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 Concept Videos

Facial Feedback Hypothesis01:24

Facial Feedback Hypothesis

Charles Darwin proposed that facial expressions are an evolutionary adaptation for communication. He argued that these expressions are not influenced by culture but are universal across species. For example, a snarling expression with exposed teeth signals a threat in many animals, including humans. Darwin also suggested that displaying an emotion can intensify the feeling. Smiling, for example, could enhance one's sense of happiness. This idea laid the foundation for understanding the role of...

You might also read

Related Articles

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

Sort by
Same author

A Four-Year Prospective Pilot Study of Newborn Screening for Late-Onset Proximal Urea-Cycle Disorders in Hyogo Prefecture in Japan.

International journal of neonatal screening·2026
Same author

Predicting ordinal clinical outcomes in at-risk mental states: a multimodal approach.

Frontiers in psychiatry·2026
Same author

Local chemoarchitecture explains widespread lower cortical thickness associated with clinical high risk for psychosis.

Molecular psychiatry·2026
Same author

Toxicity of the novel mercury species α-mercuri-acetaldehyde and α-mercuri-acetic acid, in comparison with that of methylmercury, in rats.

The Journal of toxicological sciences·2026
Same author

Fully Automated Serum LC-MS/MS Platform and Pediatric Reference Intervals for Organic Acids, Amino Acids, and Acylcarnitines in Children (Ages 0-6 Years): Toward Quantitative Diagnosis of Inborn Errors of Metabolism.

Diagnostics (Basel, Switzerland)·2026
Same author

LRRC8A Inhibition Overcomes Chemoresistance by Downregulating MRP3 and CYP3A4 in the 3D Spheroid Model of Human Breast Cancer Cells.

International journal of molecular sciences·2026
Same journal

Pleural Toxocariasis Presenting as Eosinophilic Pleural Effusion: A Case Report.

Cureus·2026
Same journal

Left Clavicular Pain Following Splenic Rupture After Colonoscopy: A Variant of Kehr's Sign?

Cureus·2026
Same journal

Severe Polyhydramnios Associated With Antenatal Bartter Syndrome.

Cureus·2026
Same journal

Focal Takotsubo Syndrome Mimicking a Distal Coronary Pathology: A Case Report.

Cureus·2026
Same journal

Metachronous Colorectal Carcinomas and Pancreatic Metastasis in Clinically Suspected Lynch Syndrome: An 18-Year Oncologic Course.

Cureus·2026
Same journal

Regional Blocks in the Era of the Opioid Crisis: Evaluating Their Opioid-Sparing Effect.

Cureus·2026
See all related articles

Related Experiment Video

Updated: Jun 2, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

Real-Time Estimation of Numerical Rating Scale (NRS) Scores Using Machine Learning-Based Facial Expression Analysis:

Kentaro Uejima1, Tsutomu Takahashi1, Miki Matsui2

  • 1School of Pharmacy, Nihon University, Chiba, JPN.

Cureus
|June 1, 2026
PubMed
Summary
This summary is machine-generated.

This study developed an AI pipeline to estimate pain using facial expressions, improving accuracy for pediatric and elderly patients with communication barriers. The system shows promise as a complementary pain assessment tool.

Keywords:
computer visionfacial expression analysismachine learningnon-verbal communicationnumerical rating scalepain assessmentpalliative careproof-of-concept

More Related Videos

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

Related Experiment Videos

Last Updated: Jun 2, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

Area of Science:

  • Medical technology
  • Artificial intelligence
  • Pain management

Background:

  • Accurate pain assessment is crucial for cancer pain management.
  • Subjective pain scales like the Numerical Rating Scale (NRS) have limitations in patients with impaired verbal communication.
  • This includes pediatric and elderly populations.

Purpose of the Study:

  • To develop a real-time facial expression-based pipeline for estimating the Numerical Rating Scale (NRS) pain scores.
  • To evaluate the technical feasibility of this approach as a proof of concept (PoC).

Main Methods:

  • A Python-based real-time analysis pipeline was created, integrating MediaPipe for facial detection and DeepFace for emotion estimation.
  • Seven emotion probability scores from video streams were used to predict NRS values via regression models, including Random Forest (RF).
  • Technical validation involved synthetic datasets and leave-one-out cross-validation (LOOCV), with performance measured by Spearman's rank correlation coefficient (ρ) and mean absolute error (MAE).

Main Results:

  • The RF model achieved significant accuracy in both pediatric (ρ = 0.7383, MAE = 1.5195) and elderly (ρ = 0.7566, MAE = 1.5760) datasets, outperforming the baseline model.
  • Feature importance analysis highlighted "Fear" as a key predictor in both groups.
  • "Neutral" expression also showed notable importance in the elderly dataset.

Conclusions:

  • The study successfully demonstrated the technical feasibility of an AI-driven facial expression analysis pipeline for real-time NRS estimation.
  • This AI approach shows potential as a supplementary pain assessment method for individuals with limited verbal communication.
  • Further clinical validation is required to confirm its practical application.