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 Video

Updated: Jul 8, 2026

Estimate the Cognitive Load Using Electrocardiographic Measure: A Human-AI Collaborative Task
07:08

Estimate the Cognitive Load Using Electrocardiographic Measure: A Human-AI Collaborative Task

Published on: December 5, 2025

177

Explainable Multitask Burnout Prediction Using Adaptive Deep Learning (EMBRACE) for Resident Physicians: Algorithm

Saima Alam1, Mohammad Arif Ul Alam2,3,4

  • 1Merrimack Health Methuen Hospital, Methuen, MA, United States.

JMIR AI
|January 8, 2026
PubMed
Summary

Related Concept Videos

Acute Coronary Syndrome III: Diagnostic Studies01:30

Acute Coronary Syndrome III: Diagnostic Studies

Diagnosing acute coronary syndrome or ACS begins with a thorough patient history. Notable symptoms include central, crushing chest pain radiating to the left arm, neck, jaw, or back, along with shortness of breath, sweating (diaphoresis), nausea, vomiting, dizziness, and palpitations.It is crucial to note any history of cardiac illnesses and assess risk factors, including age, gender, smoking, hypertension, diabetes, hyperlipidemia, and a sedentary lifestyle.During physical examination, vital...

You might also read

Related Articles

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

Sort by
Same author

Recent Advancements in Wearable Hydration-Monitoring Technologies: Scoping Review of Sensors, Trends, and Future Directions.

JMIR mHealth and uHealth·2025
Same author

Community-Wide Monitoring of Lead in Drinking Water Distribution Systems Using Hand-Held Voltammetric Sensors and Geographic Information Systems.

ACS omega·2025
Same author

Effects of Antidepressants on COVID-19 Outcomes: Retrospective Study on Large-Scale Electronic Health Record Data.

Interactive journal of medical research·2023
Same author

Nursing Perspectives on the Impacts of COVID-19: Social Media Content Analysis.

JMIR formative research·2021

This study introduces EMBRACE, a novel AI framework using wearable sensors to predict and explain burnout in resident physicians. It offers actionable insights for early intervention and improved physician well-being.

Area of Science:

  • Machine Learning in Healthcare
  • Wearable Sensor Technology
  • Physician Burnout Research

Background:

  • Medical residents face high stress and burnout due to demanding schedules.
  • Existing machine learning models for burnout lack clinical explainability.
  • Wearable sensors offer potential for objective burnout prediction.

Purpose of the Study:

  • To present EMBRACE, an Explainable Multitask Burnout Prediction framework.
  • To predict and explain future burnout in resident physicians using adaptive deep learning.
  • To enhance clinical trust through explainable AI (XAI) techniques.

Main Methods:

  • Developed an adaptive multitask deep learning framework (EMBRACE).
  • Utilized wearable sensor data for predicting activities and burnout levels.
Keywords:
clinical explainabilityfuture burnout predictionhealth care informaticsmachine learningmultitask learningwearable sensors

Related Experiment Videos

Last Updated: Jul 8, 2026

Estimate the Cognitive Load Using Electrocardiographic Measure: A Human-AI Collaborative Task
07:08

Estimate the Cognitive Load Using Electrocardiographic Measure: A Human-AI Collaborative Task

Published on: December 5, 2025

177
  • Integrated SHAP (Shapley Additive Explanations) for model interpretability.
  • Validated on three datasets, including a proprietary resident physician dataset.

    • Main Results:

    • EMBRACE achieved high accuracy in predicting activities, burnout levels, and survey responses across datasets.
    • SHAP analysis identified key burnout predictors like heart rate variability and sedentary behavior.
    • 91% of participants found the feature importance summaries satisfactory.

    Conclusions:

    • EMBRACE offers a clinically explainable and actionable solution for early burnout detection.
    • The framework demonstrates robustness and generalizability across diverse datasets.
    • Future work includes scaling the model and assessing long-term impact on physician well-being.