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

You might also read

Related Articles

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

Sort by
Same author

A gold-standard French-language annotated corpus of oncological entities with ICD-O normalisation.

Scientific data·2026
Same author

Can LLMs Turn French PET/CT Narrative Reports into Structured Knowledge?

Studies in health technology and informatics·2026
Same author

Advancing Knowledge in Evaluating the Clinical Impact of Large Language Models for Clinical Text Summarization: A Narrative Review.

Studies in health technology and informatics·2026
Same author

Benchmarking Open-Source Large Language Models in Medical French.

Studies in health technology and informatics·2026
Same author

The Limits of Generalization: Zero-Shot French Medical NER Using French, English and Multilingual GLiNER Models.

Studies in health technology and informatics·2026
Same author

Generating Human-Readable Labels for SNOMED CT Expressions with LLMs: A Study on Model Performance and Rater Subjectivity.

Studies in health technology and informatics·2026

Related Experiment Video

Updated: Sep 27, 2025

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

8.4K

Real-world Patient Trajectory Prediction from Clinical Notes Using Artificial Neural Networks and UMLS-Based

Jamil Zaghir1, Jose F Rodrigues-Jr2, Lorraine Goeuriot3

  • 1University of Grenoble Alpes, Grenoble, France.

Journal of Healthcare Informatics Research
|April 14, 2022
PubMed
Summary

This study presents a novel method using Artificial Neural Networks and clinical notes for accurate patient prognosis. The approach enhances predictions for medical conditions, mortality, and readmission, improving healthcare outcomes.

Keywords:
Clinical notesComputer-aided prognosisMIMIC-IIIPatient trajectory predictionQuickUMLS

More Related Videos

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

629
Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

9.0K

Related Experiment Videos

Last Updated: Sep 27, 2025

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

8.4K
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

629
Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

9.0K

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Healthcare
  • Clinical Prognosis

Background:

  • The increasing volume of medical data and advancements in Artificial Neural Networks (ANNs) are driving the development of computer-aided medical prognosis.
  • Electronic Health Records (EHRs), particularly unstructured clinical notes, are a rich source of information for automated patient prognoses.

Purpose of the Study:

  • To introduce a novel methodology for predicting future medical problems using unstructured clinical notes from EHRs.
  • To refine the extraction and utilization of medical concepts for improved prognostic accuracy.

Main Methods:

  • Applying preprocessing, concept extraction, and fine-tuned ANNs to unstructured clinical notes.
  • Generating a refined set of Unified Medical Language System (UMLS) concepts by applying a similarity threshold filter and acceptable concept types.
  • Utilizing these refined concepts for predicting clinical conditions, mortality, and readmission.

Main Results:

  • Achieved an Area Under the Receiver Operating Characteristic curve (AUC-ROC) of 0.91 for diagnosis codes.
  • Demonstrated an AUC-ROC of 0.93 for mortality prediction.
  • Obtained an AUC-ROC of 0.72 for readmission prediction, rivaling state-of-the-art performance.

Conclusions:

  • The proposed methodology effectively leverages unstructured clinical text for automated patient prognosis.
  • The refined concept extraction and ANN-based prediction system shows high efficacy, comparable to existing advanced methods.
  • This approach contributes to the advancement of automated prognosis systems in healthcare settings where clinical history is primarily text-based.