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

Inductive Reasoning00:59

Inductive Reasoning

59.8K
Inductive reasoning is a form of logical thinking that uses related observations to arrive at a general conclusion. It is uncertain and operates in degrees to which the conclusions are credible. As such, inductive arguments can be weak or strong, rather than valid or invalid, and conclusions can be used to formulate testable, falsifiable hypotheses.
Inductive reasoning is common in descriptive science. A life scientist makes observations and records them. This data can be qualitative or...
59.8K
Genetic Lingo01:11

Genetic Lingo

99.2K
Overview
99.2K
What is Genetic Engineering?00:49

What is Genetic Engineering?

73.1K
Overview
73.1K
Gene Therapy00:59

Gene Therapy

25.1K
Gene therapy is a technique where a gene is inserted into a person’s cells to prevent or treat a serious disease. The added gene may be a healthy version of the gene that is mutated in the patient, or it could be a different gene that inactivates or compensates for the patient’s disease-causing gene. For example, in patients with severe combined immunodeficiency (SCID) due to a mutation in the gene for the enzyme adenosine deaminase, a functioning version of the gene can be...
25.1K
Neural Regulation01:37

Neural Regulation

39.1K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
39.1K
Non-equilibrium in the Cell01:16

Non-equilibrium in the Cell

4.1K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
4.1K

You might also read

Related Articles

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

Sort by
Same author

Linear relationship between the Framingham Steatosis Index (FSI) and colorectal cancer (1999-2018): A nationwide cross-sectional study based on NHANES.

Medicine·2026
Same author

Application of Organic Small-Molecule Fluorescent Probes for NAD(P)H Imaging and Detection.

Chemistry, an Asian journal·2026
Same author

Endoscopic transcervical mediastinal drainage for treating descending necrotizing mediastinitis.

BMC surgery·2026
Same author

Rectal endometriosis mimicking rectal cancer.

Gastroenterologia y hepatologia·2026
Same author

Determination of cross-sections for the <sup>130</sup>Xe(n,p)<sup>130</sup>I reaction in the neutron energy range of 13-15 MeV using isotope targets.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2026
Same author

AI-Assisted Systematic Literature Review of the Economic Burden of Pneumococcal Disease: Development and Validation Study.

JMIR AI·2026

Related Experiment Video

Updated: Jun 23, 2026

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

Enhancing systematic literature reviews with generative artificial intelligence: development, applications, and

Ying Li1, Surabhi Datta2, Majid Rastegar-Mojarad2

  • 1Regeneron Pharmaceuticals, Inc., Tarrytown, NY 10591, United States.

Journal of the American Medical Informatics Association : JAMIA
|March 4, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces an AI-assisted system for systematic literature reviews (SLRs) in health technology assessment (HTA). The large language model (LLM) system streamlines reviews, reducing time and costs while improving evidence generation.

Keywords:
GPT-4human-in-the loop AIinformation extractionlarge language modelsystematic literature review

Related Experiment Videos

Last Updated: Jun 23, 2026

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

Area of Science:

  • Artificial Intelligence in Health Technology Assessment
  • Systematic Literature Review Automation
  • Large Language Model Applications

Background:

  • Systematic literature reviews (SLRs) are crucial for health technology assessment (HTA) but are time-consuming and resource-intensive.
  • Current SLR methods face challenges in efficiency and potential for human error.
  • The integration of advanced AI, specifically large language models (LLMs), offers a potential solution to these challenges.

Purpose of the Study:

  • To develop and validate an LLM-assisted system for conducting SLRs in HTA submissions.
  • To evaluate the performance of the LLM system in abstract screening, rationale generation, and data extraction.
  • To assess the system's ability to streamline the SLR process and enhance evidence generation.

Main Methods:

  • A five-module system was developed, including literature search setup, protocol setup (PICOS criteria), LLM-assisted abstract screening, LLM-assisted data extraction, and data summarization.
  • A human-in-the-loop design was implemented for real-time adjustment of PICOS criteria based on reviewer-LLM disagreements.
  • The system was evaluated using four datasets, including relapsed and refractory multiple myeloma (RRMM) and advanced melanoma.

Main Results:

  • The LLM system demonstrated high performance in abstract screening, with an average sensitivity of 90% and an F1 score of 82.
  • The system achieved high accuracy in providing exclusion rationales (up to 97%) and a strong F1 score of 93 for data extraction.
  • Substantial agreement was observed between human reviewers and LLM-based results (Cohen's κ = 0.71).

Conclusions:

  • The developed LLM-assisted SLR system shows significant potential for streamlining HTA submissions.
  • The system's human-in-the-loop design and reliance on GPT-4's in-context learning eliminate the need for manually annotated training data.
  • This AI-driven approach can reduce time, cost, and human error in SLRs, thereby improving evidence generation for HTA.