Utilizing Machine Learning to Identify Factors Associated with Restless Legs Syndrome and Develop a Classification Model in Patients with End-Stage Renal Disease - Scorecard - MDSpire

Utilizing Machine Learning to Identify Factors Associated with Restless Legs Syndrome and Develop a Classification Model in Patients with End-Stage Renal Disease

  • By

  • Tao Yuan

  • Na Sun

  • Lanbo Teng

  • Chuhan Xu

  • Yunyan Wang

  • Wenyu Zhang

  • Wenxiu Chang

  • April 29, 2026

  • 0 min

Share

Clinical Scorecard: Utilizing Machine Learning to Identify Factors Associated with Restless Legs Syndrome and Develop a Classification Model in Patients with End-Stage Renal Disease

At a Glance

CategoryDetail
ConditionRestless Legs Syndrome (RLS)
Key MechanismsUremic toxin accumulation, iron deficiency, dopaminergic dysfunction, chronic inflammation, peripheral neuropathy
Target PopulationPatients with End-Stage Renal Disease (ESRD) undergoing dialysis
Care SettingDialysis centers

Key Highlights

  • RLS prevalence in ESRD patients ranges from 20% to 65%
  • Developed a machine learning model using SVM with AUC of 0.791
  • Five key variables identified: β2-microglobulin, hemoglobin, diabetes, coronary heart disease, alcohol consumption
  • SHAP analysis used for model interpretability
  • Model requires prospective validation in multi-center cohorts

Guideline-Based Recommendations

Diagnosis

  • Fulfillment of five essential criteria established by the IRLSSG for RLS diagnosis

Management

  • Optimization of dialysis adequacy, iron supplementation, dopaminergic therapy, lifestyle modifications

Monitoring & Follow-up

  • Regular screening for RLS in dialysis patients to improve quality of life

Risks

  • Increased cardiovascular morbidity and mortality associated with RLS in ESRD

Patient & Prescribing Data

ESRD patients undergoing hemodialysis or peritoneal dialysis

Machine learning models can enhance screening and inform clinical decision-making

Clinical Best Practices

  • Implement routine screening for RLS in ESRD patients
  • Utilize machine learning tools for better risk stratification
  • Incorporate SHAP analysis for understanding patient-specific risk factors

References

Original Source(s)

Utilizing Machine Learning to Identify Factors Associated with Restless Legs Syndrome and Develop a Classification Model in Patients with End-Stage Renal Disease

  • by Tao Yuan, Na Sun, Lanbo Teng, Chuhan Xu, Yunyan Wang, Wenyu Zhang, Wenxiu Chang

  • April 29, 2026

Related Content

Evaluating the psychosocial effects of cancer on sleep quality and mental health in elderly populations

Holistic care in inflammatory bowel disease: is it in REACH?

Detecting isolated REM sleep behavior disorder at home using a lower-back wearable sensor