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

Sensitivity, Specificity, and Predicted Value

Sensitivity, Specificity, and Predicted Value

In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...

You might also read

Related Articles

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

Sort by

Same author

Engineered antibodies bypass bacterial immune evasion to drive complement-mediated protection against lethal infections.

Science translational medicine·2026

Same author

Magneto-optical microscopy platform for quantitative imaging of hemozoin in blood for malaria diagnosis.

Biomedical optics express·2026

Same author

Ear-Worn Inertial Sensors Can Predict Gait Metrics and Reconstruct Vertical Ground Reaction Force Curves During Running.

Journal of applied biomechanics·2026

Same author

Microfluidic platform for automatic quantification of malaria parasite invasion under physiological flow conditions.

Lab on a chip·2026

Same author

Expression of nano-engineered RNA organelles in bacteria.

Nature communications·2026

Same author

Invasion preferences suggest a possible role for Plasmodium falciparum parasites in the expansion of Duffy negativity in West and Central Africa.

Molecular biology and evolution·2026

Search research articles

Related Experiment Video

Updated: Jul 31, 2025

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

Evaluating Listening Performance for COVID-19 Detection by Clinicians and Machine Learning: Comparative Study.

Jing Han¹, Marco Montagna², Andreas Grammenos¹

¹Department of Computer Science and Technology, University of Cambridge, Cambridge, United Kingdom.

Journal of Medical Internet Research

|May 1, 2023

Summary

This summary is machine-generated.

Machine learning models show promise in diagnosing COVID-19 from respiratory sounds, outperforming clinicians. Combining AI and human expertise offers the best diagnostic accuracy and confidence in audio-based respiratory assessments.

Keywords:

COVID-19 detection audio analysis clinical decisions clinicians deep learning detection machine learning mobile health respiratory respiratory diagnosis respiratory disease diagnosis

More Related Videos

Semi-Automated Analysis of Peak Amplitude and Latency for Auditory Brainstem Response Waveforms Using R

Semi-Automated Analysis of Peak Amplitude and Latency for Auditory Brainstem Response Waveforms Using R

Published on: December 9, 2022

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Published on: March 24, 2023

Related Experiment Videos

Last Updated: Jul 31, 2025

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

Semi-Automated Analysis of Peak Amplitude and Latency for Auditory Brainstem Response Waveforms Using R

Semi-Automated Analysis of Peak Amplitude and Latency for Auditory Brainstem Response Waveforms Using R

Published on: December 9, 2022

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Published on: March 24, 2023

Area of Science:

Medical Informatics
Artificial Intelligence in Medicine
Respiratory Medicine

Background:

Machine learning (ML) and human performance in audio-based respiratory diagnosis are underexplored.
Previous comparisons between humans and machines exist in various health domains.

Purpose of the Study:

To compare the performance of human clinicians and an ML model in predicting COVID-19 using respiratory sound recordings.
To investigate the potential of combining human and ML predictions for improved diagnostic outcomes.

Main Methods:

Compared predictions from 36 clinicians and an ML model on 24 audio samples (12 COVID-19 positive).
ML model was trained on 1162 respiratory sound samples.
Audio samples included voice, cough, and breathing sounds (approx. 20 seconds each).

Main Results:

The ML model achieved higher sensitivity (0.75) and specificity (0.83) than the best clinician (0.67 sensitivity, 0.75 specificity).
Combining clinician and ML model predictions significantly improved performance, reaching 0.83 sensitivity and 0.92 specificity.
Cooperative approach enhanced both accuracy and confidence in predictions.

Conclusions:

ML models can effectively predict COVID-19 from respiratory sounds.
A collaborative approach between clinicians and ML models can lead to superior diagnostic decisions.
Integrating AI with human expertise enhances confidence and accuracy in audio-based respiratory diagnosis.