TOWARDS AN AUTOMATIC PAIN INTENSITY LEVELS EVALUATION FROM MULTIMODAL PHYSIOLOGICAL SIGNAL USING MACHINE LEARNING APPROACHES

Authors

  • M. S. Patil SSVPS's BSD College of Engineering, Dhule, KBCNMU, Jalgaon, India
  • H. D. Patil SSVPS's BSD College of Engineering, Dhule, KBCNMU, Jalgaon, India

DOI:

https://doi.org/10.4314/njt.v43i4.16

Keywords:

pain, classification, Accuracy, Non Pain, Feature, Classification, CatBoost

Abstract

A pain assessment is necessary in order to identify and manage pain. Self-report has been the prime method of measuring intensity of pain. To address this, an impartial methodology to recognizing pain that is both scalable and inexpensive must be developed. In this study, a Bio-Vid Heat Pain Database (Part A) dataset containing 86 individuals in good health condition who experience extreme pain was utilized to develop algorithms for pain recognition. Two physiological indicators, electrocardiogram and electrodermal activity were utilized. Different kinds of machine learning algorithms were implemented to establish the framework for more advances in the development of complex pain classification algorithms. CatBoost and AdaBoost performed significantly better than other methods, with average performance accuracy of 83.68% and 82.68% respectively for fusion of electrocardiogram and electrodermal activity signals. The binary classification experiment discriminates between the baseline and the pain tolerance level (T0 vs. T4).

References

[1] F.-S. Tsai, Y.-L. Hsu, W.-C. Chen, Y.-M. Weng, C.-J. Ng, and C.-C. Lee, ‘Toward Development and Evaluation of Pain Level-Rating Scale for Emergency Triage based on Vocal Characteristics and Facial Expressions’, in Interspeech 2016, ISCA, Sep. 2016, pp. 92–96. doi: 10.21437/Interspeech.2016-408.

[2] F.-S. Tsai, Y.-M. Weng, C.-J. Ng, and C.-C. Lee, ‘Embedding stacked bottleneck vocal features in a LSTM architecture for automatic pain level classification during emergency triage’, in 2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII), San Antonio, TX: IEEE, Oct. 2017, pp. 313–318. doi: 10.1109/ACII.2017.8273618.

[3] P. Thiam and F. Schwenker, ‘Combining Deep and Hand-Crafted Features for Audio-Based Pain Intensity Classification’, in Multimodal Pattern Recognition of Social Signals in Human-Computer-Interaction, F. Schwenker and S. Scherer, Eds., Cham: Springer International Publishing, 2019, pp. 49–58. doi: 10.1007/978-3-030-20984-1_5.

[4] P. Rodriguez et al., ‘Deep Pain: Exploiting Long Short-Term Memory Networks for Facial Expression Classification’, IEEE Trans. Cybern., vol. 52, no. 5, pp. 3314–3324, May 2022, doi: 10.1109/TCYB.2017.2662199.

[5] P. Werner, A. Al-Hamadi, K. Limbrecht-Ecklundt, S. Walter, S. Gruss, and H. C. Traue, ‘Automatic Pain Assessment with Facial Activity Descriptors’, IEEE Trans. Affective Comput., vol. 8, no. 3, pp. 286–299, Jul. 2017, doi: 10.1109/TAFFC.2016.2537327.

[6] M. Tavakolian and A. Hadid, ‘A Spatiotemporal Convolutional Neural Network for Automatic Pain Intensity Estimation from Facial Dynamics’, Int J Comput Vis, vol. 127, no. 10, pp. 1413–1425, Oct. 2019, doi: 10.1007/s11263-019-01191-3.

[7] P. Thiam, H. A. Kestler, and F. Schwenker, ‘Two-Stream Attention Network for Pain Recognition from Video Sequences’, Sensors, vol. 20, no. 3, p. 839, Feb. 2020, doi: 10.3390/s20030839.

[8] S. Walter et al., ‘Automatic pain quantification using autonomic parameters.’, Psychology & Neuroscience, vol. 7, no. 3, pp. 363–380, 2014, doi: 10.3922/j.psns.2014.041.

[9] E. Campbell, A. Phinyomark, and E. Scheme, ‘Feature Extraction and Selection for Pain Recognition Using Peripheral Physiological Signals’, Front. Neurosci., vol. 13, May 2019, doi: 10.3389/fnins.2019.00437.

[10] P. Thiam et al., ‘Multi-Modal Pain Intensity Recognition Based on the SenseEmotion Database’, IEEE Trans. Affective Comput., vol. 12, no. 3, pp. 743–760, Jul. 2021, doi: 10.1109/TAFFC.2019.2892090.

[11] M. Sharma, R.-S. Tan, and U. R. Acharya, ‘Automated heartbeat classification and detection of arrhythmia using optimal orthogonal wavelet filters’, Informatics in Medicine Unlocked, vol. 16, p. 100221, 2019, doi: 10.1016/j.imu.2019.100221.

[12] M. Sharma, R.-S. Tan, and U. R. Acharya, ‘Detection of shockable ventricular arrhythmia using optimal orthogonal wavelet filters’, Neural Comput & Applic, vol. 32, no. 20, pp. 15869–15884, Oct. 2020, doi: 10.1007/s00521-019-04061-8.

[13] M. Kachele, P. Thiam, M. Amirian, F. Schwenker, and G. Palm, ‘Methods for Person-Centered Continuous Pain Intensity Assessment From Bio-Physiological Channels’, IEEE J. Sel. Top. Signal Process., vol. 10, no. 5, pp. 854–864, Aug. 2016, doi: 10.1109/JSTSP.2016.2535962.

[14] P. Bellmann, P. Thiam, and F. Schwenker, ‘Multi-classifier-Systems: Architectures, Algorithms and Applications’, in Computational Intelligence for Pattern Recognition, vol. 777, W. Pedrycz and S.-M. Chen, Eds., Cham: Springer International Publishing, 2018, pp. 83–113. doi: 10.1007/978-3-319-89629-8_4.

[15] C. T. Chambers and J. S. Mogil, ‘Ontogeny and phylogeny of facial expression of pain’, Pain, vol. 156, no. 5, pp. 798–799, May 2015, doi: 10.1097/j.pain.0000000000000133.

[16] B. M. Waller, E. Julle-Daniere, and J. Micheletta, ‘Measuring the evolution of facial “expression” using multi-species FACS’, Neuroscience & Biobehavioral Reviews, vol. 113, pp. 1–11, Jun. 2020, doi: 10.1016/j.neubio rev.2020.02.031.

[17] J. A. Priebe, M. Kunz, C. Morcinek, P. Rieckmann, and S. Lautenbacher, ‘Does Parkinson’s disease lead to alterations in the facial expression of pain?’, Journal of the Neurological Sciences, vol. 359, no. 1–2, pp. 226–235, Dec. 2015, doi: 10.1016/j.jns.2015.10 .056.

[18] G. Bargshady, X. Zhou, R. C. Deo, J. Soar, F. Whittaker, and H. Wang, ‘Enhanced deep learning algorithm development to detect pain intensity from facial expression images’, Expert Systems with Applications, vol. 149, p. 113305, Jul. 2020, doi: 10.1016/j.eswa.2020.113305.

[19] E. Hosseini et al., ‘Convolution Neural Network for Pain Intensity Assessment from Facial Expression’, in 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Glasgow, Scotland, United Kingdom: IEEE, Jul. 2022, pp. 2697–2702. doi: 10.1109/EMBC48229.2022.9871770.

[20] A. N. Shreya Sri, S. Nithin, P. Vasist, V. Mundra, R. Babu, and A. Girish, ‘A Relative Analysis of Machine Learning based approaches to Detect Human Pain Intensity using Facial Expressions’, in 2023 International Conference on Advances in Electronics, Communication, Computing and Intelligent Information Systems (ICAECIS), Apr. 2023, pp. 406–411. doi: 10.1109/ICAECIS58353.2023.10170170.

[21] H. Naseri et al., ‘Development of a generalizable natural language processing pipeline to extract physician-reported pain from clinical reports: Generated using publicly-available datasets and tested on institutional clinical reports for cancer patients with bone metastases’, Journal of Biomedical Informatics, vol. 120, p. 103864, Aug. 2021, doi: 10.1016/j.jbi.2021.103864.

[22] S. S. Abdullah, N. Rostamzadeh, K. Sedig, A. X. Garg, and E. McArthur, ‘Predicting Acute Kidney Injury: A Machine Learning Approach Using Electronic Health Records’, Information, vol. 11, no. 8, p. 386, Aug. 2020, doi: 10.3390/info11080386.

[23] J. A. Hughes et al., ‘Analyzing Pain Patterns in the Emergency Department: Leveraging Clinical Text Deep Learning Models for Real-World Insights’. medRxiv, Sep. 25, 2023. doi: 10.1101/2023.09.24.23296019.

[24] P. Werner, A. Al-Hamadi, K. Limbrecht-Ecklundt, S. Walter, and H. C. Traue, ‘Head movements and postures as pain behavior’, PLoS ONE, vol. 13, no. 2, p. e0192767, Feb. 2018, doi: 10.1371/journal.pone.0192767.

[25] B. D. Winslow, R. Kwasinski, K. Whirlow, E. Mills, J. Hullfish, and M. Carroll, ‘Automatic detection of pain using machine learning’, Front. Pain Res., vol. 3, p. 1044518, Nov. 2022, doi: 10.3389/fpain.2022.1044518.

[26] E. Kasaeyan Naeini et al., ‘Pain Recognition With Electrocardiographic Features in Postoperative Patients: Method Validation Study’, J Med Internet Res, vol. 23, no. 5, p. e25079, May 2021, doi: 10.2196/25079.

[27] M. Talal, S. Aziz, M. U. Khan, Y. Ghadi, S. Z. H. Naqvi, and M. Faraz, ‘Machine learning‐based classification of multiple heart disorders from PCG signals’, Expert Systems, vol. 40, no. 10, p. e13411, Dec. 2023, doi: 10.1111/exsy.13 411.

[28] S. A. H. Aqajari et al., ‘Pain Assessment Tool With Electrodermal Activity for Postoperative Patients: Method Validation Study’, JMIR Mhealth Uhealth, vol. 9, no. 5, p. e25258, May 2021, doi: 10.2196/25258.

[29] S. Aziz, M. U. Khan, N. Hirachan, G. Chetty, R. Goecke, and R. Fernandez-Rojas, ‘“Where does it hurt?”: Exploring EDA Signals to Detect and Localise Acute Pain’, in 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Sydney, Australia: IEEE, Jul. 2023, pp. 1–5. doi: 10.1109/EMBC40787.2023.1034 1157.

[30] S. Vemulapalli, P. Varshitha, P. Kumar, and T. Vinay, "An experimental analysis of machine learning techniques for crop recommendation," Nigerian Journal of Technology, vol. 43, no. 2, 2024.

[31] A. A. Okandeji, O. F. Odeyinka, A. A. Sogbesan, and N. O. Ogunye, "A comparative analysis of haemoglobin variants using machine learning algorithms," Nigerian Journal of Technology, vol. 41, no. 4, pp. 789-796, 2022.

[32] ‘BioVid Heat Pain Database’, nit. Accessed: Jul. 06, 2024. [Online]. Available: https://www .nit.ovgu.de/-p-1358.html

[33] V. R. Patil and T. H. Jaware, ‘Random Forest and Gabor Filter Bank Based Segmentation Approach for Infant Brain MRI’, in Applied Information Processing Systems, vol. 1354, B. Iyer, D. Ghosh, and V. E. Balas, Eds., Singapore: Springer Singapore, 2022, pp. 265–272. doi: 10.1007/978-981-16-2008-9_25.

[34] V. R. Patil and T. H. Jaware, ‘Computer-Assisted Diagnosis and Neuroimaging of Baby Infants’, in Intelligence Enabled Research: DoSIER 2021, S. Bhattacharyya, G. Das, and S. De, Eds., Singapore: Springer, 2022, pp. 17–30. doi: 10.1007/978-981-19-0489-9_2.

[35] A. O. Andrade, S. Nasuto, P. Kyberd, C. M. Sweeney-Reed, and F. R. Van Kanijn, ‘EMG signal filtering based on Empirical Mode Decomposition’, Biomedical Signal Processing and Control, vol. 1, no. 1, pp. 44–55, Jan. 2006, doi: 10.1016/j.bspc.2006.03.003.

[36] A. Andrade, P. Kyberd, and S. Nasuto, ‘The application of the Hilbert spectrum to the analysis of electromyographic signals’, Information Sciences, vol. 178, no. 9, pp. 2176–2193, May 2008, doi: 10.1016/j.ins.2007.12.01 3.

[37] A. Phinyomark, F. Quaine, S. Charbonnier, C. Serviere, F. Tarpin-Bernard, and Y. Laurillau, ‘EMG feature evaluation for improving myoelectric pattern recognition robustness’, Expert Systems with Applications, vol. 40, no. 12, pp. 4832–4840, Sep. 2013, doi: 10.1016/j.es wa.2013.02.023.

[38] S. Gruss et al., ‘Pain Intensity Recognition Rates via Biopotential Feature Patterns with Support Vector Machines’, PLoS ONE, vol. 10, no. 10, p. e0140330, Oct. 2015, doi: 10.1371/jo urnal.pone.0140330.

[39] O. Owolafe, T. Alese, A. F. Thompson, and B. K. Alese, "A User Identity Management System for Cybercrime Control," Nigerian Journal of Technology, vol. 40, no. 1, pp. 56-64, Jan. 2021.

[40] L. Breiman, ‘[No title found]’, Machine Learning, vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.

[41] H. Albaqami, G. M. Hassan, A. Subasi, and A. Datta, ‘Automatic detection of abnormal EEG signals using wavelet feature extraction and gradient boosting decision tree’, Biomedical Signal Processing and Control, vol. 70, p. 102957, Sep. 2021, doi: 10.1016/j.bspc.2021.1 02957.

[42] L. Holla and K. S. Kavitha, ‘An Improved Fake News Detection Model Using Hybrid Time Frequency-Inverse Document Frequency for Feature Extraction and AdaBoost Ensemble Model as a Classifier’, JAIT, vol. 15, no. 2, pp. 202–211, 2024, doi: 10.12720/jait.15.2.202-211.

[43] B. Dhananjay and J. Sivaraman, ‘Analysis and classification of heart rate using CatBoost feature ranking model’, Biomedical Signal Processing and Control, vol. 68, p. 102610, Jul. 2021, doi: 10.1016/j.bspc.2021.102610.

[44] M. U. Khan, S. Aziz, N. Hirachan, C. Joseph, J. Li, and R. Fernandez-Rojas, ‘Experimental Exploration of Multilevel Human Pain Assessment Using Blood Volume Pulse (BVP) Signals’, Sensors, vol. 23, no. 8, p. 3980, Apr. 2023, doi: 10.3390/s23083980.

[45] D. Albahdal, W. Aljebreen, and D. M. Ibrahim, ‘PainMeter: Automatic Assessment of Pain Intensity Levels From Multiple Physiological Signals Using Machine Learning’, IEEE Access, vol. 12, pp. 48349–48365, 2024, doi: 10.1109/ACCESS.2024.3384359.

Downloads

Published

2025-01-08

Issue

Section

Computer, Telecommunications, Software, Electrical & Electronics Engineering

How to Cite

TOWARDS AN AUTOMATIC PAIN INTENSITY LEVELS EVALUATION FROM MULTIMODAL PHYSIOLOGICAL SIGNAL USING MACHINE LEARNING APPROACHES. (2025). Nigerian Journal of Technology, 43(4), 763 – 771. https://doi.org/10.4314/njt.v43i4.16