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

Size-Exclusion Chromatography01:08

Size-Exclusion Chromatography

In size-exclusion chromatography (SEC), also known as molecular-exclusion or gel-permeation chromatography, molecules are separated based on their sizes. This technique is important for separating large molecules such as polymers and biomolecules. The two classes of micron-sized stationary phases encountered in SEC are silica particles and cross-linked polymer resin beads. Both materials are porous, but their pore sizes vary significantly.
Silica particles offer advantages such as rigidity,...

You might also read

Related Articles

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

Sort by
Same author

Suggested Approaches on Communicating to the Public Implications of the Linear No-Threshold (LNT) Dose Response Model and the Fallacy That "There Are No Safe Levels of Radiation Exposure".

Health physics·2026
Same author

Clinical Standardization Across a National Health System: Perspectives From the Veterans Affairs' Electronic Health Record Transition.

Medical care·2026
Same author

Automatic Placement Within a Hierarchical Clinical Decision Support Terminology.

Studies in health technology and informatics·2026
Same author

FURIN Stimulates NOTCH2 and NOTCH3 Pathways, Leading to Return of Function in Aged Cells.

Life (Basel, Switzerland)·2026
Same author

Semantic Relations: Extending SNOMED CT and Solor.

Applied clinical informatics·2025
Same author

Environment Scan of Generative AI Infrastructure for Clinical and Translational Science.

ArXiv·2025

Related Experiment Video

Updated: May 24, 2026

Assisted Selection of Biomarkers by Linear Discriminant Analysis Effect Size (LEfSe) in Microbiome Data
04:57

Assisted Selection of Biomarkers by Linear Discriminant Analysis Effect Size (LEfSe) in Microbiome Data

Published on: May 16, 2022

DeepSeek R1 Distilled Fails to Perform Well Against the USMLE and Other LLMs with and Without Semantics.

Peter L Elkin1, Guresh Mehta1, Aaron N Elkin1

  • 1Department of Biomedical Informatics, University at Buffalo, USA.

Studies in Health Technology and Informatics
|May 23, 2026
PubMed
Summary

DeepSeek-R1, a distilled large language model (LLM), was evaluated for medical question answering. Performance on United States Medical Licensing Examinations (USMLE) questions showed a significant drop, indicating it is not yet a viable alternative.

Keywords:
AIChatBotsClinical Decision SupportMachine Learning

More Related Videos

Sampling Human Indigenous Saliva Peptidome Using a Lollipop-Like Ultrafiltration Probe: Simplify and Enhance Peptide Detection for Clinical Mass Spectrometry
08:37

Sampling Human Indigenous Saliva Peptidome Using a Lollipop-Like Ultrafiltration Probe: Simplify and Enhance Peptide Detection for Clinical Mass Spectrometry

Published on: August 7, 2012

Related Experiment Videos

Last Updated: May 24, 2026

Assisted Selection of Biomarkers by Linear Discriminant Analysis Effect Size (LEfSe) in Microbiome Data
04:57

Assisted Selection of Biomarkers by Linear Discriminant Analysis Effect Size (LEfSe) in Microbiome Data

Published on: May 16, 2022

Sampling Human Indigenous Saliva Peptidome Using a Lollipop-Like Ultrafiltration Probe: Simplify and Enhance Peptide Detection for Clinical Mass Spectrometry
08:37

Sampling Human Indigenous Saliva Peptidome Using a Lollipop-Like Ultrafiltration Probe: Simplify and Enhance Peptide Detection for Clinical Mass Spectrometry

Published on: August 7, 2012

Area of Science:

  • Artificial Intelligence in Medicine
  • Natural Language Processing
  • Medical Education Technology

Background:

  • Large Language Models (LLMs) show promise in various applications.
  • Distilled LLMs are proposed as cost-effective alternatives to traditional models.
  • Evaluating LLM performance in specialized domains like medicine is crucial.

Purpose of the Study:

  • To assess the performance of the DeepSeek-R1 distilled LLM.
  • To compare DeepSeek-R1 against traditional LLMs for medical question answering.
  • To determine the suitability of DeepSeek-R1 for United States Medical Licensing Examinations (USMLE) preparation.

Main Methods:

  • The DeepSeek-R1 model was tested on a dataset of USMLE medical questions.
  • Performance metrics were compared between DeepSeek-R1 and a baseline traditional LLM.
  • Quantitative analysis of accuracy and response quality was conducted.

Main Results:

  • A significant performance degradation was observed with the DeepSeek-R1 model.
  • DeepSeek-R1 exhibited lower accuracy in answering complex medical questions compared to the original model.
  • The cost-effectiveness of DeepSeek-R1 does not currently compensate for its reduced performance.

Conclusions:

  • DeepSeek-R1 is not currently a suitable alternative for medical question answering.
  • Further development is needed to improve the performance of distilled LLMs in specialized fields.
  • The use of distilled LLMs for high-stakes medical examinations requires caution.