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

AutoML-driven ensemble learning for intradialytic hypotension prediction.

Chih-Yang Cheng1,2, Yu-Chun Lin3, Anna Nai-Yun Tung4,5

  • 1Department of Information Management, National Chung Cheng University, Chia-Yi, Taiwan.

Digital Health
|July 13, 2026
PubMed
Summary

Related Concept Videos

Neural Regulation of Blood Pressure01:18

Neural Regulation of Blood Pressure

The neural regulation of blood pressure involves intricate interactions between the autonomic nervous system (ANS) and cardiovascular system, ensuring adequate perfusion of tissues. This regulation primarily occurs through baroreceptor and chemoreceptor reflexes, involving both short-term and long-term mechanisms.
Baroreceptor Reflex
Baroreceptors, located in the carotid sinuses and aortic arch, detect changes in blood pressure. When blood pressure rises, these stretch-sensitive receptors...
Pre-Procedural Guidelines for Assessing Blood Pressure01:10

Pre-Procedural Guidelines for Assessing Blood Pressure

Accurate blood pressure assessment is crucial for diagnosing and managing various health conditions. To ensure the reliability of these measurements, healthcare professionals must adhere to standardized pre-procedural guidelines. These guidelines enhance patient safety and improve the overall quality of healthcare. The following steps are essential for obtaining accurate and consistent blood pressure readings, from using the appropriate tools to ensuring effective communication with the patient.

You might also read

Related Articles

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

Sort by
Same author

The IMPACT framework for evaluating generative AI in critical care: development and multinational consensus validation.

Annals of intensive care·2026
Same author

Deep learning-driven anomaly detection and feature discovery in Ce-rich (Ni-Fe-Co-Ce)O <sub><i>x</i></sub> catalysts for oxygen evolution reaction.

RSC advances·2026
Same author

Pulmonary Histoplasmosis, Taiwan, 1997-2024.

Emerging infectious diseases·2026
Same author

Reconstruction of Nonrheumatic Boutonnière Deformity in Bilateral Thumbs Using Different Approaches With Distinct Outcomes.

Annals of plastic surgery·2026
Same author

Epidermal Growth Factor Receptor (EGFR) Amplification May Lead to Invalid Cobas EGFR Mutation Test v2 Results.

Diagnostics (Basel, Switzerland)·2025
Same author

Brief Report: The Effectiveness of Osimertinib in Advanced Nonsmall Cell Lung Cancer Harboring Various EGFR Exon 19 Mutation Variants.

Clinical lung cancer·2025

An artificial intelligence system effectively predicts intradialytic hypotension (IDH) during hemodialysis (HD). This AI tool enhances patient safety by enabling real-time adjustments to dialysis parameters, reducing complications.

Area of Science:

  • Nephrology
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Intradialytic hypotension (IDH) is a frequent and severe complication in hemodialysis (HD), linked to increased patient morbidity and mortality.
  • Predicting and managing IDH in real-time is crucial for improving patient outcomes and safety during HD sessions.

Purpose of the Study:

  • To develop an AI-driven early warning system for predicting IDH events.
  • To recommend real-time adjustments to dialysis parameters to mitigate IDH risks and enhance patient safety.

Main Methods:

  • Utilized a dataset of 9,634 HD sessions from 178 patients.
  • Applied advanced feature engineering, including SMOTE and RFECV, and an AutoML pipeline for hyperparameter optimization.
  • Developed hospital-specific AI models tailored to institutional variability.
Keywords:
CatBoostLightGBMLocal Interpretable Model-agnostic Explanations (LIME)artificial intelligenceauto machine learning (Auto ML)feature engineeringhemodialysisintradialytic hypotensionmachine learningrecursive feature elimination with cross-validation (RFECV)

Related Experiment Videos

Main Results:

  • CatBoost and LightGBM models demonstrated high performance, with CatBoost achieving a ROC-AUC of 0.934 and an F1-macro score of 0.508.
  • Feature selection and SMOTEEEN resampling further improved performance, reaching a ROC-AUC of 0.949.
  • The AutoML approach facilitated efficient development of customized AI models.

Conclusions:

  • AutoML enables scalable and efficient development of hospital-specific AI models for IDH prediction with minimal manual input.
  • AI-powered prediction systems are valuable for early identification and management of IDH.
  • This technology contributes to improved patient safety and better hemodialysis outcomes.