An experimental study of objective pain measurement using pupillary response based on genetic algorithm and artificial neural network

• Published in: Applied intelligence (Dordrecht, Netherlands) Vol. 52; no. 2; pp. 1145 - 1156
• Main Authors: Wang, Li, Guo, Yikang, Dalip, Biren, Xiao, Yan, Urman, Richard D., Lin, Yingzi
• Format: Journal Article
• Language: English
• Published: New York Springer US 01-01-2022; Springer Nature B.V
• Subjects: Artificial Intelligence; Artificial neural networks; Computer Science; Diameters; Feature extraction; Feature selection; Genetic algorithms; Learning theory; Machine learning; Machines; Manufacturing; Mechanical Engineering; Neural networks; Pain; Processes; Artificial neural network; Pupillary response; Genetic algorithm; Objective pain measurement; Machine learning algorithm
• ISSN: 0924-669X; 1573-7497
• DOI: 10.1007/s10489-021-02458-4

Obtaining an objective measurement of the pain level of a patient has always been challenging for health care providers. The most common method of pain assessment in the hospital setting is asking the patients’ verbal ratings, which is considered to be a subjective approach. In order to get an objective pain level of a patient, we propose measuring pain level objectively using the pupillary response and machine learning algorithms. Thirty-two healthy subjects were enrolled in this study at Northeastern University. A painful stimulus was applied to healthy subjects by asking them to place their hands inside a bucket filled with iced water. We extracted 11 features from the pupil diameter data. To get the optimal subset of the features, a genetic algorithm (GA) was used to select features for the artificial neural network (ANN) classifier. Before feature selection, the f1-score of ANN was 54.0 ± 0.25% with all 11 features. After feature selection, ANN had the best performance with an accuracy of 81.0% using the selected feature subset, namely the Mean, the Root Mean Square (RMS), and the Pupillary Area Under Curve (PAUC). The experimental results suggested that pupillary response together with machine learning algorithms could be a promising method of objective pain level assessment. The outcomes of this study could improve patients’ experience of pain measurement in telehealthcare, especially during a pandemic when most people had to stay at home.