Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Establishing a health information exchange research network (HIERN) to support population health studies.

NPJ digital medicine·2026

Same author

Evaluating NLP Approaches to Extract Drug Indications.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026

Same author

When Science Outpaces Infrastructure: People, Process, and Technology Challenges for Precision Dosing in Children.

Clinical and translational science·2026

Same author

Healthcare provider approaches to managing the health harms of xylazine: A qualitative study.

Journal of substance use and addiction treatment·2026

Same author

THERA-IE: An AI-Enabled System for Therapeutic Indication Identification and Extraction from Biomedical Literature.

Studies in health technology and informatics·2026

Same author

From Food to Clinic: Mapping FoodOn to the UMLS to Enable Nutritional Decision Support.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026

Same journal

Letter to the Editor: Contralateral suppression indices and the need for outcome-based reference standards in primary aldosteronism.

Journal of vascular and interventional radiology : JVIR·2026

Same journal

Clarifying Recurrence, Bleeding Risk, and Procedural Burden in Central Renal Tumor Ablation.

Journal of vascular and interventional radiology : JVIR·2026

Same journal

Short- and long-term changes in renal function following percutaneous cryoablation: a comparison of endophytic versus exophytic renal tumors.

Journal of vascular and interventional radiology : JVIR·2026

Same journal

Multi-Center Randomized Trial Evaluating the Safety and Effectiveness of the Instylla Hydrogel Embolic System (HES) for Vascular Occlusion of Hypervascular Tumors.

Journal of vascular and interventional radiology : JVIR·2026

Same journal

Geometric Concordance of Deterministic Tract Planning With Operator-Selected Skin Entry Sites in CT-Guided Lung Biopsy.

Journal of vascular and interventional radiology : JVIR·2026

Same journal

Reply to "Clarifying Recurrence, Bleeding Risk, and Procedural Burden in Central Renal Tumor Ablation".

Journal of vascular and interventional radiology : JVIR·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 22, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Machine Learning Offers Exciting Potential for Predicting Postprocedural Outcomes: A Framework for Developing Random

Ishan Sinha¹, Dilum P Aluthge¹, Elizabeth S Chen²

¹Warren Alpert Medical School of Brown University, Providence, Rhode Island; Brown Center for Biomedical Informatics, Brown University, 233 Richmond Street, Box G-R, Providence, RI 02912.

Journal of Vascular and Interventional Radiology : JVIR

|May 8, 2020

Summary

This summary is machine-generated.

Random forest models accurately predict outcomes in interventional radiology (IR), including complications and length of stay. These machine learning tools show promise for future clinical decision support.

More Related Videos

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: Dec 22, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Area of Science:

Machine learning applications in medicine
Predictive modeling in healthcare
Interventional Radiology (IR) outcomes research

Background:

Interventional Radiology (IR) procedures carry inherent risks and resource utilization complexities.
Accurate prediction of patient outcomes is crucial for optimizing care and resource allocation in IR.
Developing robust predictive models can enhance clinical decision-making and patient management.

Purpose of the Study:

To evaluate the efficacy of random forest models in predicting key outcomes within Interventional Radiology.
To assess the predictive accuracy for procedure-specific complications, mortality, and length of stay.
To establish the potential of machine learning as a clinical decision support tool in IR.

Main Methods:

Utilized patient data from the National Inpatient Sample (2012-2014).
Developed random forest models to predict iatrogenic pneumothorax after CT-guided transthoracic biopsy (TTB), in-hospital mortality after transjugular intrahepatic portosystemic shunt (TIPS), and prolonged length of stay after uterine artery embolization (UAE).
Model performance was quantified using Area Under the Receiver Operating Characteristic Curve (AUROC) and maximum F1 score, with an AUROC significance threshold of 0.75.

Main Results:

The TTB model achieved an AUROC of 0.913, the TIPS model 0.788, and the UAE model 0.879.
Maximum F1 scores were 0.532 for TTB, 0.357 for TIPS, and 0.700 for UAE.
All developed models met the predefined AUROC significance criteria, indicating robust predictive performance.

Conclusions:

Machine learning models, specifically random forests, demonstrate significant potential for predicting diverse clinical outcomes in IR.
The models accurately predicted procedure-specific complications, mortality, and length of stay.
Future improvements in model performance are anticipated with the availability of larger, high-quality IR datasets.