AI Science Tracker
EN

Leveraging Explainable Automated Machine Learning (AutoML) and Metabolomics for Robust Diagnosis and Pathophysiological Insights in Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS).

Malatya Turgut Ozal University; Lakehead University · 30 Oct 2025 · medicine

Discovery

Leveraging Explainable Automated Machine Learning (AutoML) and Metabolomics for Robust Diagnosis and Pathophysiological Insights in Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS).

Source check: Source checked. Not independent scientific confirmation.

Finding: TPOT reported AUC 92.1±1.9%, accuracy 87.3±2.3%, sensitivity 85.8±3.2%, specificity 89.0±2.6%; SHAP identified candidate features. These are associations/classification results, not causal mechanisms. TPOT, Auto-Sklearn and H2O AutoML searched pipelines on 888 metabolite/lipid features; SHAP was applied to the selected TPOT model. Testing: Methods describe 100 repeated 80/20 random train/test splits and 5-fold model selection within training. This is internal validation on one reused cohort; the paper does not establish external diagnostic performance.. AutoML was applied to plasma metabolomics/lipidomics from 106 ME/CFS cases and 91 controls; TPOT had the highest reported internal AUC (92.1%) and SHAP-ranked candidate metabolites. Source affiliation was not stated in the reviewed case checks and was unavailable in the local bibliographic cache.

Technology: TPOT, Auto-Sklearn and H2O AutoML searched pipelines on 888 metabolite/lipid features; SHAP was applied to the selected TPOT model.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
TPOT, Auto-Sklearn and H2O AutoML searched pipelines on 888 metabolite/lipid features; SHAP was applied to the selected TPOT model.
Test and result
Methods describe 100 repeated 80/20 random train/test splits and 5-fold model selection within training. This is internal validation on one reused cohort; the paper does not establish external diagnostic performance.
Limitation / still unknown
Generalizability beyond the reported study population, data, and protocol was not established in the reviewed material.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://www.mdpi.com/2075-4418/15/21/2755/pdf

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.