Nematbakhsh, Shayan, Mohammadifard, Noushin, Riahi, Roya et al. · Journal of infection and public health · 2026 · DOI
Researchers used machine learning to identify factors associated with post-COVID fatigue in a cohort of 3,850 patients in Isfahan, Iran. The analysis identified 37 factors linked to fatigue; anxiety, BMI, depression, irritability, and memory issues were among the strongest predictors. A machine learning model achieved 85% accuracy at identifying patients at risk, though these results are based on observed associations and have not yet been validated in independent populations.
By analogy, understanding predictive factors for post-COVID fatigue may inform researchers investigating ME/CFS, given that some long COVID cases evolve into ME/CFS-like presentations. Identifying common symptom and metabolic correlates (anxiety, BMI, depression, neurological symptoms) across fatigue syndromes could guide prevention and early intervention strategies, though the relevance of these specific predictors to ME/CFS pathophysiology remains unclear.
This study does not establish causation or prove that any of the identified factors cause post-COVID fatigue. It does not validate the 85% accuracy rate in an independent cohort. It does not confirm whether these predictors apply to ME/CFS populations or whether machine learning predictions will improve patient outcomes. The case definition used to identify 'post-COVID fatigue' is not specified, limiting confidence in which patients were classified as affected.
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
Nematbakhsh, Shayan, Mohammadifard, Noushin, Riahi, Roya, Mohammadkhani, Mahdi, & Hosseini, Mohsen (2026). Prediction of post-COVID chronic fatigue syndrome using data mining and machine learning techniques in Isfahan COVID cohort study.. Journal of infection and public health. https://doi.org/10.1016/j.jiph.2026.103218
BibTeX
@article{mecfsatlas-nematbakhsh-2026-prediction-post,
author = {Nematbakhsh, Shayan and Mohammadifard, Noushin and Riahi, Roya and Mohammadkhani, Mahdi and Hosseini, Mohsen},
title = {Prediction of post-COVID chronic fatigue syndrome using data mining and machine learning techniques in Isfahan COVID cohort study.},
journal = {Journal of infection and public health},
year = {2026},
doi = {10.1016/j.jiph.2026.103218},
note = {PubMed: 42000587},
url = {https://www.mecfsatlas.com/evidence/nematbakhsh-2026-prediction-post},
}Atlas snapshot reference
ME/CFS Atlas. Generator v1 / Scanner v1.4 / policy v0.1. Accessed 2026-06-07. https://www.mecfsatlas.com/evidence/nematbakhsh-2026-prediction-post
Contribute
Private, reviewed by a human. Not a public comment thread.