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

Search research articles

Related Experiment Video

Updated: Jan 10, 2026

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

Development and Validation of a Hybrid Machine Learning Model to Predict Lung Transplant Outcomes.

Gaurav Sharma^1,2,3, Vineet Kumar Kamal⁴, Srinivas Bollineni⁵

¹Department of Cardiovascular and Thoracic Surgery, University of Texas Southwestern Medical Center, Dallas.

JAMA Network Open

|November 25, 2025

Summary

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

Performability evaluation, validation and optimization for the steam generation system of a coal-fired thermal power plant.

MethodsX·2022

Same author

A Comparative Study of Blood Loss With and Without Infusion of Tranexamic Acid in Total Knee Replacement.

Cureus·2022

Same author

Reply to Oren et al., "New Phylum Names Harmonize Prokaryotic Nomenclature".

mBio·2022

Same author

Ecological variations in adult life table attributes of Aedes aegypti (L.) from the desert and coastal regions of India.

Medical and veterinary entomology·2022

Same author

Registration of polarimetric images for in vivo skin diagnostics.

Journal of biomedical optics·2022

Same author

High interfacial charge separation in visible-light active Z- scheme g-C<sub>3</sub>N<sub>4</sub>/MoS<sub>2</sub> heterojunction: Mechanism and degradation of sulfasalazine.

Chemosphere·2022

A new hybrid machine learning model offers improved risk stratification for lung transplant recipients, predicting survival outcomes with moderate accuracy. This tool aids in personalized care and shared decision-making for patients undergoing lung transplantation.

Area of Science:

Transplantation Medicine
Machine Learning in Healthcare
Prognostic Modeling

Background:

Long-term survival post-lung transplant is highly variable.
Current risk stratification tools lack accuracy and clinical utility.
Need for improved methods to predict lung transplant outcomes.

Purpose of the Study:

Develop and validate an interpretable hybrid machine learning model.
Predict time to death or retransplant at 1, 5, and 10 years post-lung transplant.
Assess the clinical utility of the developed prognostic model.

Main Methods:

Utilized a large cohort from the United Network for Organ Sharing-Organ Procurement and Transplantation Network (UNOS-OPTN).
Employed the AutoScore-Survival framework combining random survival forests and Cox regression.

Related Experiment Videos

Last Updated: Jan 10, 2026

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

Evaluated model performance using discrimination metrics (AUC, C-index) and calibration.

Main Results:

The hybrid model identified nine key predictors of lung transplant outcomes.
Demonstrated moderate discrimination (iAUC 0.61, C-index 0.64) in the testing set.
Showed good calibration and consistent net benefit across decision thresholds.

Conclusions:

The interpretable hybrid model provides practical, personalized risk stratification for lung transplant recipients.
The model supports shared decision-making between clinicians and patients.
A web-based calculator enhances accessibility and clinical utility.