Jove
Visualize
Contact Us

Related Concept Videos

Extraction: Advanced Methods00:56

Extraction: Advanced Methods

559
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...
559
ER Retrieval Pathway01:45

ER Retrieval Pathway

3.9K
In the secretory pathway, vesicles transport proteins from one cellular compartment to another in forward transport to deliver the protein to its correct location. Occasionally, misfolded proteins and incorrect proteins escape their original compartments, and a retrieval pathway is used to return the escaped proteins to their original compartment.
The ER uses many checkpoints to prevent the entry of incorrectly folded or a resident protein as cargo onto a transport vesicle. These mechanisms...
3.9K
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
  1. Home
  3. Exploring Chatgpt 3.5 For Structured Data Extraction From Oncological Notes.
  1. Home
  3. Exploring Chatgpt 3.5 For Structured Data Extraction From Oncological Notes.

Related Experiment Video

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.6K

Exploring ChatGPT 3.5 for structured data extraction from oncological notes.

Ty J Skyles1, Isaac J Freeman2, Georgewilliam Kalibbala1

  • 1Brigham Young University, Provo, UT.

AMIA Joint Summits on Translational Science Proceedings. AMIA Joint Summits on Translational Science
|June 12, 2025

View abstract on PubMed

Summary
This summary is machine-generated.

Large language models (LLMs) show promise for extracting valuable data from electronic health records to improve cancer research. ChatGPT effectively identified patient information like Gleason scores and palliative care status from clinical notes.

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.9K

Related Experiment Videos

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.6K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.9K

Area of Science:

  • Clinical informatics
  • Artificial intelligence in medicine
  • Cancer research

Background:

  • Electronic health records (EHRs) contain vast amounts of unstructured data crucial for large-scale clinical research.
  • Maximizing the usability of EHR data is essential for advancing medical insights and patient care.
  • Large language models (LLMs) offer a potential solution for extracting structured information from unstructured clinical notes.

Purpose of the Study:

  • To evaluate the efficacy of ChatGPT, a large language model, in extracting structured clinical data from unstructured electronic health records for cancer research.
  • To assess the impact of different prompt engineering strategies on the accuracy of data extraction by GPT models.

Main Methods:

  • Utilized ChatGPT to process clinical notes and answer six predefined clinical questions relevant to cancer research.
  • Employed four distinct prompt engineering strategies: zero-shot, zero-shot with context, few-shot, and few-shot with context.
  • Quantified the performance of GPT in extracting specific patient data points, including Gleason scores, age, palliative care status, and pain identification.

    • Main Results:

    • GPT achieved a high F1 score of 0.99 for extracting patients' Gleason scores and ages.
    • GPT demonstrated a strong performance with an F1 score of 0.86 in identifying palliative care status and patient-reported pain.
    • Few-shot prompting strategies sometimes reduced output accuracy, and the inclusion of context did not consistently enhance performance.

    Conclusions:

    • Large language models, such as ChatGPT, can significantly improve data availability and extraction from electronic health records for cancer research.
    • Effective implementation of LLMs holds the potential to enhance interoperability between healthcare systems and clinical research initiatives.
    • Further research into optimal prompt engineering is needed to maximize the benefits of LLMs in clinical informatics.