was studied, observed, or discussed. Studies using criteria that do not require PEM (e.g. Fukuda, Oxford) are tagged “PEM not required”. How the atlas works →
The first block is for the primary paper and is the citation you should use in research work. The atlas-snapshot line only applies if you are specifically referring to this atlas’s reading of the paper on the date shown.
Primary citation
Linder, R, Dinser, R, Wagner, M, Krueger, G R F, & Hoffmann, A (2002). Generation of classification criteria for chronic fatigue syndrome using an artificial neural network and traditional criteria set.. In vivo (Athens, Greece). https://pubmed.ncbi.nlm.nih.gov/11980359/
BibTeX
@article{mecfsatlas-linder-2002-generation-classification,
author = {Linder, R and Dinser, R and Wagner, M and Krueger, G R F and Hoffmann, A},
title = {Generation of classification criteria for chronic fatigue syndrome using an artificial neural network and traditional criteria set.},
journal = {In vivo (Athens, Greece)},
year = {2002},
note = {PubMed: 11980359},
url = {https://www.mecfsatlas.com/evidence/linder-2002-generation-classification},
}Atlas snapshot reference
ME/CFS Atlas. Generator v1 / Scanner v1.4 / policy v0.1. Accessed 2026-05-30. https://www.mecfsatlas.com/evidence/linder-2002-generation-classification
Contribute
Private, reviewed by a human. Not a public comment thread.