Leveraging Explainable Automated Machine Learning (AutoML) and Metabolomics for Robust Diagnosis and Pathophysiological Insights in Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS)
Bibliographic record
Abstract
Background/Objectives: Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is a debilitating complex disease with an elusive etiology, lacking objective diagnostic biomarkers. This study leverages advanced Automated Machine Learning (AutoML) to analyze plasma metabolomic and lipidomic profiles for the purpose of ME/CFS detection. Methods: We utilized a publicly available dataset comprising 888 metabolic features from 106 ME/CFS patients and 91 matched controls. Three AutoML frameworks—TPOT, Auto-Sklearn, and H2O AutoML—were benchmarked under identical time constraints. Univariate ROC and PLS-DA analyses with cross-validation, permutation testing, and VIP-based feature selection were applied to standardized, log-transformed omics data to identify significant discriminatory metabolites/lipids and assess their intercorrelations. Results: TPOT significantly outperformed its counterparts, achieving an area under the curve (AUC) of 92.1%, accuracy of 87.3%, sensitivity of 85.8%, and specificity of 89.0%. The PLS-DA model revealed a moderate but statistically significant discrimination between ME/CFS and controls. Explainable artificial intelligence (XAI) via SHAP analysis of the optimal TPOT model identified key metabolites implicating dysregulated pathways in mitochondrial energy metabolism (succinic acid, pyruvic acid, leucine), chronic inflammation (prostaglandin D2, 11,12-EET), gut–brain axis communication (glycocholic acid), and cell membrane integrity (pc(35:2)a). Conclusions: Our results demonstrate that TPOT-derived models not only provide a highly accurate and robust diagnostic tool but also yield biologically interpretable insights into the pathophysiology of ME/CFS, highlighting its potential for clinical decision support and elucidating novel therapeutic targets.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".