Evaluating neonatal pain via fusing vision transformer and concept-cognitive computing.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
31 Oct 2024
31 Oct 2024
Historique:
received:
15
08
2024
accepted:
23
10
2024
medline:
1
11
2024
pubmed:
1
11
2024
entrez:
1
11
2024
Statut:
epublish
Résumé
In clinical nursing, neonatal pain assessment is a challenging task for preventing and controlling the impact of pain on neonatal development. To reduce the adverse effects of repetitive painful treatments during hospitalization on newborns, we propose a novel method (namely pain concept-cognitive computing model, PainC3M) for evaluating facial pain in newborns. In the fusion system, we first improve the attention mechanism of vision transformer by revising the node encoding way, considering the spatial structure, edge and centrality of nodes, and then use its corresponding encoder as a feature extractor to comprehensively extract image features. Second, we introduce a concept-cognitive computing model as a classifier to evaluate the level of pain. Finally, we evaluate our PainC3M on various open pain data sets and a real clinical pain data stream, and the experimental results demonstrate that our PainC3M is very effective for dynamic classification and superior to other comparative models. It also provides a good approach for pain assessment of individuals with aphasia (or dementia).
Identifiants
pubmed: 39482345
doi: 10.1038/s41598-024-77521-4
pii: 10.1038/s41598-024-77521-4
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
26201Subventions
Organisme : the Hunan Provincial Natural Science Foundation of China
ID : (No. 2024JJ7374, No. 2023JJ50456, No. 2024JJ7383)
Organisme : the Hunan Provincial Natural Science Foundation of China
ID : (No. 2024JJ7374, No. 2023JJ50456, No. 2024JJ7383)
Organisme : the Scientific Research Projects of the Hunan Provincial Department of Education
ID : (No. 21A0488, No. 22A0547, No. 23B0719)
Organisme : the Scientific Research Projects of the Hunan Provincial Department of Education
ID : (No. 21A0488, No. 22A0547, No. 23B0719)
Informations de copyright
© 2024. The Author(s).
Références
Doesburg, S. M. et al. Neonatal pain-related stress, functional cortical activity and visual-perceptual abilities in school-age children born at extremely low gestational age. Pain. 154 (10), 1946–1952 (2013).
doi: 10.1016/j.pain.2013.04.009
pubmed: 23711638
pmcid: 3778166
Mitchell, A. & Boss, B. J. Adverse effects of pain on the nervous system of newborns and young children: a review of the literature. J. Neurosci. Nurs. 34 (5), 228 (2002).
doi: 10.1097/01376517-200210000-00002
pubmed: 12391738
Suraseranivongse, K. A comparison of postoperative pain scales in neonates. Br. J. Anaesth. 97 (4), 540–544 (2006).
doi: 10.1093/bja/ael184
pubmed: 16885171
Grunau, R. E. et al. Bedside application of the Neonatal Facial Coding System in pain assessment of premature infants. Pain. 76 (3), 277–286 (1998).
doi: 10.1016/S0304-3959(98)00046-3
pubmed: 9718246
Lawrence, J. et al. The development of a tool to assess neonatal pain (NIPS). Neonatal Netw. NN. 12 (6), 59–66 (1993).
pubmed: 8413140
Stevens, B. et al. Premature infant Pain Profile: development and initial validation. Clin. J. Pain. 12 (1), 13–22 (1996).
doi: 10.1097/00002508-199603000-00004
pubmed: 8722730
Govindaraj, D. R. An automated pain assessment system using SVM classifier. Int. J. Adv. Sci. Technol. 29 (9s), 5463 (2021).
Corns, J. The Routledge Handbook of Philosophy of pain (Routledge, Taylor & Francis Group, 2017). https://doi.org/10.4324/9781315742205
Williams, A.C.C. Facial expression of pain: an evolutionary account. Behav. Brain Sci. 25 (4), 439–455 (2002).
pubmed: 12879700
Meina, Z. et al. Using artificial intelligence to improve pain assessment and pain management: a scoping review. Innov. Aging, Supplement_1. (2021). https://doi.org/10.1093/geroni/igab046.2409
Singh, S. K. & MIoT Medical internet of things in pain assessment. (2021). https://doi.org/10.1016/B978-0-12-821472-5.00005-3
Sen, K. & Pal, S. Alternative method for pain assessment using EMG and GSR. J. Mech. Med. Biology. 21 (06), 2150039. https://doi.org/10.1142/S0219519421500391 (2021).
doi: 10.1142/S0219519421500391
Krishnan, C., Sandhyavarshini, R. & Jeyakumar, V. Non-clinical pain assessment system—a pilot a study. J. Phys. Conf. Ser., 1917(1), 012008 (2021).
Hossain, M. B. et al. Automatic motion artifact detection in electrodermal activity data using machine learning. Biomed. Signal Process. Control. 74, 103483 (2022).
doi: 10.1016/j.bspc.2022.103483
Morabit, S. E. et al. Automatic pain estimation from facial expressions: a comparative analysis using off-the-Shelf CNN architectures. Electronics 2021(16).
Carlini, L. P., Ferreira, L. A., Coutrin, G. A. S., Varoto, V. V. & Thomaz, C. E. Mobile convolutional neural network for neonatal pain assessment. LatinX in Computer Vision (LXCV) workshop - Computer Vision and Pattern Recognition (CVPR) (2021).
Rodriguez, P. et al. Deep Pain: exploiting long short-term memory networks for facial expression classification. IEEE Transactions on Cybernatics. 52(2), 3314–3324 (2022).
Egede, J., Valstar, M. & Martinez, B. Fusing deep learned and hand-crafted features of appearance, shape, and dynamics for automatic pain estimation, 12th IEEE international conference on automatic face & gesture recognition (FG 2017). IEEE, 689–696 (2017).
Lopez Martinez, D. & Picard, R. Personalized automatic estimation of self-reported pain intensity from facial expressions, Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 70–79 (2017).
Al-Eidan, M., Al-Khalifa, R. & Al-Salman, H. Deep-learning-based models for pain recognition: a systematic review. Appl. Sci. 10 (17), 5984 (2020).
doi: 10.3390/app10175984
Vaswani, A. et al. Attention is all you need. https://doi.org/10.48550/arXiv.1706.03762 (2017).
Vaswani, A. et al. Tensor2Tensor for neural machine translation. https://doi.org/10.48550/arXiv.1803.07416 (2018).
Zhang, Y. Double-attention YOLO: vision transformer model based on image processing technology in complex environment of transmission line connection fittings and rust detection. Machines (2022). https://doi.org/10.3390/machines10111002
Parmar, N. et al. Image transformer https://doi.org/10.48550/arXiv.1802.05751 (2018).
Li G., Yao H., Le Y., Qin C.. Recaptured screen image identification based on vision transformer. J. Vis. Commun. Image Represent. 90, C. https://doi.org/10.1016/j.jvcir.2022.103692 (2022).
Yun, S., Jeong, M., Kim, R., Kang, J. & Kim, H. J. Graph Transformer Networks, 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada (2019).
Ying, C. et al. Do transformers really perform bad for graph representation? 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia (2021).
Wu, Y. et al. Large scale incremental learning, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 374–382 (2019).
Dosovitskiy, A. et al. An image is worth 16x16 words: transformers for image recognition at scale, International Conference on Learning Representations. (2021).
Mi, Y. L. et al. Research on granular concept cognitive learning system under MapReduce framework. Acta Electron. Sin.. 46, 289–297 (2018).
Mi, Y. L. Concept-cognitive computing theory and model, Ph.D. dissertation, School of Computer Science and Technology, University of Chinese Academy of SciencesJun., (2020).
Shi, Y., Mi, Y. L., Li, J. H. & Liu, W. Q. Concurrent concept-cognitive learning model for classification. Inf. Sci., 496, 65–81 (2019).
Mi, Y. L., Quan, P. & Shi, Y. Stream Concept-cognitive Computing System for Streaming Data Learning (TechRxiv, 2023).
Mi, Y. et al. Divide and conquer: a granular concept-cognitive computing system for dynamic classification decision making. Eur. J. Oper. Res. 308 (1), 255–273 (2023).
doi: 10.1016/j.ejor.2022.12.018
Yun, S. et al. Graph transformer networks. Proceedings of the 33rd International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, Article 1073, 11983–11993. https://dlnext.acm.org/doi/10.5555/3454287.3455360 (2019).
Veličković, P. et al. Graph attention networks. 6th International Conference on Learning Representations(ICLR) (2018).
Ying, C. et al. Do transformers really perform bad for graph representation ? 35th Conference on Neural Information Processing Systems (NeurIPS), Sydney, Australia (2021).
Ba, J.L., Lei, J.R.K. & Hinton, G.E. Layer Normalization https://doi.org/10.48550/arXiv.1607.06450 (2016).
Santurkar, S., Tsipras, D., Ilyas, A. & Madry, A. How does batch normalization help optimization? Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS’18). Curran Associates Inc., Red Hook, NY, USA, 2488–2498. https://dl.acm.org/doi/10.5555/3327144.3327174 (2018).
Tolstikhin, I. O. et al. Mlp-mixer: an all-mlp architecture for vision. Adv. Neural. Inf. Process. Syst. 34, 24261–24272 (2021).
Lin, J., Wen, W. K. & Liao, J. Y. A novel concept-cognitive learning method for bird song classification. Mathematics. 11 (20), 4298. https://doi.org/10.3390/math11204298 (2023).
doi: 10.3390/math11204298
Bifet, A., Pfahringer, B., Read, J. & Holmes, G. Efficient data stream classification via probabilistic adaptive windows. In Proceedings of the 28th Annual ACM Symposium on Applied Computing, Coimbra, Portugal, 18–22 March ; p. 801 (2013). (2013).
Gomes, H. M. et al. Adaptive random forests for evolving data stream classification. Machine Learning, Springer (2017).
Gama, J. & Kosina, P. Learning Decision Rules from Data Streams. In Toby Walsh. Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. Menlo Park, California, USA, s. 1255–1260 (2011).
Bernardo, A., Gomes, H. M., Montiel, J., Pfahringer, B. & Valle, E. D. C-smote: Continuous synthetic minority oversampling for evolving data streams, IEEE International Conference on Big Data (Big Data), IEEE (2020). (2020).
Brzezinski, D. & Stefanowski, J. Reacting to different types of concept drift: the accuracy updated ensemble algorithm. IEEE Trans. Neural Netw. Learn. Syst. 25 (1), 81–94. https://doi.org/10.1109/TNNLS.2013.2251352 (2013).
doi: 10.1109/TNNLS.2013.2251352
Cal, P. & Woniak, M. Parallel hoeffding decision tree for streaming data. Adv. Intell. Syst. Comput. https://doi.org/10.1007/978-3-319-00551-5_4 (2013).
doi: 10.1007/978-3-319-00551-5_4
Bifet, A. et al. New Ensemble Methods for Evolving data Streams, Knowledge Discovery and Data Mining (ACM, 2009). https://doi.org/10.1145/1557019.1557041
Gunasekara, N., Pfahringer, B., Gomes, H. & Bifet, A. Gradient boosted trees for evolving data streams[J]. Mach. Learn. 113 (5), 3325–3352. https://doi.org/10.1007/s10994-024-06517-y (2024).
doi: 10.1007/s10994-024-06517-y
Wan, S. W. & Wang, S. D. Concept drift detection based on pre-clustering and statistical testing. J. Internet Technol. 2, 22 (2021).
Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. Comput. Sci. https://doi.org/10.48550/arXiv.1409.1556 (2015).
doi: 10.48550/arXiv.1409.1556
Ribeiro, M. T., Singh, S. & Guestrin, C. Why should I trust you? Explaining the predictions of any classifier[J]. ACM. https://doi.org/10.1145/2939672.2939778 (2016).
doi: 10.1145/2939672.2939778