A5102019673- Explainable Artificial Intelligence (XAI)
- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare and Education
- Privacy-Preserving Technologies in Data
- Multimodal Machine Learning Applications
- Sepsis Diagnosis and Treatment
- Scientific Computing and Data Management
- Remote Sensing and Land Use
- Human Pose and Action Recognition
- Anomaly Detection Techniques and Applications
- Meta-analysis and systematic reviews
- Blockchain Technology Applications and Security
- Remote-Sensing Image Classification
- Data Quality and Management
- Advanced Image Fusion Techniques
Duke-NUS Medical School
2022-2025
Tianjin University of Technology
2017
Risk scores are widely used for clinical decision making and commonly generated from logistic regression models. Machine-learning-based methods may work well identifying important predictors to create parsimonious scores, but such 'black box' variable selection limits interpretability, importance evaluated a single model can be biased. We propose robust interpretable approach using the recently developed Shapley cloud (ShapleyVIC) that accounts variability in across Our evaluates visualizes...
Machine learning (ML) methods are increasingly used to assess variable importance, but such black box models lack stability when limited in sample sizes, and do not formally indicate non-important factors. The Shapley importance cloud (ShapleyVIC) addresses these limitations by assessing from an ensemble of regression models, which enhances robustness while maintaining interpretability, estimates uncertainty overall test its significance. In a clinical study, ShapleyVIC reasonably identified...