Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Drug Absorption: Factors Affecting GI Absorption01:19

Drug Absorption: Factors Affecting GI Absorption

3.8K
The process of oral drug absorption can be influenced by several factors. Weakly acidic drugs tend to be absorbed more readily from the stomach due to their nonionized state. However, absorption may be less efficient in the upper intestine, where drugs are often ionized. Interestingly, despite the stomach's apparent advantage for drug absorption, its mucous layer can hinder diffusion. Its surface area is also smaller than the intestine's, which can further slow down the absorption rate.
3.8K
Drug Absorption: Overview01:17

Drug Absorption: Overview

509
The process of drug absorption signifies the transition of a drug from its site of administration into the plasma. This process is influenced by various factors, including the route of administration, the anatomy of the absorption site, the mechanism of absorption, gut motility, and the drug's physicochemical properties.
When drugs are injected intravenously, they directly enter the systemic circulation. Alternatively, orally administered drugs navigate through the gastrointestinal (GI)...
509
Methods for Studying Drug Absorption: In vitro01:16

Methods for Studying Drug Absorption: In vitro

199
In vitro experiments are crucial for understanding the transport and absorption of drugs through biological materials. These studies employ varied methods such as the diffusion cell method, the everted sac technique, and the everted ring technique.
The diffusion cell method uses a two-compartment cell, including a donor compartment with the drug solution, which simulates the environment where the drug is applied, and a receptor compartment with a buffer solution, which simulates the environment...
199
Methods for Studying Drug Absorption: In situ01:09

Methods for Studying Drug Absorption: In situ

201
In situ experiments, such as the Doluisio method and Single-Pass Perfusion technique, provide critical insights into drug uptake by simulating in vivo conditions for drug absorption.
The Doluisio method involves perfusing a prepared segment of a rat's small intestine with a solution of radiolabeled drug and a non-absorbable marker. This helps to differentiate between absorbed and non-absorbed drug concentrations. The intestinal segment is connected at both ends using tubing and syringes,...
201
Prescription, Nonprescription and Orphan Drugs01:02

Prescription, Nonprescription and Orphan Drugs

686
Prescription drugs require a prescription from a medical practitioner and can only be obtained from a pharmacy. They have many applications, including treating pain, anxiety, and hypertension.
The misuse and addiction to prescription drugs is a growing problem that can affect people of all age groups, specifically teenagers. This can happen when prescription medications are used in ways not intended by the prescriber, such as taking someone else's prescription or using medication for...
686
Drug Biotransformation: Overview01:16

Drug Biotransformation: Overview

2.3K
Pharmaceutical substances known as xenobiotics are predominantly lipophilic and nonionized. This enables them to permeate lipid bilayers, such as cell membranes, and interact with intracellular target receptors. Lipophilic drugs have an advantage in crossing biological barriers and reaching their intended sites of action. However, lipophilic drugs often have a restricted capacity for renal expulsion or elimination from the body. When these drugs enter the kidneys and undergo glomerular...
2.3K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine.

Findings of ACL. ACL·2026
Same author

Low Back Pain in Chinese Adults Aged 45 Years and Older: Trends, Drivers, and Projections, 1990-2040.

Healthcare (Basel, Switzerland)·2026
Same author

Benchmarking information extraction of physical activity from electronic health record with large language models: an natural language processing pipeline and comparative evaluation.

Journal of the American Medical Informatics Association : JAMIA·2026
Same author

Let large language models judge each other: multi-agent peer-reviewed reasoning for medical question answering.

Journal of the American Medical Informatics Association : JAMIA·2026
Same author

Molecular Dynamics Investigation of CSH/SiO<sub>2</sub> Interface Degradation in High-Temperature and Water-Rich Environments.

Materials (Basel, Switzerland)·2026
Same author

<i>OrgaCast</i>: A Trustworthy Spatiotemporal Diffusion Model for Fluorescence Organoid Forecasting.

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence·2026

Related Experiment Video

Updated: Jun 3, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

494

RAMIE: retrieval-augmented multi-task information extraction with large language models on dietary supplements.

Zaifu Zhan1, Shuang Zhou2, Mingchen Li2

  • 1Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN 55455, United States.

Journal of the American Medical Informatics Association : JAMIA
|January 11, 2025
PubMed
Summary
This summary is machine-generated.

The retrieval-augmented multi-task information extraction (RAMIE) framework significantly improves extracting dietary supplement (DS) data from clinical records. This advanced LLM approach enhances accuracy and efficiency in analyzing complex health information.

Keywords:
dietary supplementsinstruction fine-tuninglarge language modelmulti-task learningretrieval-augmented generation

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

634

Related Experiment Videos

Last Updated: Jun 3, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

494
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

634

Area of Science:

  • Computational linguistics
  • Biomedical informatics
  • Artificial intelligence in healthcare

Background:

  • Extracting dietary supplement (DS) information from clinical records is crucial for patient safety and research.
  • Existing methods often struggle with the complexity and diversity of DS data within unstructured clinical text.
  • Large language models (LLMs) offer potential but require specialized frameworks for optimal performance in this domain.

Purpose of the Study:

  • To develop and evaluate an advanced multi-task large language model (LLM) framework for extracting diverse dietary supplement (DS) information from clinical records.
  • To enhance the efficiency and accuracy of information extraction tasks, including named entity recognition, relation extraction, triple extraction, and usage classification.
  • To assess the contribution of multi-task learning and retrieval-augmented generation within the proposed framework.

Main Methods:

  • Introduced the retrieval-augmented multi-task information extraction (RAMIE) framework.
  • Employed instruction fine-tuning with task-specific prompts for LLMs.
  • Utilized multi-task training to improve storage efficiency and reduce training costs.
  • Integrated retrieval-augmented generation to leverage similar examples from the training set for enhanced performance.

Main Results:

  • The RAMIE framework demonstrated significant improvements across multiple DS information extraction tasks.
  • Llama2-13B achieved an 87.39 F1 score for named entity recognition and 93.74 for relation extraction.
  • Llama2-7B achieved a 79.45 F1 score for triple extraction (14.26% improvement), and MedAlpaca-7B achieved 93.45 for usage classification.
  • Ablation studies confirmed that retrieval-augmented generation substantially boosted overall accuracy, while multi-task learning improved efficiency.

Conclusions:

  • The RAMIE framework provides substantial improvements for multi-task information extraction of dietary supplement data from clinical records.
  • This framework represents a significant advancement in leveraging LLMs for detailed analysis of health-related information.
  • RAMIE offers a robust solution for enhancing the extraction and utilization of DS information in clinical settings.