Association Rule Mining of Interdepartmental ICD-Coded Transitions
P. Vatiwutipong, J. Tansue, P. Anantapakorn, T. Juengkijthanawat, W. Pansiritanachot, N. Yodrabum, T. Noraset
Ongoing
XERUS
Explainable AI Research for Understandable Systems
At XERUS, we aim to develop machine learning models that provide meaningful explanations and insights into data behavior, enabling users to better understand, trust, and effectively apply these models in high-stakes healthcare settings.
Research Crew
Projects
xMICD: Explainable Representation of Multiple ICD Codes
P. Vatiwutipong, K. Keeratisiwakul, W. Pansiritanachot, M. N. Wright, A. P. K. V. Truong, N. Yodrabum, T. Noraset
SeqBoost: A Sequential Explainable Model for Predicting ED Revisits within 72 Hours
P. Vatiwutipong, T. Noraset · BMC Medical Informatics and Decision Making, 2026
Collaborations
Multi-Wave Data Representations for Prediction in Longitudinal Healthcare Cohort Data
In collaboration with Harbour.Space Institute of Technology @ UTCC
Conference Talk · The 18th International Conference on Information Technology and Electrical Engineering (ICITEE 2026) · Lombok, Indonesia
Transferability of Cough Audio-Based Tuberculosis Screening Models to Thai Smartphone-Based Clinical Recordings
In collaboration with Faculty of Medicine Siriraj Hospital, Mahidol University
Physics-Informed Reinforcement Learning for Decision Support on Continuous Renal Replacement Therapy Discontinuation and Cost-Utility Analysis
In collaboration with Faculty of Medicine, Khon Kaen University
Multicenter Analysis of Emergency Department Utilization Patterns to Develop Models for Crowding Management, Resource Allocation, and Workforce Planning
In collaboration with Faculty of Medicine, Chiang Mai University