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

Intravenous extravasation report generation using deep learning, generative artificial intelligence, and visual

Adirek Munthuli1,2, Pitchaporn Liao3, Padcha Pongcharoen4

  • 1Center of Excellence in Nexus for Advanced Intelligence in Law, Engineering, and Medicine (Nail'Em), Thammasat University, Rangsit Campus, Khlong Nueng, Khlong Luang, 10120, Pathum Thani, Thailand.

Scientific Reports
|May 11, 2026
PubMed
Summary

Related Concept Videos

Imaging Studies V: Intravenous Urography and Retrograde Pyelography01:22

Imaging Studies V: Intravenous Urography and Retrograde Pyelography

IntroductionIntravenous Urography (IVU) and Retrograde Pyelography (RP) are important diagnostic imaging techniques used to evaluate the urinary system. These methods help identify structural abnormalities, obstructions, and functional issues in the kidneys, ureters, and bladder. Both procedures use iodine-based contrast media to enhance the visibility of urinary tract structures on X-ray images, though they differ in their methods and indications.1. Intravenous Urography (IVU)Intravenous...

You might also read

Related Articles

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

Sort by
Same author

A 10-year retrospective cross-sectional study of severe cutaneous adverse drug reactions in Thailand: Human leukocyte antigen typing and enzyme-linked immunospot assay-assisted drug identification.

JAAD international·2025
Same author

A practical guide to biologic treatments for psoriasis in resource-limited areas.

Asian Pacific journal of allergy and immunology·2025
Same author

Dose-Dependent Effects of Benzodiazepines and Other Psychotropic Drugs on Seizure Duration in Electroconvulsive Therapy.

The journal of ECT·2025
Same author

Health-related quality of life in Thai patients with hepatocellular carcinoma and its influencing factors: A cross-sectional study.

Belitung nursing journal·2025
Same author

Optimizing deep learning models for glaucoma screening with vision transformers for resource efficiency and the pie augmentation method.

PloS one·2025
Same author

Real-Life Data of Secukinumab in Patients with Moderate to Severe Plaque Psoriasis, Psoriatic Arthritis, and Ankylosing Spondylitis: Patient Baseline Characteristics Data from the PROMPT Study.

Dermatology and therapy·2024
Same journal

Peripheral B-cell receptor repertoire predicts immune-related adverse events following immune checkpoint inhibitor therapy in advanced renal cell carcinoma.

Scientific reports·2026
Same journal

Effects of black soldier fly (Hermetia illucens L.) larvae zoocompost on the mineral element content of blue honeysuckle berries.

Scientific reports·2026
Same journal

Investigation on absorption refrigeration performance of R1243zf with imidazolium ionic liquid as the working pairs.

Scientific reports·2026
Same journal

DeepTriage-CN: integrating clinical text with vital signs for emergency department admission prediction in an aging population.

Scientific reports·2026
Same journal

Gold nanoparticles as dual-action antiviral agents: disruption of SARS-CoV-2 viral envelopes and RNA integrity.

Scientific reports·2026
Same journal

Comparison of capillary microsampling and venous blood for multi-pathogen serosurveillance.

Scientific reports·2026
See all related articles
This summary is machine-generated.

Visual Question Answering (VQA) technology integrated into the Thammasat University eXtravasation Assessment Tool (TUXAT) can automate and standardize extravasation reporting. This AI approach shows promise for improving clinical decision support in managing extravasation injuries.

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Healthcare
  • Clinical Decision Support Systems

Background:

  • Peripheral intravenous extravasation is a common clinical challenge requiring accurate assessment for effective management.
  • Current assessment methods can be subjective, leading to variability in reporting and intervention.
  • Standardized, objective reporting is crucial for timely and appropriate patient care.

Purpose of the Study:

  • To evaluate the integration of Visual Question Answering (VQA) technology into the Thammasat University eXtravasation Assessment Tool (TUXAT).
  • To assess the VQA system's ability to generate structured clinical reports for extravasation management.
  • To compare the performance of different VQA model architectures in this clinical application.

Main Methods:

Related Experiment Videos

  • Two VQA approaches (single large model vs. mixture of models) were evaluated within the TUXAT framework.
  • The VQA system was tasked with generating reports on Findings (Skin Discoloration, Integrity, Edema), Implications (Severity), and Treatment Plans.
  • Inter-rater reliability and statistical analyses were used to assess agreement, sensitivity to clinical severity, and annotator/model effects.

Main Results:

  • Moderate-to-substantial agreement was observed for skin discoloration assessment, with subjectivity impacting integrity and edema scoring.
  • The VQA system demonstrated sensitivity to clinical severity and captured expected expert variability.
  • Both VQA architectures performed comparably, indicating robustness for extravasation reporting.
  • Relative differences in annotator ratings remained consistent across severity levels.

Conclusions:

  • Visual Question Answering (VQA) technology shows significant potential for automating and standardizing extravasation reporting.
  • The integration of VQA into TUXAT offers a promising pathway for enhanced clinical decision support.
  • Further development could improve the precision of VQA in assessing all aspects of extravasation injuries.