Related Experiment Video
Updated: Sep 9, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
DeepGut: A collaborative multimodal large language model framework for digestive disease assisted diagnosis and
Xiao-Han Wan1, Mei-Xia Liu1, Yan Zhang1
1Department of Gastroenterology, Qilu Hospital of Shandong University, Jinan 250012, Shandong Province, China.
A new multimodal large language model (LLM) framework, DeepGut, enhances diagnostic accuracy for gastrointestinal diseases by integrating diverse patient data. This AI tool offers improved diagnostic and treatment recommendations, surpassing single-modality systems.
Area of Science:
- Artificial Intelligence in Medicine
- Digestive Disease Diagnostics
- Clinical Decision Support Systems
Background:
- Gastrointestinal diseases present complex diagnostic challenges requiring integration of varied patient data.
- Current AI diagnostic tools often rely on single data types, leading to incomplete recommendations and potential risks.
- Physicians need advanced tools to synthesize medical history, lab results, and imaging for accurate diagnosis.
Purpose of the Study:
- To develop and evaluate a collaborative multimodal large language model (LLM) framework for improved clinical decision-making in digestive diseases.
- To create an AI system capable of integrating diverse data sources for comprehensive diagnostic support.
- To assess the performance and reliability of a novel multimodal LLM in assisting physicians with gastrointestinal diagnoses.
Main Methods:
- Developed DeepGut, a four-tiered collaborative multimodal LLM framework integrating four large models.
- Implemented sequential processing for multimodal information extraction, logical chain construction, and diagnostic/treatment suggestion generation.
- Evaluated the framework using objective metrics for reliability and comprehensiveness, alongside subjective expert assessments.
Main Results:
- DeepGut achieved high performance: 97.8% diagnostic accuracy, 93.9% diagnostic completeness, 95.2% treatment plan accuracy, and 98.0% treatment plan completeness.
- The multimodal LLM collaboration significantly outperformed single-modal AI diagnostic tools.
- Expert reviewers praised the completeness, relevance, and logical coherence of the AI-generated outputs.
Conclusions:
- The DeepGut framework successfully integrates multimodal diagnostic data for enhanced AI-assisted clinical decision-making in digestive diseases.
- Multimodal LLM collaboration demonstrates significant potential for advancing artificial intelligence applications in healthcare.
- This approach opens new avenues for utilizing AI to support physicians in complex diagnostic scenarios.
Related Concept Videos
Inflammatory Bowel Disease III: Diagnostic Studies and Management I-Nutritional Therapy
Diagnostic studies
A colonoscopy is the definitive screening test, distinguishing ulcerative colitis from other colon diseases with similar symptoms. During a colonoscopy test, inflamed mucosa with exudate ulcerations can be observed, and biopsies are taken to determine the histologic characteristics of the...
Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy
Radionuclide Testing
Radionuclide testing is a sophisticated medical technique for assessing gastrointestinal motility. It focuses on gastric emptying and colonic transit time. Radioactive markers track the movement of food through the digestive system, providing insights into gastrointestinal disorders.
In gastric emptying studies, a meal's liquid and...
Chronic Pancreatitis II: Collaborative Care
Assessment:
Gastrointestinal Motility Disorders
Chronic Bowel Disorders: Introduction
Irritable Bowel Syndrome (IBS) is a common disorder affecting the gastrointestinal tract. The distinctive feature is recurrent abdominal pain associated with altered bowel movements, manifesting as constipation, diarrhea, or fluctuating between both. The...
Peptic Ulcer Disease III: Clinical Manifestations and Diagnostic Studies
Few clinical manifestations differentiate gastric ulcers from duodenal ulcers. Distinctions in the location, timing, and pain relief are crucial for healthcare providers in differentiating between gastric and duodenal ulcers during clinical assessments.

