Pain Level Classification Using Eye-Tracking Metrics and Machine Learning Models

Pain estimation is a critical aspect of healthcare, particularly for patients who are unable to communicate discomfort effectively. The traditional methods, such as self-reporting or observational scales, are subjective and prone to bias. This study proposes a novel system for non-invasive pain esti...

Full description

Saved in:
Bibliographic Details
Main Authors: Oussama El Othmani, Sami Naouali
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Computers
Subjects:
Online Access:https://www.mdpi.com/2073-431X/14/6/212
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849433313369915392
author Oussama El Othmani
Sami Naouali
author_facet Oussama El Othmani
Sami Naouali
author_sort Oussama El Othmani
collection DOAJ
description Pain estimation is a critical aspect of healthcare, particularly for patients who are unable to communicate discomfort effectively. The traditional methods, such as self-reporting or observational scales, are subjective and prone to bias. This study proposes a novel system for non-invasive pain estimation using eye-tracking technology and advanced machine learning models. The methodology begins with preprocessing steps, including resizing, normalization, and data augmentation, to prepare high-quality input face images. DeepLabV3+ is employed for the precise segmentation of the eye and face regions, achieving 95% accuracy. Feature extraction is performed using VGG16, capturing key metrics such as pupil size, blink rate, and saccade velocity. Multiple machine learning models, including Random Forest, SVM, MLP, XGBoost, and NGBoost, are trained on the extracted features. XGBoost achieves the highest classification accuracy of 99.5%, demonstrating its robustness for pain level classification on a scale from 0 to 5. The feature analysis using SHAP values reveals that pupil size and blink rate contribute most to the predictions, with SHAP contribution scores of 0.42 and 0.35, respectively. The loss curves for DeepLabV3+ confirm rapid convergence during training, ensuring reliable segmentation. This work highlights the transformative potential of combining eye-tracking data with machine learning for non-invasive pain estimation, with significant applications in healthcare, human–computer interaction, and assistive technologies.
format Article
id doaj-art-1fdfe579958d4a41871690d24a3803fd
institution Kabale University
issn 2073-431X
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Computers
spelling doaj-art-1fdfe579958d4a41871690d24a3803fd2025-08-20T03:27:06ZengMDPI AGComputers2073-431X2025-05-0114621210.3390/computers14060212Pain Level Classification Using Eye-Tracking Metrics and Machine Learning ModelsOussama El Othmani0Sami Naouali1Information Systems Department, Military Academy of Fondouk Jedid, Nabeul 8012, TunisiaInformation Systems Department, College of Computer Science and Information Technology, King Faisal University, Al Ahsa 31982, Saudi ArabiaPain estimation is a critical aspect of healthcare, particularly for patients who are unable to communicate discomfort effectively. The traditional methods, such as self-reporting or observational scales, are subjective and prone to bias. This study proposes a novel system for non-invasive pain estimation using eye-tracking technology and advanced machine learning models. The methodology begins with preprocessing steps, including resizing, normalization, and data augmentation, to prepare high-quality input face images. DeepLabV3+ is employed for the precise segmentation of the eye and face regions, achieving 95% accuracy. Feature extraction is performed using VGG16, capturing key metrics such as pupil size, blink rate, and saccade velocity. Multiple machine learning models, including Random Forest, SVM, MLP, XGBoost, and NGBoost, are trained on the extracted features. XGBoost achieves the highest classification accuracy of 99.5%, demonstrating its robustness for pain level classification on a scale from 0 to 5. The feature analysis using SHAP values reveals that pupil size and blink rate contribute most to the predictions, with SHAP contribution scores of 0.42 and 0.35, respectively. The loss curves for DeepLabV3+ confirm rapid convergence during training, ensuring reliable segmentation. This work highlights the transformative potential of combining eye-tracking data with machine learning for non-invasive pain estimation, with significant applications in healthcare, human–computer interaction, and assistive technologies.https://www.mdpi.com/2073-431X/14/6/212eye-trackingpain estimationmachine learningDeepLabV3+feature extractionXGBoost
spellingShingle Oussama El Othmani
Sami Naouali
Pain Level Classification Using Eye-Tracking Metrics and Machine Learning Models
Computers
eye-tracking
pain estimation
machine learning
DeepLabV3+
feature extraction
XGBoost
title Pain Level Classification Using Eye-Tracking Metrics and Machine Learning Models
title_full Pain Level Classification Using Eye-Tracking Metrics and Machine Learning Models
title_fullStr Pain Level Classification Using Eye-Tracking Metrics and Machine Learning Models
title_full_unstemmed Pain Level Classification Using Eye-Tracking Metrics and Machine Learning Models
title_short Pain Level Classification Using Eye-Tracking Metrics and Machine Learning Models
title_sort pain level classification using eye tracking metrics and machine learning models
topic eye-tracking
pain estimation
machine learning
DeepLabV3+
feature extraction
XGBoost
url https://www.mdpi.com/2073-431X/14/6/212
work_keys_str_mv AT oussamaelothmani painlevelclassificationusingeyetrackingmetricsandmachinelearningmodels
AT saminaouali painlevelclassificationusingeyetrackingmetricsandmachinelearningmodels