Research

Research Interests

Data Science, Health Informatics
Predictive Modeling: Feature Selection, Supervised Machine Learning, Applied Statistics
Knowledge Extraction and Representation: Semantic Web and Ontologies, Applied Natural Language Processing
Quantification of Data Quality
AI Agents and Intelligent Systems
AI-Powered Software and Toolkit Development

Description

To me, data science is a challenge-driven field. I am interested in identifying research challenges and applying cutting-edge technologies or developing new methods to solve real-world problems. I am particularly interested in healthcare-related challenges, especially in translating healthcare data into knowledge and improving the generalizability and robustness of health informatics approaches. Data science is often viewed as the intersection of statistics, computer science, and domain knowledge. Building on my formal academic training in computer science and the statistical mindset I have further strengthened as a statistics faculty member, my next goal is to dive deeper into specific disease areas and conduct research with practical impact.

Selected Journal Publications

Methodology:

Shi, J., Zhang, J., & Ge, Y. (2019). CASMI—An Entropic Feature Selection Method in Turing’s Perspective. Entropy, 21(12), 1179. https://doi.org/10.3390/e21121179

Zhang, J., & Shi, J. (2024). Nonparametric clustering of discrete probability distributions with generalized Shannon’s entropy and heatmap. Statistics & Probability Letters, 208, 110070. https://doi.org/10.1016/j.spl.2024.110070

Collaborative Research:

Guo, Y., & Shi, J. (2024). Factors associated with psychological wellbeing in home care older adults with Alzheimer’s disease: A longitudinal analysis. Journal of Applied Gerontology, 43(8), 1069-1081. https://doi.org/10.1177/07334648241231406

Alabbas, M., Shi, J., Guo, Y., Wu, H., Oshobu, I., Castano, M., ... & Sims, O. T. (2025). Prevalence and Trends in Active Smoking Among Adults Living with HCV in the US over the Last Decade: A Population-Level Analysis. Journal of Clinical Medicine, 14(18), 6671. https://doi.org/10.3390/jcm14186671

Liu, L., May, N. S., Hou, Y., Shi, J., Gracely, E. J., Frank, A. L., & Eisen, H. J. (2026). The US diabetes belt and factors explaining the excess risk: Multifactorial modeling and machine learning analysis. Primary care diabetes, 20(1), 99-105. https://doi.org/10.1016/j.pcd.2025.12.001

Innovation for Development:

Shi, J., Zheng, M., Yao, L., & Ge, Y. (2018). Developing a healthcare dataset information resource (DIR) based on Semantic Web. BMC medical genomics, 11(Suppl 5), 102. https://doi.org/10.1186/s12920-018-0411-5

Click here to explore my Google Scholar profile.

R Packages

"CASMI" on CRAN: https://cran.r-project.org/package=CASMI (maintainer)

"EntropicStatistics" on CRAN: https://cran.r-project.org/package=EntropicStatistics (co-author)

Grant History

External:

Data Science Core, Mississippi INBRE (5-year, subaward PI)
Developing Innovative Methods for Rapid Characterization of PVS and NVS Function at the Neural Level (Co-PI)
Natural History and Machine Learning-Based Predictive Modeling of PBC-Related Osteoporosis (Consultant)
Risk Stratification and Prognosis of Metabolic Bone Disease in Primary Biliary Cholangitis (Consultant)
A Combined Propensity Score Matching and Machine Learning Approach to Demonstrate the Safety and Efficacy of Statins in Patients with Decompensated Cirrhosis (Consultant)

MSU Internal:

Developing a Machine Learning Tool for Mining Factor Combinations (PI)
Developing Automatic Pipelines and Algorithms to Enable Rapid Learning of COVID-19 Publications (PI)
Mapping Adolescent Emotional Reactivity and Risk for Depression and Anxiety Using Fast Periodic Visual Stimulation (Co-PI)

Conference Activities

Peer-reviewed conference papers/abstracts: 9

Google Sites

Report abuse