Papers with automatic diagnosis generation
DictLLM: Harnessing Key-Value Data Structures with Large Language Models for Enhanced Medical Diagnostics (2024.findings-acl)
Copied to clipboard
| Challenge: | Structured data processing is a complex and complex process. |
| Approach: | They propose a framework that captures heterogeneity of structured data using large language models . they propose group positional encoding, hierarchical attention bias and optimal transport alignment layer . |
| Outcome: | The proposed framework outperforms baseline methods and few-shot GPT-4 on a medical lab report dataset. |
EMGLLM: Data-to-Text Alignment for Electromyogram Diagnosis Generation with Medical Numerical Data Encoding (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing Large Language Models struggle to interpret EMG tables . EMGLLM is a data-to-text model for medical examination tables based on electrical signals . |
| Approach: | They propose a data-to-text model that aligns EMG data into word embeddings that reflect health degree. |
| Outcome: | The proposed model outperforms baseline models in understanding EMG tables and generating high-quality diagnoses. |