The field of clinical decision support is rapidly advancing with the integration of large language models (LLMs) and other artificial intelligence (AI) technologies. Recent developments have focused on improving the accuracy and safety of AI-assisted decision-making in healthcare, with a particular emphasis on addressing the challenges of data quality, clinical relevance, and patient-centered care. Notable advancements include the development of retrieval-augmented generation frameworks, expert-guided clinical text augmentation, and hierarchical error correction systems. These innovations have the potential to enhance the reliability and effectiveness of clinical decision support systems, ultimately leading to better patient outcomes. Noteworthy papers include LLM-Based Support for Diabetes Diagnosis, which evaluates the use of GPT-5 for diabetes diagnosis and demonstrates strong alignment with clinical criteria. Expert-guided Clinical Text Augmentation via Query-Based Model Collaboration is also noteworthy, as it proposes a novel framework for integrating expert-level domain knowledge into the augmentation process, resulting in improved safety and reduced factual errors.
Advancements in AI-Assisted Clinical Decision Support
Sources
LLM-Based Support for Diabetes Diagnosis: Opportunities, Scenarios, and Challenges with GPT-5
Expert-guided Clinical Text Augmentation via Query-Based Model Collaboration
Taxonomy of Comprehensive Safety for Clinical Agents
Retrieval-Augmented Guardrails for AI-Drafted Patient-Portal Messages: Error Taxonomy Construction and Large-Scale Evaluation
PAME-AI: Patient Messaging Creation and Optimization using Agentic AI
Hierarchical Error Correction for Large Language Models: A Systematic Framework for Domain-Specific AI Quality Enhancement
CliniBench: A Clinical Outcome Prediction Benchmark for Generative and Encoder-Based Language Models
Beyond the Algorithm: A Field Guide to Deploying AI Agents in Clinical Practice
LLM-Assisted Emergency Triage Benchmark: Bridging Hospital-Rich and MCI-Like Field Simulation
TVS Sidekick: Challenges and Practical Insights from Deploying Large Language Models in the Enterprise
DexBench: Benchmarking LLMs for Personalized Decision Making in Diabetes Management
Retrieval-Augmented Generation for Electrocardiogram-Language Models
Automated Evaluation can Distinguish the Good and Bad AI Responses to Patient Questions about Hospitalization
EMR-AGENT: Automating Cohort and Feature Extraction from EMR Databases
Context Matters: Comparison of commercial large language tools in veterinary medicine
Retrieval-Augmented Framework for LLM-Based Clinical Decision Support
A Locally Executable AI System for Improving Preoperative Patient Communication: A Multi-Domain Clinical Evaluation