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

Issues And Trends In Healthcare Delivery System01:29

Issues And Trends In Healthcare Delivery System

6.5K
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
6.5K
Patient-centered Care01:13

Patient-centered Care

3.1K
Patient-centered care involves delivering care beyond inpatient hospitalization. Reflective practice can enhance a patient-centered approach. Reflective practice is a process of reasoning that considers all aspects of the present situation, including practicalities, learning from personal practice, and consideration of patient needs. Patients appreciate care decisions made while considering their input. Involving the patient in their care provides the patient with a sense of contribution rather...
3.1K

You might also read

Related Articles

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

Sort by
Same author

Evidence for Evidence-Based Medicine - A Call for Some Theory and a New Problem.

NEJM evidence·2026
Same author

Intersectional HIV disparities among transgender Medicare beneficiaries of color.

AIDS (London, England)·2026
Same author

Age-Friendly Health System Implementation in Outpatient Settings: A Systematic Review.

Journal of the American Geriatrics Society·2026
Same author

Differences in Bladder Cancer Diagnosis by Demographic Factors: A Simulation Modeling Analysis.

medRxiv : the preprint server for health sciences·2026
Same author

Understanding Bladder Cancer Screening Limits Through Comparative Modeling: The Maximum Clinical Incidence Reduction (MCLIR) Methodology.

medRxiv : the preprint server for health sciences·2026
Same author

Fiber intake and laxation in people with normal bowel function: a systematic review.

The American journal of clinical nutrition·2026

Related Experiment Video

Updated: May 5, 2026

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

1.3K

Automatically annotating topics in transcripts of patient-provider interactions via machine learning.

Byron C Wallace1, M Barton Laws1, Kevin Small2

  • 1Department of Health Services, Policy and Practice, Brown University, School of Public Health, Providence, RI (BCW, MBL, IBW, TAT).

Medical Decision Making : an International Journal of the Society for Medical Decision Making
|November 29, 2013
PubMed
Summary

Automated machine learning can now classify patient-provider conversation topics, offering a cost-effective alternative to manual annotation for improving clinical communication and health outcomes.

Keywords:
CRFcommunicationinformaticsmachine learningnatural language processingpatient-provider interactionspeech acts

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

8.0K

Related Experiment Videos

Last Updated: May 5, 2026

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

1.3K
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

8.0K

Area of Science:

  • Natural Language Processing
  • Machine Learning in Healthcare
  • Clinical Communication Analysis

Background:

  • Manual annotation of patient-provider interactions is crucial for understanding clinical communication but is costly and time-consuming.
  • Existing methods like Roter or General Medical Interaction Analysis System (GMIAS) coding are limited by expense.
  • Automated topic coding via machine learning presents a scalable solution.

Purpose of the Study:

  • To develop and evaluate a machine learning model for automatically annotating patient-provider interaction transcripts with topic codes.
  • To assess the accuracy and utility of automated annotations in analyzing clinical communication, particularly in the context of health interventions.

Main Methods:

  • A conditional random field (CRF) model was employed to predict utterance topic probabilities, considering conversational structure and word content.
  • The model was trained and validated using 10-fold cross-validation on GMIAS-annotated transcripts from 360 outpatient visits.
  • Automated annotations were used to reanalyze data from a randomized trial on antiretroviral (ARV) adherence communication.

Main Results:

  • The CRF model achieved a mean pairwise kappa of 0.49 and mean overall accuracy of 0.64 compared to human annotators across 6 topic codes.
  • Automated annotations in the randomized trial reanalysis yielded results consistent with manual annotations.
  • The automated analysis indicated a significant difference in ARV-related utterances with the intervention (P = 0.04), aligning with manual findings.

Conclusions:

  • Machine learning methods demonstrate reasonable accuracy in classifying patient-provider interaction utterances into clinically relevant topics.
  • Automated topic inference offers a promising, cost-effective approach to analyzing clinical communication.
  • Further research is needed to fully understand the utility of automated topic annotations as intermediate outcomes.