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

Self-healing chitosan-catechol hydrogel with tailored self-assembled fibrillar or micellar structures for biomedical applications.

Carbohydrate polymers·2026

Same author

Building MCP-native hierarchical AI scientist ecosystems: a perspective on scaling multi-agent scientific discovery.

Frontiers in artificial intelligence·2026

Same author

Biomechanical effects of various occlusal conditions and orthodontic force levels on mandibular canine distalization: a finite element analysis.

Scientific reports·2026

Same author

Blue-Light-Free Orange-Red Organic Light-Emitting Diodes With Less Influence on Melatonin Secretion.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same author

Fundamental safety-capability trade-offs in fine-tuning large language models.

PNAS nexus·2026

Same author

Effects of bright light and near-infrared light on insomnia symptoms in community-dwelling older adults: a randomized clinical trial.

Photodiagnosis and photodynamic therapy·2026

Search research articles

Related Experiment Video

Updated: Jun 21, 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

CURE: A deep learning framework pre-trained on large-scale patient data for treatment effect estimation.

Ruoqi Liu¹, Pin-Yu Chen², Ping Zhang^1,3,4

¹Department of Computer Science and Engineering, The Ohio State University, 2015 Neil Avenue, Columbus, OH 43210, USA.

Patterns (New York, N.Y.)

|July 15, 2024

Summary

This summary is machine-generated.

CURE, a new framework for causal treatment effect estimation (TEE), uses unlabeled patient data for pre-training and fine-tuning on labeled data. This approach improves TEE accuracy, outperforming existing methods and aiding clinical trial analysis.

Keywords:

pre-training and fine-tuning real-world patient data treatment effect estimation

More Related Videos

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Related Experiment Videos

Last Updated: Jun 21, 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

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Area of Science:

Biostatistics
Machine Learning
Health Informatics

Background:

Treatment effect estimation (TEE) is crucial for identifying causal effects of treatments.
Current machine learning methods for TEE struggle with limited labeled data.
Observational data presents challenges for accurate TEE.

Purpose of the Study:

To propose CURE (Causal treatment effect estimation), a novel pre-training and fine-tuning framework for TEE.
To enhance TEE performance using large-scale unlabeled patient data.
To develop a robust method for estimating heterogeneous treatment effects.

Main Methods:

CURE employs a pre-training phase on unlabeled patient data to learn contextual representations.
A sequence encoding approach is used to embed structure and time in longitudinal patient data.
The framework is fine-tuned on labeled data for specific TEE tasks.

Main Results:

CURE significantly outperforms state-of-the-art methods in TEE.
Achieved a 7% increase in area under the precision-recall curve.
Demonstrated an 8% rise in precision for estimating heterogeneous effects.

Conclusions:

CURE effectively estimates causal treatment effects from observational data.
The framework's performance was validated against four randomized clinical trials.
CURE shows potential to supplement traditional clinical trial methodologies.