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

Propagation of Uncertainty from Systematic Error01:10

Propagation of Uncertainty from Systematic Error

1.1K
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...
1.1K
Propagation of Uncertainty from Random Error00:59

Propagation of Uncertainty from Random Error

1.5K
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
1.5K

You might also read

Related Articles

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

Sort by
Same author

Reply by Authors.

The Journal of urology·2026
Same author

Preoperative Circulating Tumor DNA Predicts Upstaging and Recurrence in High-Risk Nonmuscle-Invasive Bladder Cancer Undergoing Radical Cystectomy.

The Journal of urology·2026
Same author

Generative Artificial Intelligence Successfully Automates Data Extraction From Unstructured Magnetic Resonance Imaging Reports: Feasibility in Prostate Cancer Care.

JCO clinical cancer informatics·2026
Same author

Development and Validation of a Generative Artificial Intelligence-Based Pipeline for Automated Clinical Data Extraction From Electronic Health Records: Technical Implementation Study.

JMIR bioinformatics and biotechnology·2026
Same author

Association of household net worth with healthcare costs after radical cystectomy using real-world data.

Cancer medicine·2024
Same author

Patient Engagement With and Perspectives on a Mobile Health Home Spirometry Intervention: Mixed Methods Study.

JMIR mHealth and uHealth·2024

Related Experiment Video

Updated: Nov 23, 2025

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

16.2K

Natural language processing systems for pathology parsing in limited data environments with uncertainty estimation.

Anobel Y Odisho1, Briton Park2, Nicholas Altieri2

  • 1Department of Urology, UCSF Helen Diller Family Comprehensive Cancer Center, San Francisco, California, USA.

JAMIA Open
|December 31, 2020
PubMed
Summary

Machine learning for pathology parsing can be effective even with limited data. Calibration methods enhance the reliability of uncertainty estimates for these AI models in cancer diagnostics.

Keywords:
cancerinformation extractionmachine learningnatural language processingpathologyprostate cancer

More Related Videos

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

562
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

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

Published on: December 6, 2024

853

Related Experiment Videos

Last Updated: Nov 23, 2025

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

16.2K
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

562
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

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

Published on: December 6, 2024

853

Area of Science:

  • Computational pathology
  • Artificial intelligence in medicine
  • Machine learning for healthcare

Background:

  • Pathology reports contain crucial diagnostic information but are often unstructured.
  • Extracting data from these reports is essential for improving cancer diagnostics.
  • Current machine learning models for pathology parsing require robust uncertainty estimation.

Purpose of the Study:

  • To improve uncertainty estimates for machine learning-based pathology parsers.
  • To evaluate the performance of these models in low-data scenarios.
  • To enhance the reliability of AI in analyzing unstructured pathology data.

Main Methods:

  • Utilized a dataset of 3232 annotated prostate cancer pathology reports.
  • Employed document classification and token extraction models for 17 information extraction tasks.
  • Applied isotonic calibration to improve model uncertainty estimates.

Main Results:

  • Achieved a weighted F1 score of 0.97 for document classification and 0.93 accuracy for token extraction.
  • Model performance saturated with as few as 128 data points.
  • Isotonic calibration significantly improved uncertainty estimates for extraction methods, reducing expected calibration error below 0.03.

Conclusions:

  • Large datasets are not always necessary for effective machine learning in pathology parsing.
  • Calibration methods are crucial for improving the reliability of uncertainty estimates in AI-driven pathology analysis.
  • These findings support the use of AI in improving cancer diagnostics with potentially smaller datasets.