Enhancing Healthcare with WBAN and Digital Twins: A Machine Learning Approach for Predictive Health Monitoring

Strategic Insights -

A new breakthrough in artificial intelligence and machine learning has been achieved by researchers from Manipal Academy of Higher Education, who have successfully integrated digital twins with Wireless Body Area Networks (WBAN) for predictive health monitoring. The study uses machine learning algorithms to process data from WBAN sensors, enabling proactive healthcare interventions. The researchers assessed several machine learning models, including Logistic Regression, Support Vector Classifier, and Random Forest, and found that the Random Forest model scored highest in accuracy, precision, recall, F1 score, ROC AUC score, and cross-validation accuracy.

Key Takeaways:

  • Researchers from Manipal Academy of Higher Education have developed a machine learning approach for predictive health monitoring using WBAN and digital twins.
  • The study uses machine learning algorithms to process data from WBAN sensors, enabling proactive healthcare interventions.
  • The Random Forest model scored highest in accuracy, precision, recall, F1 score, ROC AUC score, and cross-validation accuracy among the evaluated models.
  • The XGBoost and Support Vector Classifier models also performed strongly, with GB, Ba, ET, and AB ranking high in efficiency.
  • Integrating digital twins with these models offers an innovative framework to improve healthcare efficiency and enable real-time simulation and accurate forecasting of patient outcomes.
  • The study was conducted by researchers Rishit Mahapatra, Deepak Sethi, and Kaushik Mishra.
  • The paper "Enhancing Healthcare With WBAN and Digital Twins: A Machine Learning Approach for Predictive Health Monitoring" was published in IEEE Access in July 2025.

Statistics:

  • The Random Forest model achieved an accuracy of 97%, precision of 98%, recall of 97%, F1 score of 98%, ROC AUC score of 97%, and cross-validation accuracy of 97%.
  • The XGBoost model scored high across all measurements, with efficiency scores in the mid-90s.
  • The study used a range of machine learning algorithms, including Logistic Regression, Support Vector Classifier, and Random Forest.
  • The WBAN sensors were used to collect data on glucose, blood pressure, body temperature, and other parameters.
  • The digital twins used in the study were virtual representations of the physical body.

Sources:

  • Manipal Academy of Higher Education Researchers Highlight Recent Research in Machine Learning (Enhancing Healthcare With WBAN and Digital Twins: A Machine Learning Approach for Predictive Health Monitoring). Journal of Engineering. July 21, 2025; p 1393.
  • Enhancing Healthcare With WBAN and Digital Twins: A Machine Learning Approach for Predictive Health Monitoring. IEEE Access, 2025, 13():113305-113317. (IEEE Access - http://ieeexplore.ieee.org/servlet/opac?punumber=6287639)
  • Rishit Mahapatra, Deepak Sethi, and Kaushik Mishra. Manipal Institute of Technology Bengaluru, Manipal Academy of Higher Education, Manipal, India.