Marija BLAGOJEVIĆ, Aleksandar PEULIĆ, Željko JOVANOVIĆ, Dragan JANKOVIĆ

Patient comfort level prediction during transport using artificial neural network

Since patient comfort during transport is a matter of paramount importance, this paper aims to determinethe possibilities of applying neural networks for its prediction and monitoring. Specific objectives of the research includemonitoring and predicting patient transport comfort, with subjective assessment of comfort by medical personnel. Anoriginal Android application that collects signals from an accelerometer and a GPS sensor was used with the aim ofachieving the research goals. The collected signals were processed and a total of twelve parameters were calculated. Amultilayer perceptron was created in the proposed research. The evaluation results indicate acceptable accuracy andgive the possibility to apply the same model to the next patient transport. The root mean square error was 0.0215 andthe overall confusion matrix prediction accuracy was 90.07%. Moreover, the results were validated in real usage. Thelimitations and future work are highlighted.

PDF

___

[1] Griffin M. Handbook of Human Vibration. London, UK: Elsevier Academic Press, 1996.
[2] ISO. Standard by Technical Committee ISO/TC 108/SC 4. Human Exposure to Mechanical Vibration and Shock, ISO 2631-1 Mechanical Vibration and Shock - Evaluation of Human Exposure to Whole-Body Vibration - Part 1: General Requirements. Geneva, Switzerland: ISO, 1997.
[3] Coats T, Davies G. Prehospital care for road traffic casualties. British Medical Journal 2002; 324 (7346): 1135.
[4] Gray A. Secondary transport of the critically ill and injured adult. Emerging Medicine Journal 2004; 21 (3): 281-285.
[5] British Standards Institution. British-Adopted European Standard. BS EN 1789:2007+A2:2014: Medical Vehicles and their Equipment - Road Ambulances. London, UK: BSI, 2014.
[6] Ferreira J, Hignett S. Reviewing ambulance design for clinical efficiency and paramedic safety. Application Ergonomics 2005; 36 (1): 97-105.
[7] Ferdinande P. Recommendations for intra-hospital transport of the severely head injured patient. Intensive Care Medicine 1999; 25 (12): 1441-1443.
[8] Theodore N, Aarabi B, Dhall S, Gelb DE, Hurlbert RJ. Transportation of patients with acute traumatic cervical spine injuries. Neurosurgery 2013; 72 (Suppl. 2): 35-39.
[9] Jovanovic Z, Bacevac R, Markovic R. Information system for the centralized display of the transport comfort information. Facta Universitatis Series Electronics and Energetics 2017; 30 (4): 5547-5570.
[10] Paschold H, Mayton A. Whole-body vibration: building awareness in SH&E. Professional Safety 2011; 56 (4): 30.
[11] BSI. Standard BS 6841, Guide to Measurement and Evaluation of Human Exposure to Whole-Body Mechanical Vibration and Repeated Shock. London, UK: BSI, 1987.
[12] American National Standards Institute. ASA S2.72-2002/Part 1 / ISO 2631-1:1997 (R2012). Washington, DC, USA; American National Standards Institute, 2002.
[13] European Union. Directive 2002/44/EC, Vibration - Safety and Health at Work - EU-OSHA. Brussels, Belgium: EU, 2002.
[14] HSE. The Control of Vibration at Work Regulations. Guidance on Regulations (L140), 104. London, UK: HSE, 2005.
[15] Dickey J, Oliver M, Boileau P. Multi-axis sinusoidal whole-body vibrations: Part I - How long should the vibration and rest exposures be for reliable discomfort measures? Journal of Low Frequency Noise Vibration and Active Control 2006; 25 (3): 175-184.
[16] Dickey J, Eger T, Oliver M. Multi-axis sinusoidal whole-body vibrations: Part II - Relationship between vibration total value and discomfort varies between vibration axes. Journal of Low Frequency Noise Vibration and Active Control 2009; 26 (3): 195-204.
[17] Cuadrado J, Dopico D, Perez J. Automotive observers based on multibody models and the extended Kalman filter. Multibody System Dynamics 2012; 27 (1): 3-19.
[18] Lee J, Park E, Robinovitch S. Estimation of attitude and external acceleration using inertial sensor measurement during various dynamic conditions. IEEE Transactions Instruments Measurements 2012; 61 (8): 2262-2273.
[19] Blanco-Claraco J, Torres-Moreno J, Giménez-Fernández A. Multibody dynamic systems as Bayesian networks: applications to robust state estimation of mechanisms. Multibody System Dynamics 2015; 34 (2): 103-128.
[20] Eriksson J, Girod L, Hull B. The pothole patrol: using a mobile sensor network for road surface monitoring. In: Proceedings of the 6th International Conference; Breckenridge, CO, USA; June 2008. pp. 29-39.
[21] Shaw R, Steinberg, D, Bonnet J. Mobile health devices: will patients actually use them? Journal of the American Medical Informatics Association 2006; 23 (3): 462-466.
[22] Mednis A, Strazdins G, Zviedris R, Kanonirs G, Selavo L. Real time pothole detection using Android smartphones with accelerometers. In: International Conference on Distributed Computing in Sensor Systems and Workshops; Ottawa,Canada; 2011. doi: http://dx.doi.org/10.1155/2015/869627
[23] Mohan P, Padmanabhan V, Ramjee R. TrafficSense? Rich monitoring of road and traffic conditions using mobile smartphones. In: 6th ACM Conference on Embedded Networked Sensory System; Rayleigh, NC, USA; 2008. pp. 1-29.
[24] Plewa K, Eger T, Oliver M. Comparison between ISO 2631-1 comfort prediction equations and self-reported comfort values during occupational exposure to whole-body vehicular vibration. Journal of Low Frequency Noise, Vibration and Active Control 2012; 31 (1): 43-53.
[25] Grenier S, Eger T, Dickey J. Predicting discomfort scores reported by LHD operators using whole-body vibration exposure values and musculoskeletal pain scores. Work 2010; 35 (1): 49-62.
[26] Tüchsen F, Feveile H, Christensen K, Krause N. The impact of self-reported exposure to whole-body-vibrations on the risk of disability pension among men: a 15 year prospective study. BMC Public Health 2010; 10: 305.
[27] Ayari H, Thomas M, Dor S. A design of experiments for statistically predicting risk of adverse health effects on drivers exposed to vertical vibrations. International Journal of Occupational Safety and Ergonomics 2011; 17 (3): 221-232.
[28] Munish P, Yashwant P, Vijau S, Tipparaju S, Moreno W. Artificial Neural Network for Drug Design, Delivery and Disposition. Amsterdam, the Netherlands: Academic Press, 2015.
[29] Massie D, White K, Daly S. Application of neural networks to predict ice jam occurrence. Cold Regions Science and Technology 2002; 35 (2): 115-122.
[30] Karlaftis M, Vlahogianni E. Statistical methods versus neural networks in transportation research: differences, similarities and some insights. Transportation Research Part C: Emerging Technologies 2011; 19 (3): 387-399.
[31] Garrido C, De Oña R, De Oña J. Neural networks for analyzing service quality in public transportation. Expert Systems and Applications 2014; 41 (15): 6830-6838.
[32] Xiao G, Juan Z, Zhang C. Travel mode detection based on GPS track data and Bayesian networks. Computers, Environment and Urban Systems 2015; 54: 14-22.
[33] Osaba E, Onieva E, Moreno A. Decentralised intelligent transport system with distributed intelligence based on classification techniques. IET Intelligent Transportation Systems 2016; 10 (10): 674-682.
[34] Jovanovic Z, Bacevic R, Markovic R. Android application for observing data streams from built-in sensors using RxJava. In: 2015 23rd Telecommunications Forum; Belgrade, Serbia; 2015. pp. 918-921.
[35] Christensen B, Nurkiewitz T. Reactive Programming with RxJava. Sebastopol, CA, USA: O’Reilly Media, 2016.
[36] Grzymala-Busse J, Hu M. A comparison of several approaches to missing attribute values in data mining. In: International Conference on Rough Sets and Current Trends in Computing; Canada; 2000. pp. 378-385.
[37] Harper G. Viability of artificial neural networks in mobile healthcare. PhD, Goteburg University, Oulu, Finland, 2011.
[38] Kohavi R, Provost F. Glossary of terms special issue on applications of machine learning and the knowledge discovery process. Machine Learning 1998; 30 (2/3): 271-274.
[39] Chukwu A, Nwachukwu S. Analysis of some meteorological parameters using artificial neural network method for Makurdi, Nigeria. African Journal of Environmental Science and Technology 2012; 6 (3): 182-188.
[40] Senkal S, Ozgonenel O. Performance analysis of artificial and wavelet neural networks for short term wind speed prediction. In: 8th International Conference on Electrical and Electronics Engineering; Bursa, Turkey; 2013. pp. 196-198.
[41] Blokduk G. Data Mining Extensions. Brisbane, Australia: Emereo Pty. Ltd., 2018.