Institute of Information Science, Academia Sinica

Hospitalizations account for more than 30% of the 2 trillion annual cost of healthcare in the United States. Around 20% of all hospital admissions occur within 30 days of a previous discharge and 3 out of 20 readmissions are considered preventable. Identifying patients at the higher risk of readmission can guide quality patient care and efficient resource utilization. The task of readmission prediction requires understanding the interplay between multitude of complex factors that cause readmission and appropriate adaptation of advanced analytical models to effectively predict readmissions; added to the complexity is the existence of large volume of noisy data with significant missing values. Our team applies data mining techniques in predicting 30-day hospital readmission risk for heart failure patients. Our proposed solutions involve understanding and exploring complex real world data, applying and appropriately adapting the state-of-the-art predictive modeling techniques, as well as proposing scalable implementation of the solutions to ensure efficiency.

Si-Chi obtained her Ph.D. at the University of Iowa, in Informatics –Information Science. Her research interests include the areas of knowledge discovery, healthcare analytics, and quantitative analysis of information. She was a co-chair of Workshop on Hospital Readmission Prediction and Clinical Risk Management (HRPCRM 2013) held in conjunction with the IEEE International Conference on Healthcare Informatics 2013 (ICHI 2013). Si-Chi currently works as a Research Associate for Center for Web and Data Science within the Institute of Technology at the University of Washington - Tacoma.