Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Improving Translational Accuracy

Improving Translational Accuracy

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

Comparing Experimental Results: Student's t-Test

Comparing Experimental Results: Student's t-Test

The t-test is a statistical method used to compare the sample mean with a population mean or compare two means from two data sets. The test statistic is calculated from the standard deviation, mean, and number of measurements in the data set at a selected confidence interval and then compared to a table of critical values at this confidence level. If the test statistic is smaller than the critical value, the null hypothesis is accepted. In this case, we state that the difference between the...

Student t Distribution

Student t Distribution

The population standard deviation is rarely known in many day-to-day examples of statistics. When the sample sizes are large, it is easy to estimate the population standard deviation using a confidence interval, which provides results close enough to the original value. However, statisticians ran into problems when the sample size was small. A small sample size caused inaccuracies in the confidence interval.
The Student t distribution was developed by William S. Goset (1876–1937) of the...

You might also read

Related Articles

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

Sort by

Same author

Large Language Model-Based Identification of Acute Coronary Syndrome Management Delays.

The American journal of cardiology·2026

Same author

Dissipation induced localization transitions in an open quasiperiodic ladder.

Journal of physics. Condensed matter : an Institute of Physics journal·2026

Same author

Assessing workload, compensation, and burnout in academic dermatology: a national multi-institutional survey study.

International journal of women's dermatology·2026

Same author

Career development awards support early-stage researchers in life sciences entrepreneurship.

Nature biotechnology·2025

Same author

Program Evaluation for Graduate Medical Education: Practical Approaches From the Reimagining Residency Evaluation Community of Practice.

Journal of graduate medical education·2025

Same author

Multicenter evaluation of the impact of COVID-19 on the uptake of endoscopic skills by gastroenterology trainees.

Surgical endoscopy·2025

Same journal

Preliminary Effectiveness of 360° Immersive Virtual Reality for the Acquisition of Empathy-Related Skills in Physiotherapy Students: A Quasi-Experimental Study.

Medical science educator·2026

Same journal

Beyond Content Support: A One-on-One Near-Peer Tutoring Approach to Study Skills in a Bilingual Medical Program.

Medical science educator·2026

Same journal

A Sound Education: A Qualitative Study of the Role of Podcasts in Postgraduate Medical Education.

Medical science educator·2026

Same journal

A Bootcamp for Transition into Clerkship in a Distributed Campus Model.

Medical science educator·2026

Same journal

Comment on "Incorporating Artificial Intelligence in Qualitative Research: Exploring the Role of ChatGPT in Thematic Analysis".

Medical science educator·2026

Same journal

Homework with a Probe: Boosting Pre-clerkship Ultrasound Engagement.

Medical science educator·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Apr 7, 2026

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

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

Published on: December 6, 2024

Using a Large Language Model to Extract Information from Student Submitted Free-Text Feedback.

Nikola Košćica¹, Colleen Gillespie¹, Tyler Webster¹

¹NYU Grossman School of Medicine, New York, NY USA.

Medical Science Educator

|April 6, 2026

Summary

This summary is machine-generated.

Large Language Models (LLMs) show promise for analyzing qualitative student feedback in medical education. While not perfect, ChatGPT 4o offers a feasible and efficient tool for curriculum evaluation and improvement.

Keywords:

AI Cirriculum development Evaluations Qualitative feedback

Related Experiment Videos

Last Updated: Apr 7, 2026

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

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

Published on: December 6, 2024

Area of Science:

Medical Education
Artificial Intelligence in Education

Background:

Qualitative student feedback is crucial for curriculum evaluation but challenging to analyze.
Traditional methods for analyzing text-based feedback are time-consuming and require expertise.
Narrative comments offer unique insights beyond quantitative data for curriculum refinement.

Purpose of the Study:

To assess the feasibility and accuracy of using a Large Language Model (LLM), specifically ChatGPT 4o, for analyzing medical student comments.
To evaluate the LLM's ability to categorize and summarize challenging basic science topics identified by students.
To compare LLM-generated analyses with expert human evaluations for consistency, accuracy, and meaningfulness.

Main Methods:

Utilized ChatGPT 4o to process and analyze open-ended student feedback on challenging basic science topics.
Developed and refined specific prompts for the LLM to categorize and summarize student comments.
Conducted experiments including replication analysis, comparison of LLM categorization with expert human ratings, and comparison of LLM explanation analysis with expert human analysis.

Main Results:

LLM output was found to be useful, generally aligned with human expert analysis, and easy to implement.
Replication consistency was not perfect, and some differences between LLM and human analyses were observed.
The LLM demonstrated sufficient consistency and accuracy to support continuous quality improvement.

Conclusions:

LLMs like ChatGPT 4o present a viable solution for efficiently analyzing qualitative student feedback in medical education.
While current LLM capabilities provide valuable support for curriculum refinement, ongoing development is needed to address minor inconsistencies and accuracy variations.
The use of LLMs in this context is well-suited for continuous quality improvement initiatives in basic science curricula.