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

Imaging Studies I: CT and MRI01:14

Imaging Studies I: CT and MRI

231
Introduction: MRI and CT scans are crucial advancements in medical imaging techniques, playing a vital role in diagnosing conditions related to the gastrointestinal (GI) system. Each scan serves distinct purposes, targets specific areas, and requires unique nursing duties.
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
231
Radiological Investigation III: Pulmonary Angiogram and PET Scan01:13

Radiological Investigation III: Pulmonary Angiogram and PET Scan

91
Radiological investigations are paramount in the diagnosis and management of various pulmonary diseases. Two essential investigations are the Pulmonary Angiogram and the Positron Emission Tomography (PET) Scan.
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
91
Radiological Investigation I: X-ray and CT01:30

Radiological Investigation I: X-ray and CT

227
Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...
227
Radiological Investigation II: MRI and Ventilation Perfusion Scan01:30

Radiological Investigation II: MRI and Ventilation Perfusion Scan

111
Description
Magnetic Resonance Imaging (MRI) and Ventilation Perfusion Scans are two radiological investigations that offer detailed diagnostic images of the body, particularly lung structures.
MRI
MRI uses magnetic fields and radiofrequency signals to distinguish between normal and abnormal tissues. This technology provides a more detailed diagnostic image than CT scans, enabling it to characterize pulmonary nodules, stage bronchogenic carcinoma, and evaluate inflammatory activity in...
111
Imaging Studies for Cardiovascular System III: X-Ray01:20

Imaging Studies for Cardiovascular System III: X-Ray

173
The most common cardiovascular diagnostic test is an X-ray. It produces images of the heart, blood vessels, and adjacent structures.
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
173
Positron Emission Tomography01:29

Positron Emission Tomography

4.2K
Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
4.2K
  1. Home
  2. Evaluation Of Gpt-4 Ability To Identify And Generate Patient Instructions For Actionable Incidental Radiology Findings.
  1. Home
  2. Evaluation Of Gpt-4 Ability To Identify And Generate Patient Instructions For Actionable Incidental Radiology Findings.

Related Experiment Video

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant
05:18

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant

Published on: October 6, 2023

1.3K

Evaluation of GPT-4 ability to identify and generate patient instructions for actionable incidental radiology

Kar-Mun C Woo1, Gregory W Simon1, Olumide Akindutire1

  • 1Ronald O. Perelman Department of Emergency Medicine, NYU Grossman School of Medicine, New York, NY 10016, United States.

Journal of the American Medical Informatics Association : JAMIA
|May 23, 2024

View abstract on PubMed

Summary
This summary is machine-generated.

A HIPAA-compliant GPT-4 model effectively identifies actionable incidental findings in radiology reports. AI-generated patient summaries are mostly appropriate, but clinician oversight remains crucial for safe implementation.

Keywords:
ChatGPTGPTfollow-upincidentalomalarge language modelradiology

More Related Videos

Safety Precautions and Operating Procedures in an ABSL-4 Laboratory: 4. Medical Imaging Procedures
09:36

Safety Precautions and Operating Procedures in an ABSL-4 Laboratory: 4. Medical Imaging Procedures

Published on: October 3, 2016

10.9K
Author Spotlight: Point-of-Care Ultrasound for Gastric Content Assessment and Risk Stratification in Perioperative Care
05:50

Author Spotlight: Point-of-Care Ultrasound for Gastric Content Assessment and Risk Stratification in Perioperative Care

Published on: September 22, 2023

2.8K

Related Experiment Videos

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant
05:18

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant

Published on: October 6, 2023

1.3K
Safety Precautions and Operating Procedures in an ABSL-4 Laboratory: 4. Medical Imaging Procedures
09:36

Safety Precautions and Operating Procedures in an ABSL-4 Laboratory: 4. Medical Imaging Procedures

Published on: October 3, 2016

10.9K
Author Spotlight: Point-of-Care Ultrasound for Gastric Content Assessment and Risk Stratification in Perioperative Care
05:50

Author Spotlight: Point-of-Care Ultrasound for Gastric Content Assessment and Risk Stratification in Perioperative Care

Published on: September 22, 2023

2.8K

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Healthcare
  • Radiology

Background:

  • Unstructured radiology reports contain incidental findings requiring follow-up.
  • Automated identification of these findings can improve patient care.
  • Large language models (LLMs) show potential for analyzing clinical text.

Purpose of the Study:

  • To evaluate a HIPAA-compliant GPT-4's accuracy in detecting actionable incidental findings in emergency department radiology reports.
  • To assess the appropriateness of AI-generated patient-facing summaries of these findings.

Main Methods:

  • A HIPAA-compliant GPT-4 model was developed and optimized using instruction prompts.
  • The model analyzed 430 unstructured radiology reports to identify 'definitely actionable' (DA) and 'possibly actionable-clinical correlation' (PA-CC) findings.
  • Performance was measured by recall, precision, and F-1 score; AI summaries were evaluated for appropriateness.
  • Main Results:

    • GPT-4 achieved high recall (99.3% for DA or PA-CC, 95.2% for DA only) in identifying actionable findings.
    • Precision varied (73.6% for DA or PA-CC, 77.3% for DA only), with minimal inferred recommendations (2.8%).
    • The majority of AI-generated patient summaries required no or minor revisions.

    Conclusions:

    • Refined prompting enables GPT-4 to proficiently detect actionable incidental findings in radiology reports.
    • AI-generated summaries are largely appropriate, but may include inferred recommendations.
    • Human-in-the-loop workflows are essential for clinical implementation of this AI technology.