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

Reliability and Validity01:29

Reliability and Validity

13.8K
Reliability and validity are two important considerations that must be made with any type of data collection. Reliability refers to the ability to consistently produce a given result. In the context of psychological research, this would mean that any instruments or tools used to collect data do so in consistent, reproducible ways.
13.8K
Language01:16

Language

898
Language is a unique communication system that uses words and systematic rules to organize and transmit information. Unlike other forms of communication, which may involve postures, movements, odors, or vocalizations, language relies on symbols and grammar. This makes human communication distinct from that of other species, who also communicate but do not use language in the same way humans do.
Corballis and Suddendorf (2007) and Tomasello and Rakoczy (2003) highlight the role of language in...
898
Psychology as a Science01:13

Psychology as a Science

3.8K
Psychology, as a scientific discipline, aims to understand the mind and behavior through rigorous and systematic methods. The foundation of psychological research is evidence-based, relying heavily on the scientific method to derive and validate knowledge. This structured approach ensures that findings are reliable, valid, and applicable to broader contexts.
The scientific method in psychology involves six critical steps: making observations, formulating hypotheses, conducting tests, analyzing...
3.8K
Components of Language01:24

Components of Language

796
Language, whether spoken, signed, or written, consists of specific components: lexicon and grammar. The lexicon is the vocabulary of a language, comprising its words. Grammar is the set of rules used to convey meaning through the lexicon. For example, English grammar adds “-ed” to most verbs to indicate past tense. Words are formed by combining phonemes, which are the basic sound units of a language. Different languages have different sets of phonemes (e.g., “ah” vs.
796
Language Development01:22

Language Development

877
Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
877
Language and Cognition01:27

Language and Cognition

741
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
741

You might also read

Related Articles

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

Sort by
Same author

NFYB-lncRNA axis resets the tumor microenvironment to promote HCC aggressive progression by a positive feedback loop.

Acta pharmaceutica Sinica. B·2026
Same author

Rainfall Drives Differentiation of Plant Rhizosphere Microbial Communities in Two Different Types of Alpine Wetlands: A Perspective Based on a Carbon-Water Coupling Framework.

Microbial ecology·2026
Same author

Association between hypertension and sepsis-related complications: a retrospective nationwide inpatient sample database cross-sectional study.

BMC infectious diseases·2026
Same author

Methane Flux Responses to Warming and Inundation in the Qinghai Lake Littoral Wetland.

Biology·2026
Same author

Spatial distribution and environmental attributes dataset of China's large-scale data centers in 2024.

Scientific data·2026
Same author

Dscam alternative splicing tunes intestinal immunity and microbiota homeostasis in the Chinese mitten crab.

Fish & shellfish immunology·2026
Same journal

Derivation of functional retinal endothelial cells from human pluripotent stem cells for therapeutics and modelling.

Nature biomedical engineering·2026
Same journal

Engineered circular RNA compatible with complete nucleoside modification and rolling circle translation through a Cap-independent translation enhancer.

Nature biomedical engineering·2026
Same journal

The evolving role of cytokines for CAR-T cell manufacturing and beyond.

Nature biomedical engineering·2026
Same journal

Off‑the‑shelf, engineered non-living stem cell strategy for advancing cellular therapies.

Nature biomedical engineering·2026
Same journal

Engineering stable, off-the-shelf cellular depots.

Nature biomedical engineering·2026
Same journal

Towards clinical-level interpretation of dental panoramic radiography using an instance-guided vision-language model.

Nature biomedical engineering·2026
See all related articles

Related Experiment Video

Updated: Jan 24, 2026

Scaled Anatomical Model Creation of Biomedical Tomographic Imaging Data and Associated Labels for Subsequent Sub-surface Laser Engraving SSLE of Glass Crystals
07:57

Scaled Anatomical Model Creation of Biomedical Tomographic Imaging Data and Associated Labels for Subsequent Sub-surface Laser Engraving SSLE of Glass Crystals

Published on: April 25, 2017

8.7K

Making large language models reliable data science programming copilots for biomedical research.

Zifeng Wang1,2, Benjamin Danek1,2, Ziwei Yang3

  • 1Keiji AI, Seattle, WA, USA.

Nature Biomedical Engineering
|January 22, 2026
PubMed
Summary
This summary is machine-generated.

Large language models (LLMs) show low accuracy (<40%) in biomedical data visualization tasks. An improved AI agent achieved 74% accuracy by refining analysis plans, enhancing scientific research reliability.

More Related Videos

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data
04:13

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Published on: November 13, 2019

12.8K
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.4K

Related Experiment Videos

Last Updated: Jan 24, 2026

Scaled Anatomical Model Creation of Biomedical Tomographic Imaging Data and Associated Labels for Subsequent Sub-surface Laser Engraving SSLE of Glass Crystals
07:57

Scaled Anatomical Model Creation of Biomedical Tomographic Imaging Data and Associated Labels for Subsequent Sub-surface Laser Engraving SSLE of Glass Crystals

Published on: April 25, 2017

8.7K
Computer-based Multitaper Spectrogram Program for Electroencephalographic Data
04:13

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Published on: November 13, 2019

12.8K
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.4K

Area of Science:

  • Biomedical research
  • Data visualization
  • Artificial intelligence

Background:

  • Large language models (LLMs) show potential for generating data visualizations from user requests.
  • The accuracy of LLM-generated visualizations in scientific contexts is largely unassessed.
  • Current LLMs may pose risks of propagating inaccurate scientific findings.

Purpose of the Study:

  • To benchmark the accuracy of various LLMs in biomedical data visualization.
  • To develop and evaluate an improved AI agent for generating accurate scientific visualizations.
  • To create a platform for collaborative development of analysis plans with LLMs.

Main Methods:

  • A benchmark of 293 coding tasks from 39 studies across 7 biomedical research areas was created.
  • Eight proprietary and eight open-source LLMs were evaluated using different prompting strategies.
  • An AI agent was developed to iteratively refine analysis plans before code generation.

Main Results:

  • LLMs demonstrated an overall accuracy below 40% in the benchmark tasks.
  • The developed AI agent achieved 74% accuracy in generating analysis code.
  • A user study showed the platform enabled researchers to complete over 80% of analysis code for three studies.

Conclusions:

  • Blind reliance on current LLMs for scientific data visualization carries a significant risk of error.
  • An AI agent that prioritizes analysis plan refinement can substantially improve accuracy.
  • A collaborative platform integrating LLMs can enhance the efficiency and reliability of biomedical data analysis.