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 Experiment Videos

Automatic concept extraction from spoken medical reports.

André Happe1, Bruno Pouliquen, Anita Burgun

  • 1Intermède, La Basse Revachais, 35580 Guignen, France. happe@intermede.net

International Journal of Medical Informatics
|August 12, 2003
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Economic evaluation of adjuvant chemotherapy for non-metastatic sarcoma using the real-world data from the French nationwide DEEPSARC study.

Journal of medical economics·2026
Same author

Overall survival of patients with localized soft tissue sarcoma treated with or without adjuvant chemotherapy (DEEPSARC): a real world nationwide retrospective cohort study in France.

EClinicalMedicine·2026
Same author

Multi-site health research integrating complementary data sources: A scoping review of statistical inference methods for vertically partitioned data.

International journal of medical informatics·2026
Same author

Adoption and Use of Social Media in Health Care Among Medical Residents: Cross-Sectional Study.

JMIR medical education·2026
Same author

Development and Validation of a Multi-Modal Algorithm for Chronic Kidney Disease Detection in a Hospital Clinical Data Warehouse.

Studies in health technology and informatics·2026
Same author

OPTIMA-DAW: Improving Cerebral Vasospasm Detection After Aneurysmal Subarachnoid Haemorrhage Using Machine Learning.

Studies in health technology and informatics·2026
Same journal

Medical students' use of large language models: a national survey.

International journal of medical informatics·2026
Same journal

BlockFedMed: A blockchain-federated learning framework for privacy-preserving mortality prediction across heterogeneous intensive care units.

International journal of medical informatics·2026
Same journal

Integrating clinical decision support systems in pediatric oncology: A scoping review of applications, implementation gaps, and management Implications.

International journal of medical informatics·2026
Same journal

Understanding digital health capability of allied health professionals - a mixed-methods study with content validity analysis.

International journal of medical informatics·2026
Same journal

On-premises open-source large language models for privacy-preserving multimodal depression screening.

International journal of medical informatics·2026
Same journal

Data mining methods, tasks, and algorithms for adverse drug reaction analysis in pharmacovigilance: A scoping review.

International journal of medical informatics·2026
See all related articles

Combining speech recognition and automated indexing offers a promising alternative to manual transcription and indexing. This method achieved high recall (90%) with minimal errors from speech recognition, demonstrating its potential for medical text processing.

Area of Science:

  • Medical Informatics
  • Natural Language Processing

Background:

  • Current medical transcription and indexing practices are time-consuming and labor-intensive.
  • Automated methods are sought to improve efficiency and accuracy in medical record processing.

Purpose of the Study:

  • To investigate the efficacy of combining speech recognition with automated indexing to replace traditional methods.
  • To evaluate a system using speech recognition and NOMINDEX for extracting MeSH concepts from French medical texts.

Main Methods:

  • Utilized existing speech recognition software and NOMINDEX, a tool based on a French medical lexicon and UMLS.
  • Processed documents through dictation, speech recognition, and automatic indexing.
  • Evaluated performance by comparing automated indexing results with manually extracted keywords from 28 French patient discharge summaries.

Related Experiment Videos

Main Results:

  • Achieved an overall precision of 73% and a recall of 90%.
  • Speech recognition accuracy exceeded 98%, with only 3% of indexing errors attributed to speech recognition.
  • Primary indexing errors stemmed from word sense ambiguity and abbreviations, not speech recognition failures.

Conclusions:

  • The combination of speech recognition and automated indexing shows significant potential for medical documentation.
  • Further improvements can be made by addressing issues like word sense ambiguity and diacritics in MeSH terms.
  • The low error rate from speech recognition validates its integration into automated indexing workflows.