My lab’s research focuses on FAIR and explainable machine learning (ML), systems informatics (SI) and their application to health outcomes, decision support, quality of life, and health equity. The ever-increasing volumes of health data, such as electronic medical records, patient-reported outcomes, wearable sensor data, etc., created a potential of facilitating cancer research and translational oncology to improve clinical decision-making and reasoning. ML approaches have been proposed to unravel potential relationship among the inputs, outputs, and system status of complex systems from them. However, using ML approaches to integrate, extract, and interpret these health data for the improvement of cancer prevention and care is still challenging. It is important to develop FAIR and explainable ML approaches for this goal by bringing technological, biomedical, and behavioral scientists together. Therefore, my lab’s research interests include, but not limited to, the following aspects:

  • Biomedical missing data analysis 
  • FAIR and explainable outcomes prediction models 
  • Bias control and causal inference for outcomes analysis 
  • Human-in-the-loop mechanisms to improve prediction models' accuracy and credibility 
  • Online human-machine interface for treatment planning and symptom management
  • Analytical and simulation methods for community based cancer prevention
  • Systems approach to eliminate/reduce health disparities

Also, my lab intends to collaborate with scientists in other clinical and scientific departments and translate our research to improve cancer prevention and cure.