Classification of elderly pain severity from automated video clip facial action unit analysis: A study from a Thai data repository
Data from 255 Thais with chronic pain were collected at Chiang Mai Medical School Hospital. After the patients self-rated their level of pain, a smartphone camera was used to capture faces for 10 s at a one-meter distance. For those unable to self-rate, a video recording was taken immediately after...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-10-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2022.942248/full |
| _version_ | 1797997205383020544 |
|---|---|
| author | Patama Gomutbutra Patama Gomutbutra Adisak Kittisares Atigorn Sanguansri Noppon Choosri Passakorn Sawaddiruk Puriwat Fakfum Peerasak Lerttrakarnnon Sompob Saralamba |
| author_facet | Patama Gomutbutra Patama Gomutbutra Adisak Kittisares Atigorn Sanguansri Noppon Choosri Passakorn Sawaddiruk Puriwat Fakfum Peerasak Lerttrakarnnon Sompob Saralamba |
| author_sort | Patama Gomutbutra |
| collection | DOAJ |
| description | Data from 255 Thais with chronic pain were collected at Chiang Mai Medical School Hospital. After the patients self-rated their level of pain, a smartphone camera was used to capture faces for 10 s at a one-meter distance. For those unable to self-rate, a video recording was taken immediately after the move that causes the pain. The trained assistant rated each video clip for the pain assessment in advanced dementia (PAINAD). The pain was classified into three levels: mild, moderate, and severe. OpenFace© was used to convert the video clips into 18 facial action units (FAUs). Five classification models were used, including logistic regression, multilayer perception, naïve Bayes, decision tree, k-nearest neighbors (KNN), and support vector machine (SVM). Out of the models that only used FAU described in the literature (FAU 4, 6, 7, 9, 10, 25, 26, 27, and 45), multilayer perception is the most accurate, at 50%. The SVM model using FAU 1, 2, 4, 7, 9, 10, 12, 20, 25, and 45, and gender had the best accuracy of 58% among the machine learning selection features. Our open-source experiment for automatically analyzing video clips for FAUs is not robust for classifying pain in the elderly. The consensus method to transform facial recognition algorithm values comparable to the human ratings, and international good practice for reciprocal sharing of data may improve the accuracy and feasibility of the machine learning's facial pain rater. |
| first_indexed | 2024-04-11T10:29:28Z |
| format | Article |
| id | doaj.art-8e2056f8d59a4970b0f320796b3e2568 |
| institution | Directory Open Access Journal |
| issn | 2624-8212 |
| language | English |
| last_indexed | 2024-04-11T10:29:28Z |
| publishDate | 2022-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Artificial Intelligence |
| spelling | doaj.art-8e2056f8d59a4970b0f320796b3e25682022-12-22T04:29:28ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122022-10-01510.3389/frai.2022.942248942248Classification of elderly pain severity from automated video clip facial action unit analysis: A study from a Thai data repositoryPatama Gomutbutra0Patama Gomutbutra1Adisak Kittisares2Atigorn Sanguansri3Noppon Choosri4Passakorn Sawaddiruk5Puriwat Fakfum6Peerasak Lerttrakarnnon7Sompob Saralamba8Aging and Aging Palliative Care Research Cluster, Department of Family Medicine, Faculty of Medicine, Chiang Mai University, Chiang Mai, ThailandNorthern Neuroscience Center, Faculty of Medicine, Chiang Mai University, Chiang Mai, ThailandNorthern Neuroscience Center, Faculty of Medicine, Chiang Mai University, Chiang Mai, ThailandCollege of Arts, Media, and Technology, Chiang Mai University, Chiang Mai, ThailandCollege of Arts, Media, and Technology, Chiang Mai University, Chiang Mai, ThailandDepartment of Anesthesiology, Faculty of Medicine, Chiang Mai University, Chiang Mai, ThailandAging and Aging Palliative Care Research Cluster, Department of Family Medicine, Faculty of Medicine, Chiang Mai University, Chiang Mai, ThailandAging and Aging Palliative Care Research Cluster, Department of Family Medicine, Faculty of Medicine, Chiang Mai University, Chiang Mai, ThailandMahidol-Oxford Tropical Medicine Research Unit, Faculty of Tropical Medicine, Mahidol University, Bangkok, ThailandData from 255 Thais with chronic pain were collected at Chiang Mai Medical School Hospital. After the patients self-rated their level of pain, a smartphone camera was used to capture faces for 10 s at a one-meter distance. For those unable to self-rate, a video recording was taken immediately after the move that causes the pain. The trained assistant rated each video clip for the pain assessment in advanced dementia (PAINAD). The pain was classified into three levels: mild, moderate, and severe. OpenFace© was used to convert the video clips into 18 facial action units (FAUs). Five classification models were used, including logistic regression, multilayer perception, naïve Bayes, decision tree, k-nearest neighbors (KNN), and support vector machine (SVM). Out of the models that only used FAU described in the literature (FAU 4, 6, 7, 9, 10, 25, 26, 27, and 45), multilayer perception is the most accurate, at 50%. The SVM model using FAU 1, 2, 4, 7, 9, 10, 12, 20, 25, and 45, and gender had the best accuracy of 58% among the machine learning selection features. Our open-source experiment for automatically analyzing video clips for FAUs is not robust for classifying pain in the elderly. The consensus method to transform facial recognition algorithm values comparable to the human ratings, and international good practice for reciprocal sharing of data may improve the accuracy and feasibility of the machine learning's facial pain rater.https://www.frontiersin.org/articles/10.3389/frai.2022.942248/fullfacial action coding systemchronic painelderlydementiaAsian |
| spellingShingle | Patama Gomutbutra Patama Gomutbutra Adisak Kittisares Atigorn Sanguansri Noppon Choosri Passakorn Sawaddiruk Puriwat Fakfum Peerasak Lerttrakarnnon Sompob Saralamba Classification of elderly pain severity from automated video clip facial action unit analysis: A study from a Thai data repository Frontiers in Artificial Intelligence facial action coding system chronic pain elderly dementia Asian |
| title | Classification of elderly pain severity from automated video clip facial action unit analysis: A study from a Thai data repository |
| title_full | Classification of elderly pain severity from automated video clip facial action unit analysis: A study from a Thai data repository |
| title_fullStr | Classification of elderly pain severity from automated video clip facial action unit analysis: A study from a Thai data repository |
| title_full_unstemmed | Classification of elderly pain severity from automated video clip facial action unit analysis: A study from a Thai data repository |
| title_short | Classification of elderly pain severity from automated video clip facial action unit analysis: A study from a Thai data repository |
| title_sort | classification of elderly pain severity from automated video clip facial action unit analysis a study from a thai data repository |
| topic | facial action coding system chronic pain elderly dementia Asian |
| url | https://www.frontiersin.org/articles/10.3389/frai.2022.942248/full |
| work_keys_str_mv | AT patamagomutbutra classificationofelderlypainseverityfromautomatedvideoclipfacialactionunitanalysisastudyfromathaidatarepository AT patamagomutbutra classificationofelderlypainseverityfromautomatedvideoclipfacialactionunitanalysisastudyfromathaidatarepository AT adisakkittisares classificationofelderlypainseverityfromautomatedvideoclipfacialactionunitanalysisastudyfromathaidatarepository AT atigornsanguansri classificationofelderlypainseverityfromautomatedvideoclipfacialactionunitanalysisastudyfromathaidatarepository AT nopponchoosri classificationofelderlypainseverityfromautomatedvideoclipfacialactionunitanalysisastudyfromathaidatarepository AT passakornsawaddiruk classificationofelderlypainseverityfromautomatedvideoclipfacialactionunitanalysisastudyfromathaidatarepository AT puriwatfakfum classificationofelderlypainseverityfromautomatedvideoclipfacialactionunitanalysisastudyfromathaidatarepository AT peerasaklerttrakarnnon classificationofelderlypainseverityfromautomatedvideoclipfacialactionunitanalysisastudyfromathaidatarepository AT sompobsaralamba classificationofelderlypainseverityfromautomatedvideoclipfacialactionunitanalysisastudyfromathaidatarepository |