The field of clinical decision support systems is moving towards the integration of multimodal data and the use of large language models to improve patient state representation and disease diagnosis. Researchers are exploring the application of reinforcement learning and explainable AI techniques to enable more accurate and trustworthy predictions. Notable papers in this area include MORE-CLEAR, which leverages pre-trained language models to extract rich semantic representations from clinical notes, and TT-XAI, which improves classification performance and interpretability through domain-aware keyword distillation and reasoning with large language models. Other noteworthy papers include A Chain of Diagnosis Framework, which generates accurate and explainable radiology reports, and Improving ARDS Diagnosis Through Context-Aware Concept Bottleneck Models, which incorporates contextual information from clinical notes to improve disease classification.
Advances in Clinical Decision Support Systems
Sources
MORE-CLEAR: Multimodal Offline Reinforcement learning for Clinical notes Leveraged Enhanced State Representation
TT-XAI: Trustworthy Clinical Text Explanations via Keyword Distillation and LLM Reasoning
Weakly Supervised Fine-grained Span-Level Framework for Chinese Radiology Report Quality Assurance
A Chain of Diagnosis Framework for Accurate and Explainable Radiology Report Generation
Improving ARDS Diagnosis Through Context-Aware Concept Bottleneck Models
Interpretable Machine Learning Model for Early Prediction of Acute Kidney Injury in Critically Ill Patients with Cirrhosis: A Retrospective Study