Prof. Zijun Yao from University of Kansas will visit SAIL and give a CSCE colloquium presentation.
Seminar Date: Wednesday, April 10, 2024 Time: 10:45am – 12:00pm Location: JBHT 239
Seminar Title: Enhancing Personalization, Transparency, and Trustworthiness in Longitudinal Healthcare Recommender Systems
Abstract: For care of the chronic disease (e.g., depression, diabetes, hypertension), it is critical to identify the effective treatment pathway which aims to promptly switch prescriptions following the change of patient state and disease progression. However, this task is challenging because the optimal treatment pathway for each patient needs to be personalized due to the significant heterogeneity among individuals. Therefore, it is naturally promising to investigate how to use abundant electronic health records (EHRs) for effective and safe treatment recommendations. In this talk, we will explore multiple research efforts on developing personalized, transparent, and trustworthy algorithms tailored to healthcare scenarios. From a research point of view, we will address the unique challenges in mining EHR data, and illustrate how we develop frameworks of ontological paths, graphical intents, or adversarial attacks to meet our objectives. By the conclusion of this talk, attendees will have a deeper insight into the transformative impact of data science in healthcare, and the opportunities within this dynamic field.
Short Bio: Zijun Yao joined Electrical Engineering & Computer Science Department at The University of Kansas as an Assistant Professor in 2021. Prior to that, he received his Ph.D. in Information Technology from Rutgers, the State University of New Jersey in 2018, and worked as a Research Staff Member in AI for healthcare at IBM TJ Watson Research Center. His general interests lie in data mining and machine learning applications. Particularly, His research aims to develop personalized, transparent, and trustworthy machine learning frameworks for real-world healthcare decision-support systems, such as treatment recommendation, disease progression modeling, and health event prediction. His works have been published in premier journals and top-tier conferences including IEEE TKDE, ACM TOIS, ACM KDD, IJCAI, and ACM WSDM.
Recent Comments