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

Modeling in Therapy

Modeling in Therapy

Modeling, a key technique in therapy, uses observational learning to help clients acquire and practice new skills by watching therapists demonstrate desired behaviors. This approach, rooted in Albert Bandura's concept of vicarious learning, plays a significant role in therapeutic interventions for various psychological conditions, including social anxiety, ADHD, and depression.
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in...

You might also read

Related Articles

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

Sort by

Same author

Multimodal LLM vs. Human-Measured Features for AI Predictions of Autism in Home Videos.

Algorithms·2026

Same author

Ensemble Modeling of Multiple Physical Indicators to Dynamically Phenotype Autism Spectrum Disorder.

Algorithms·2026

Same author

Compact subsets of autism screening items predict clinical diagnoses with a machine learning analysis of the QCHAT-10.

Scientific reports·2025

Same author

Aiding Large Language Models Using Clinical Scoresheets for Neurobehavioral Diagnostic Classification From Text: Algorithm Development and Validation.

JMIR AI·2025

Same author

An analysis of the real world performance of an artificial intelligence based autism diagnostic.

Scientific reports·2025

Same author

Temporal trends and risk factors for bleeding and thrombosis in pediatric ECMO: A multicenter cohort study.

Perfusion·2025

Search research articles

Related Experiment Video

Updated: Feb 28, 2026

A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis

A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis

Published on: May 10, 2022

Abstention and Threshold Identification for Uncertainty Management in Clinical Decision Tools: A Case Study using

Aiden Ko¹, Aaron Kline², Kaitlyn Dunlap³

¹Department of Pediatrics (Clinical Informatics), Stanford University, Stanford, CA 94305, USA, aidensko@stanford.edu.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing

|February 27, 2026

Summary

This study introduces abstention, a method for managing uncertainty in artificial intelligence (AI) diagnostic classifiers. It improves clinical decision-making by allowing AI to abstain from uncertain predictions, especially in complex pediatric autism assessments.

More Related Videos

Behavioral Assessment of Hearing in 2 to 4 Year-old Children: A Two-interval, Observer-based Procedure Using Conditioned Play-based Responses

Behavioral Assessment of Hearing in 2 to 4 Year-old Children: A Two-interval, Observer-based Procedure Using Conditioned Play-based Responses

Published on: January 23, 2017

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Related Experiment Videos

Last Updated: Feb 28, 2026

A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis

A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis

Published on: May 10, 2022

Behavioral Assessment of Hearing in 2 to 4 Year-old Children: A Two-interval, Observer-based Procedure Using Conditioned Play-based Responses

Behavioral Assessment of Hearing in 2 to 4 Year-old Children: A Two-interval, Observer-based Procedure Using Conditioned Play-based Responses

Published on: January 23, 2017

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Area of Science:

Artificial Intelligence in Healthcare
Clinical Decision Support Systems
Machine Learning for Diagnostics

Background:

Uncertainty quantification is underdeveloped in AI clinical decision tools.
Managing AI uncertainty is crucial for safe healthcare integration.
Current AI diagnostic tools lack robust uncertainty management.

Purpose of the Study:

To investigate abstention as a practical mechanism for managing uncertainty in diagnostic classifiers.
To evaluate abstention performance on a noisy dataset of pediatric autism video assessments.
To demonstrate how abstention can support clinical decision-making by quantifying and managing AI uncertainty.

Main Methods:

Applied abstention strategies to existing autism classifiers trained on diagnostic data.
Evaluated performance on a heterogeneous dataset of pediatric autism video assessments.
Compared baseline performance with various thresholding configurations for abstention.

Main Results:

Abstention strategies were tested on a purposefully noisy dataset.
Performance was compared across different thresholding configurations, balancing coverage and clinical metrics.
Demonstrated use cases for prioritizing sensitivity, specificity, or balanced improvements (Youden's J).

Conclusions:

Abstention provides a concrete method for uncertainty management in diagnostic AI.
Integrating abstention enhances the reliability and clinical utility of AI decision tools.
This approach enables both uncertainty quantification and management in healthcare AI.