| Popis: |
Background It is increasingly interesting to monitor pain severity in the elder by applying machine learning models. In previous studies, OpenFace© - a well-known automated facial analysis algorithm, was used to detect facial action units (FAUs) that initially need long hours of human coding. However, OpenFace© was developed using the dataset of young Caucasians in illicit pain in the lab. Therefore, this study aims to evaluate the accuracy and feasibility of the model using data from OpenFace© to classify pain severity in the Asian elderly in clinical settings. Methods The data from 255 Thai with chronic pain was collected in Chiang Mai Medical school hospital. The phone camera recorded faces for 10 seconds at a 1-meter distance briefly after the patients provided a self-rating pain severity. For those unable to self-rate, the video was recorded just after the move, which illicit pain. The trained assistant rated each video clip for the Pain Assessment in Advanced Dementia (PAINAD). The classify of pain severity was mild, moderate, or severe. OpenFace© process video clip into 18 FAUs. Five classification models were used, including logistic regression, multilayer perception, Naïve Bayes, decision tree, k-nearest neighbors (KNN), and support vector machine (SVM). Results Among the model that includes only FAU described in liturature (FAU 4,6,7,9,10,25,26,27 and 45), multilayer perception yields the most accuracy of 50%. Among the machine learning selection features, the SVM model for FAU 1, 2, 4, 7, 9, 10, 12, 20, 25, 45, and gender yielded the best accuracy of 58%. Conclusion Our experiment of open-source automatic video clip Facial Action Units analysis is not robust to classifying elder pain. Retraining facial action unit detection algorithms, enhancing frame selection strategy, and adding pain-related functions may improve the accuracy and feasibility of the model. |
