Inteligencia computacional para la medición de presencia de dolor mediante el uso de señales electrofisiológicas
Computational Intelligence to Assess the Existence of Pain, Based on the Use of Electrophysiological Signals
Contenido principal del artículo
Resumen
El dolor es un problema de salud que afecta a las personas física y emocionalmente.
Para determinar el nivel de dolor experimentado, se realiza una encuesta que implica
autoevaluación por parte del paciente y capacidades de comunicación verbal o facial. En este
artículo, se presenta la comparación de los resultados de dos algoritmos computacionales
para dos tipos de clasificación: el primero discrimina entre dolor y no dolor, el segundo
clasifica tres niveles de dolor. Los algoritmos empleados fueron Máquina de Soporte
Vectorial (SVM) y el método de Análisis de Discriminante Cuadrático (QDA). Se indujo
dolor agudo a 15 participantes por electroestimulación, se evaluó electromiografía (EMG),
electrocardiografía (ECG), actividad electrodérmica (EDA), y electroencefalografía (EEG), y
se le pidió a los participantes reportar el dolor percibido mediante la escala análoga visual.
Posteriormente se adquirieron características de las señales asociadas al dolor. Se realizaron
tres análisis: clasificación binaria con múltiples variables, binaria con una característica y
clasificación de tres niveles con varias características. Se compararon los algoritmos SVM y
QDA utilizando la matriz de confusión y el costo computacional. Para la clasificación binaria
la exactitud del SVM fue del 88,02% y del QDA del 70,78%, con un costo computacional de
9,587s y 3,023s respectivamente.
Descargas
Detalles del artículo
Referencias (VER)
Bellmann P.; Schwenker F. (2020). Automated pain assessment: Is it useful to combine person-specific data samples?. 2020 IEEE Symposium Series on Computational Intelligence (SSCI), Caberra, ACT, Australia. pp. 1588–1593. DOI: 10.1109/SSCI47803.2020.9308279
Breau L. (2010). The science of pain measurement and the frustration of clinical pain assessment: Does an individualized numerical rating scale bridge the gap for children with intellectual disabilities? PAIN. 150(2), pp. 213-214. DOI: 10.1016/j.pain.2010.03.029
Briggs M.; Closs J. S. (1999). A descriptive study of the use of visual analogue scales and verbal rating scales for the assessment of postoperative pain in orthopedic patients. Journal of Pain and Symptom Management. 18(6), pp. 438–446. DOI: 10.1016/s0885-3924(99)00092-5.
Díaz, R.; Marulanda, F. (2019). Dolor crónico nociceptivo y neuropático en población adulta de Manizales (Colombia). Acta Médica Colombiana, 36(1), pp. 10-17. DOI: 10.36104/amc.2011.151
Christie S.; di Fronso S.; Bertollo M.; Werthner P. (2017). Individual alpha peak frequency in ice hockey shooting performance. Frontiers in Psychology. 8, p. 762. DOI: 10.3389/fpsyg.2017.00762
Egede, J. O.; Song, S.; Olugbade, T. A.; Wang, C.; Williams, A. C. D. C.; Meng, H.; Aung, M.; Lane, N. D.; Valstar, M.; Bianchi-Berthouze, N. (2020). EMOPAIN challenge 2020: Multimodal pain evaluation from facial and bodily expressions. 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG), Buenos Aires, Argentina. pp. 849–856. DOI: 10.1109/FG47880.2020.00078
Erdogan, B.; Ogul, H. (2020). Objective pain assessment using vital signs. Procedia Computer Science. 170, pp. 947–952. DOI:10.1016/j.procs.2020.03.103
Hadjileontiadis, L. J. (2015). Eeg-based tonic cold pain characterization using wavelet higher order spectral features. IEEE Transactions on Biomedical Engineering. 62(8), pp. 1981–1991. DOI: 10.1109/TBME.2015.2409133
Hadjileontiadis, L. J. (2018). Continuous wavelet transform and higher-order spectrum: combinatory potentialities in breath sound analysis and electroencephalogram-based pain characterization. Philosophical Transactions of The Royal Society a Mathematical, physical, and engineering sciences. 376 (2126). DOI: 10.1098/rsta.2017.0249
Hassan, T.; Seuß, D.; Wollenberg, J.; Weitz, K.; Kunz, M.; Lautenbacher, S.; Garbas, J. U.; Schmid, U. (2021). Automatic detection of pain from facial expressions: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. 43(6), pp. 1815–1831. DOI: 10.5121/ijcses.2012.3604. 47
Hautala, A. J.; Karppinen, J.; Sepp ̈anen, T. (2016). Short-term assessment of autonomic nervous system as a potential tool to quantify pain experience. 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando,FL, USA. pp. 2684–2687. DOI: 10.1109/EMBC.2016.7591283
Hung, C.; Shen, T.; Liang, C.; Wu, W. (2014). Using surface electromyography (semg) to classify low back pain based on lifting capacity evaluation with principal component analysis neural network method. 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society; Chicago, IL, USA. pp. 18–21. DOI: 10.1109/EMBC.2014.6943518
Jollant, F.; Voegeli, G.; Kordsmeier, N. C.; Carbajal, J. M.; Richard-Devantoy, S.; Turecki, G.; Caceda, R. (2019). A visual analog scale to measure psychological and physical pain: A preliminary validation of the ppp-vas in two independent samples of depressed patients. Progress in Neuro-Psychopharmacology and Biological Psychiatry. 90, pp.55–61. DOI: 10.1016/j.pnpbp.2018.10.018
Kostyunina, M. B.; Kulikov, M. A. (1996). Frequency characteristics of eeg spectra in the emotions. Neuroscience and Behavioral Physiology. 26(4), pp. 340–343. DOI: 10.1007/BF02359037
Lusher, J.; Elander, J.; Bevan, D.; Telfe,r P.; Burton, B. (2006). Analgesic addiction and pseudo-addiction in painful chronic illness. The Clinical Journal of Pain. 22(3). DOI: 10.1097/01.ajp.0000176360.94644.41
Medrano, R.; Varela, A.; Domínguez, M.; PardM, G.; Acosta, Y.; Pardo, G. (2010). Aspectos epidemiológicos relacionados con el
dolor en la población adulta. Revista Archivo Médico de Camagüey. 14(4). http://scielo.sld.cu/scielo.php?script=sci_arttext&pid=S1025-02552010000400013&lng=es&tlng=es.
Monroe, T. B.; Misra, S.; Habermann, R. C.; Dietrich, M. S.; Bruehl, S. P.; Cowan, R. L.; Newhouse, P. A.; Simmons, S. F. (2015). Specific physician orders improve pain detection and pain reports in nursing home residents: Preliminary data. Pain management nursing: official journal of the American Society of Pain Management Nurses. 16(5), pp. 770–780. DOI: 10.1016/j.pmn.2015.06.002
Nir, R. R.; Sinai, A.; Raz, E.; Sprecher, E.; Yarnitsky, D. (2010). Pain assessment by continuous eeg: Association between subjective perception of tonic pain and peak frequency of alpha oscillations during stimulation and at rest. Brain research. 1344, pp. 77–86. DOI: 10.1016/j.brainres.2010.05.004
Nisbet, G.; Sehgal, A. (2019). Pharmacology in the management of chronic pain. Anaesthesia and Intensive Care Medicine. 20(10), pp. 555 – 558. DOI:10.1016/j.mpaic.2019.07.009
Nora D. (2014). America’s addiction to opioids: Heroin and prescription drug abuse. Pearson Educacion. Padmanabhan S, SindhuG. 2014. Design of an ecg acquisition device for the nonlinear analysis of heart rate variability (hrv). 02
Petrovic, P.; Petersson, K. M.; Ghatan, P.; Stone-Elander, S.; Ingvar, M. (2000). Pain-related cerebral activation is altered by a distracting cognitive task. Pain. 85, pp. 19–30. DOI: 10.1016/s0304-3959(99)00232-8
Pikulkaew, K.; Chouvatut, V. (2021). Enhanced pain detection and movement of motion with data augmentation based on deep learning. 2021 13th International Conference on Knowledge and Smart Technology (KST), Bangsaen, Chounburi, Thailand. pp. 197–201. DOI: 10.1109/KST51265.2021.9415827
Pouromran, F.; Radhakrishnan, S.; Kamarthi S. (2021). Exploration of physiological sensors, features, and machine learning models for pain intensity estimation. PLoS One. 16(7). DOI: 10.1371/journal.pone.0254108
Lo Presti, L.; La Cascia, M. (2017). Boosting hankel matrices for face emotion recognition and pain detection. Computer Vision and Image Understanding. 156, pp.19–33. DOI: 10.1016/J.CVIU.2016.10.007
Rathee, N.; Ganotra, D. (2015). A novel approach for pain intensity detection based on facial
feature deformations. Journal of Visual Communication and Image Representation. 33, pp. 247 -254. DOI: 10.1016/J.JVCIR.2015.09.007
Rodriguez, P.; Cucurull, G.; González, J.; Gonfaus, J. M.; Nasrollahi, K.; Moeslund, T. B.; Roca, F. X. (2022). Deep pain: Exploiting long short-term memory networks for facial expression classification. IEEE Transactions on Cybernetics. 52(5), pp. 3314-3324. DOI: 10.1109/TCYB.2017.2662199
Rojo, R.; Prados-Frutos, J. C.; López-Valverde, A. (2015). Pain assessment using the facial action coding system. A systematic review. Medicina Clínica (English Edition). 145(8), pp. 350–355. DOI: 10.1016/j.medcli.2014.08.010
Roy, S. D.; Bhowmik, M. K.; Saha, P.; Ghosh, A. K. (2016). An approach for automatic pain detection through facial expression. Procedia Computer Science. 84, pp. 99–106. DOI:10.1016/j.procs.2016.04.072
Rupenga, M.; Vadapalli, H. B. (2016). Automatic spontaneous pain recognition using supervised classification learning algorithms. 2016 Pattern Recognition Association of South Africa and Robotics and Mechatronics International Conference (PRASA-RobMech), South Africa, Stellenbosch. IEEE. pp. 1-6. DOI:10.1109/ROBOMECH.2016.7813150
Siqueira, S. R. D. T.; de Siqueira, J. T. T. T.; Teixeira, M. J. (2020). Chronic pain, somatic unexplained complaints and multimorbidity: A mutimorbidity painful syndrome?. Medical Hypotheses. 138, p. 109598. DOI: 10.1016/j.mehy.2020.109598.
Stahlschmidt, L.; Friedrich, Y.; Zernikow, B.; Wager, J. (2018). Assessment of pain-related disability in pediatric chronic pain: A comparison of the functional disability inventory and the pediatric pain disability index. Clinical Journal of Pain. 34 (2), pp. 1173-1179. DOI: 10.1097/AJP.0000000000000646
Subramaniam, S. D.; Dass, B. (2021). Automated nociceptive pain assessment using physiological signals and a hybrid deep learning network. IEEE Sensors Journal. 21(3), pp. 3335–3343. DOI: 10.1109/JSEN.2020.3023656.
Susam, B.; Akcakaya, M.; Nezamfar, H.; Diaz, D.; Xu, X.; de Sa, V.; Craig, K.; Huang, J.; Goodwin, M. (2018). Automated pain assessment using electrodermal activity data and machine learning. 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Honolulu, HI, USA. IEEE Sensors Journal, pp. 372–375. DOI: 10.1109/JSEN.2020.3023656.
Susam, B. T.; Riek, N. T.; Akcakaya, M.; Xu, X.; de Sa,, V. R.; Nezamfar, H.; Diaz, D.; Craig, K. D.; Good-win, M. S.; Huang, J. S. (2022). Automated pain assessment in children using electrodermal activity and video data fusion via machine learning. IEEE Transactions on Biomedical Engineering. 69(1), pp. 422–431. DOI: 10.1109/TBME.2021.3096137
Thiam, P.; Hihn, H.; Braun, D.A.; Kestler, H.A.; Schwenker, F. (2021). Multi-modal pain intensity assessment based on physiological signals: A deep learning perspective. Frontiers in Physiology. 12. https://doi.org/10.3389/fphys.2021.720464
Van, A. J.; Van den, W. (2015). The misuse of prescription opioids: A threat for Europe? Current Drug Abuse Reviews, 8(1), pp. 3–14. DOI: 10.2174/187447370801150611184218
Wang, R.; Xu, K.; Feng, H.; Chen, W. (2020). Hybrid RNN-ANN based deep physiological network for pain recognition. 42nd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC), Montreal, QC, Canada. Institute of Electrical and Electronics Engineers (IEEE), pp. 5584–5587. DOI: 10.1109/EMBC44109.2020.9175247.
Wong, T.T.; Yeh, P.Y. (2020). Reliable accuracy estimates from fold cross validation. IEEE Transactions on Knowledge and Data Engineering. 32(8):1586–1594. DOI: 10.1109/TKDE.2019.2912815
Yang, F.; Banerjee, T.; Panaggio, M. J.; Abrams, D. M.; Shah, N.R. (2019). Continuous pain assessment using ensemble feature selection from wearable sensor data. 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), San Diego, CA, USA, Institute of Electrical and Electronics Engineers (IEEE), pp. 569–576. DOI: 10.1109/BIBM47256.2019.8983282