The field of healthcare and biomedical research is witnessing significant advancements with the integration of artificial intelligence (AI) and large language models (LLMs). Recent developments are focused on improving the accuracy and reliability of medical diagnoses, treatment decisions, and patient outcomes. Notably, researchers are exploring the potential of LLMs in generating high-quality medical summaries, constructing knowledge graphs, and developing agent-based frameworks for healthcare infrastructure planning. Furthermore, there is a growing emphasis on evaluating the faithfulness and serendipity of LLM-generated responses in medical contexts. The use of retrieval-augmented generation (RAG) frameworks and multi-agent systems is also being investigated to enhance the performance of LLMs in biomedical reasoning and decision-making tasks. Overall, these innovations have the potential to transform the healthcare landscape by providing more accurate, efficient, and personalized medical services. Noteworthy papers in this area include Faithful Summarization of Consumer Health Queries, MedBuild AI, and CARE-RAG, which demonstrate the effectiveness of AI-driven approaches in improving medical summarization, healthcare infrastructure planning, and clinical assessment and reasoning.
Advancements in AI-Driven Healthcare and Biomedical Research
Sources
Faithful Summarization of Consumer Health Queries: A Cross-Lingual Framework with LLMs
Enhancing Demand-Oriented Regionalization with Agentic AI and Local Heterogeneous Data for Adaptation Planning
AI Agent-Driven Framework for Automated Product Knowledge Graph Construction in E-Commerce
MedBuild AI: An Agent-Based Hybrid Intelligence Framework for Reshaping Agency in Healthcare Infrastructure Planning through Generative Design for Medical Architecture
Assessing LLMs for Serendipity Discovery in Knowledge Graphs: A Case for Drug Repurposing
Auditing Google's AI Overviews and Featured Snippets: A Case Study on Baby Care and Pregnancy
Assessing Automated Fact-Checking for Medical LLM Responses with Knowledge Graphs
MedRule-KG: A Knowledge-Graph--Steered Scaffold for Reliable Mathematical and Biomedical Reasoning
Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrieval
MedDCR: Learning to Design Agentic Workflows for Medical Coding
Automated Construction of Medical Indicator Knowledge Graphs Using Retrieval Augmented Large Language Models
CafeMed: Causal Attention Fusion Enhanced Medication Recommendation
Build AI Assistants using Large Language Models and Agents to Enhance the Engineering Education of Biomechanics
KRAL: Knowledge and Reasoning Augmented Learning for LLM-assisted Clinical Antimicrobial Therapy
CARE-RAG - Clinical Assessment and Reasoning in RAG
Multidimensional Rubric-oriented Reward Model Learning via Geometric Projection Reference Constraints
Beyond Generative AI: World Models for Clinical Prediction, Counterfactuals, and Planning