What question did this study set out to answer?

This research aims to use AI to differentiate chronic fatigue syndrome patients from healthy controls based on autonomic measurements.

January 10, 2026Journal of Translational Medicine0 citationsOpen Access

Diagnosis of chronic fatigue syndrome using beat-to-beat autonomic measurements

Q: What does this research mean for the field?

An AI classifier achieved 89% accuracy in distinguishing Chronic Fatigue Syndrome patients from healthy controls using beat-to-beat autonomic measurements. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.NEUTRAL.

SKSławomir KujawskiNicolaus Copernicus University HTHanna TabiszNicolaus Copernicus University KMKarl J. MortenJohn Radcliffe Hospital

Key Result

The AI classifier achieved 89% accuracy in distinguishing Chronic Fatigue Syndrome patients from healthy controls using beat-to-beat autonomic measurements.

Key Points

This research aims to use AI to differentiate chronic fatigue syndrome patients from healthy controls based on autonomic measurements.
Included 112 chronic fatigue syndrome patients and 61 healthy controls.
Measured heart rate, R-to-R interval, diastolic blood pressure, stroke volume, and stroke volume index.
Applied a sequential learning approach with a Transformer model followed by an XGBoost classifier.
Assessed classifier performance using accuracy, Matthews correlation coefficient, and ROC AUC.
Classifier achieved a subject-level accuracy of 0.89 and an AUC of 1.00.
Lower heart rate variability and raw R-to-R intervals indicated higher likelihood of chronic fatigue syndrome.
Higher diastolic blood pressure differences were associated with chronic fatigue syndrome classification.
Lower stroke volume difference suggested less effective cardiac function in CFS patients.

Structured PICO

Does an AI pipeline using beat-to-beat autonomic measurements accurately differentiate patients with Chronic Fatigue Syndrome from healthy controls?

Population

112 patients with Chronic Fatigue Syndrome (CFS) meeting Fukuda criteria and 61 healthy controls (HCs), aged 25 to 65 years.

Intervention

Artificial intelligence (AI) pipeline combining a Transformer neural network and XGBoost classifier using beat-to-beat cardiovascular and autonomic parameters (HR, HF RRI, dBP, SV, SV/FFM) measured at rest by Task Force Monitor.

Comparator

Healthy controls (HCs) evaluated with the same beat-to-beat cardiovascular and autonomic measurements.

Outcome

Diagnostic classification performance measured by subject-level accuracy, Matthews correlation coefficient (MCC), and Area Under the Receiver Operating Characteristic Curve (ROC AUC).surrogate

An AI-driven classifier utilizing beat-to-beat autonomic and cardiovascular measurements can accurately distinguish patients with Chronic Fatigue Syndrome from healthy controls, offering a potential objective diagnostic tool.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Background An artificial intelligence (AI) pipeline was used to differentiate patients suffering from Chronic Fatigue Syndrome (CFS) from healthy controls (HC) based on high-frequency, large-scale data obtained using beat-to-beat measurement of the autonomic nervous system (ANS) and cardiovascular function. Methods This prospective, case-control study included a cohort of 112 CFS patients and 61 HCs examined. Heart rate (HR), high-frequency R-to-R interval (HF RRI), diastolic blood pressure (dBP), stroke volume (SV), and SV index (SV/FFM) were measured using the Task Force Monitor. A novel sequential learning approach was applied: first, a Transformer model was trained, followed by an XGBoost classifier that learned from the errors of the Transformer. Matthews correlation coefficient (MCC), accuracy, and Area Under the Receiver Operating Characteristic Curve (ROC AUC) were assessed. Model classifications were explained globally. Results The applied classifier achieved a subject-level accuracy of 0.89, an MCC of 0.79, and an AUC of 1.00. Lower values of beat-to-beat difference in HR and raw HF RRI (indicating reduced cardiac vagal tone) and higher values of dBP difference (more beat-to-beat increases, indicating higher sympathetic vascular tone) were related to being more likely classified as CFS patients. Low values of SV difference and low values of SV/FFM (both indicating less effective cardiac hemodynamics) were related to being more likely classified as CFS patients. Conclusions The AI-driven classifier demonstrates remarkable proficiency in distinguishing between patients with CFS and HC. By leveraging this automated pipeline, beat-to-beat measurements of the ANS can significantly enhance the objective assessment of CFS diagnosis.

Ask AI

Helpful

Bookmark

View Full Paper