Degan Hao specializes in vision-language models in health care. In his current role at the School of Health and Rehabilitation Sciences (SHRS), he maintains the Rehabilitation Datamart With Informatics Infrastructure for Research (ReDWINE), where he is responsible for developing and managing data infrastructure to support rehabilitation research. During his PhD, Hao studied trustworthy artificial intelligence and its applications in medicine, such as computer aided diagnosis and survival prediction from electronic health records and/or medical images.
Departments
Department of Health Information Management
Education & Training
- Doctor of Philosophy in Intelligent Systems, University of Pittsburgh
- Master of Science in Information Science, University of Pittsburgh
- Bachelor of Science in Applied Physics, Beijing Institute of Technology
Representative Publications
- Hao, Degan, et al. "Inaccurate labels in weakly-supervised deep learning: Automatic identification and correction and their impact on classification performance." IEEE journal of biomedical and health informatics 24.9 (2020): 2701-2710.
- Hao, Degan, et al. "Identifying prognostic markers from clinical, radiomics, and deep learning imaging features for gastric cancer survival prediction." Frontiers in oncology 11 (2022): 725889.
- Hao, Degan, et al. "A self-training teacher-student model with an automatic label grader for abdominal skeletal muscle segmentation." Artificial Intelligence in Medicine 132 (2022): 102366.
Research Interests
- Generative Artificial Intelligence