Researchers have developed a multimodal large language model (LLM) system designed to extract information from scanned cognitive and behavioral assessments, which often suffer from handwriting and scanning artifacts. The system uses a modular approach with a form classifier and a score extractor, incorporating a human-in-the-loop design to improve accuracy and reduce manual review. This LLM-based solution demonstrated high accuracy rates, with end-to-end accuracy reaching 88% for cognitive assessments and 97.5% for the NICHQ Vanderbilt Assessment, significantly reducing processing time and costs compared to manual methods. AI
IMPACT This system offers a scalable and cost-efficient method for structuring clinical data, potentially improving decision support and reducing administrative overhead in healthcare.
RANK_REASON The cluster describes a research paper detailing a novel system for information extraction using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →