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: May 7, 2026

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

Multi-scale data improves performance of machine learning model for long COVID identification.

Christopher Guardo¹, Zhang Xinmeng², Srushti Gangireddy¹

¹Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, USA.

Communications Medicine

|May 5, 2026

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

Prevalence and Clinical Impact of Pathogenic Variants in Cardiomyopathy Genes Among Individuals with Cardiac Conduction Disorders.

medRxiv : the preprint server for health sciences·2026

Same author

A comparison of Fast Healthcare Interoperability Resources and Observational Medical Mutcomes Partnership electronic health record data within the All of Us Research Program.

Journal of the American Medical Informatics Association : JAMIA·2026

Same author

Implementing trust in non-small cell lung cancer diagnosis with a conformalized uncertainty-aware AI framework.

Nature biomedical engineering·2026

Same author

Generating synthetic multi-national longitudinal cohorts for clinically grounded HIV research.

Nature communications·2026

Same author

Critical illness expands a transcriptionally distinct hypometabolic CD8<sup>+</sup> T effector program associated with respiratory failure and mortality.

bioRxiv : the preprint server for biology·2026

Same author

Evaluating Large Language Models for Translating Multimodal Phenotype Documentations into Executable EHR Phenotyping Algorithms.

medRxiv : the preprint server for health sciences·2026

Same journal

OncoMimic peptide-based immunotherapy EO2401 induces shared T cell clusters in patients with adrenal cancer.

Communications medicine·2026

Same journal

Brain aging in Type II GM1 gangliosidosis.

Communications medicine·2026

Same journal

The roles of neuroticism, genetic susceptibility, and amygdala structure in chronic musculoskeletal pain onset and recovery.

Communications medicine·2026

Same journal

Rostral lesion shift and tract-specific degeneration drive functional heterogeneity in degenerative cervical myelopathy.

Communications medicine·2026

Same journal

A wearable device dataset for mental health assessment using laser Doppler flowmetry and fluorescence spectroscopy sensors.

Communications medicine·2026

Same journal

Lipidomic profiling reveals a distinct lipidomic signature of early gestational diabetes.

Communications medicine·2026

See all related articles

Summary

This summary is machine-generated.

Integrating social, behavioral, and genetic data with electronic health records improves long COVID prediction models. This multi-scale approach enhances risk stratification for personalized interventions, though cost-effectiveness requires consideration.

Area of Science:

Genomics
Epidemiology
Health Informatics

Background:

Long COVID impacts a significant portion of SARS-CoV-2 survivors, with current predictive models having limitations.
Existing research, including the National COVID Cohort Collaborative (N3C), primarily uses electronic health record (EHR) data.
Social, behavioral, and genetic factors are increasingly recognized as crucial contributors to long COVID risk.

Purpose of the Study:

To investigate the impact of integrating multi-scale data (EHR, survey, genomic) on long COVID risk prediction.
To compare the performance of a multi-scale data model against an EHR-only model.

Main Methods:

Utilized a cohort of over 17,200 SARS-CoV-2 infected individuals from the NIH All of Us Research Program.
Integrated electronic health record (EHR) data with survey-based and genomic information.

More Related Videos

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Related Experiment Videos

Last Updated: May 7, 2026

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Developed and evaluated predictive models using area under the receiver operating curve (AUC).

Main Results:

The multi-scale data model achieved a higher AUC (0.748) compared to the EHR-only model (0.736).
Active-duty service status and self-reported fatigue were identified as significant predictors from survey data.
The integration of diverse data sources demonstrated improved predictive performance.

Conclusions:

Incorporating multi-scale data significantly enhances risk stratification for long COVID.
Findings support the development of personalized interventions for long COVID management.
The modest accuracy increase necessitates consideration of the costs associated with collecting genetic and survey data.