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

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...

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...

You might also read

Related Articles

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

Sort by

Same author

Clinical and Economic Burden of Poor Bone Health in Adult Spinal Deformity Surgery: A Multicenter Cohort Study.

Spine·2026

Same author

Risk factors for elevated endotracheal tube cuff pressure in anterior cervical spine surgery.

Journal of neurosurgery. Spine·2026

Same author

Cage Overhang Ratio and Increased Radiographic Subsidence in Stand-Alone Lateral Lumbar Interbody Fusion.

World neurosurgery·2026

Same author

Administration of ketogenic intervention as a potential treatment during post-traumatic brain injury recovery: a scoping review.

Frontiers in nutrition·2026

Same author

Management for Chronic Neck Pain: Identifying Groups at Risk for Increased Emergency Room Utilization and Healthcare Gaps.

Neurosurgery·2026

Same author

Superior displacement of the inflexion point does not predict proximal junctional kyphosis after fusion for adult spinal deformity.

Journal of spine surgery (Hong Kong)·2026

Search research articles

Related Experiment Video

Updated: May 11, 2026

Pedicle Screw Placement Using an Augmented Reality Head-Mounted Display in a Porcine Model

Pedicle Screw Placement Using an Augmented Reality Head-Mounted Display in a Porcine Model

Published on: May 24, 2024

Prompt Engineering and Follow-Up Questioning Improves the Readability of Spine Surgery Questions in Large Language

Sohail Daulat¹, Nikhil Dholaria², Gregory Burnet¹

¹Department of Neurological Surgery, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA.

World Neurosurgery

|September 1, 2025

Summary

Prompt engineering and follow-up questions significantly improve large language model (LLM) readability for spine surgery patient education. ChatGPT-4o generally produced more readable content than ChatGPT-5.

Keywords:

Artificial Intelligence Large Language Model Prompt Engineering Readability Spine

More Related Videos

3D Printing Model of a Patient's Specific Lumbar Vertebra

3D Printing Model of a Patient's Specific Lumbar Vertebra

Published on: April 14, 2023

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

Related Experiment Videos

Last Updated: May 11, 2026

Pedicle Screw Placement Using an Augmented Reality Head-Mounted Display in a Porcine Model

Pedicle Screw Placement Using an Augmented Reality Head-Mounted Display in a Porcine Model

Published on: May 24, 2024

3D Printing Model of a Patient's Specific Lumbar Vertebra

3D Printing Model of a Patient's Specific Lumbar Vertebra

Published on: April 14, 2023

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 Healthcare
Spine Surgery

Background:

Patient education materials in spine surgery often exceed recommended reading levels.
Large language models (LLMs) show promise for generating educational content but need further study on readability and adaptability.
Assessing LLM performance in creating accessible patient information is crucial.

Purpose of the Study:

To evaluate which LLM model and prompting strategies enhance the readability of spine surgery patient education the most.
To compare the performance of newer LLM models in generating understandable content.
To identify optimal methods for improving LLM-generated educational materials.

Main Methods:

ChatGPT-4o and ChatGPT-5 were prompted with 45 spine surgery questions across five common procedures.
Responses were generated through five prompting phases, including baseline, follow-up clarification, sixth-grade level requests, rule-based prompting, and direct readability targeting.
Readability was assessed using multiple scoring systems (SMOG, FRE, FKGL, GFI, CLI) and analyzed statistically.

Main Results:

ChatGPT-4o generated significantly more readable responses than ChatGPT-5 across most phases (p<0.001).
The sixth-grade level request phase (Phase 2) resulted in the most readable answers, with over 51% meeting the target.
Follow-up clarification and simplified prompts were more effective than complex rule-based strategies for improving readability.

Conclusions:

Prompt engineering and follow-up questioning substantially improve LLM-generated spine surgery content readability for patients.
While ChatGPT-4o showed better readability, ChatGPT-5 provided more reliable citations.
Future research should validate these findings in real-world clinical settings beyond objective scoring.