Novel Hybrid Trauma Injury Classification based on Trauma Revise Injury Severity Score (TRISS) and Visum et Repertum (VeR) Features

Novel Hybrid Trauma Injury Classification based on Trauma Revise Injury Severity Score (TRISS) and Visum et Repertum (VeR) Features
  IJETT-book-cover           
  
© 2022 by IJETT Journal
Volume-70 Issue-7
Year of Publication : 2022
Authors : Mohd Hadyan Wardhana, Abd Samad Hasan Basari, Nuzulha Khilwani Ibrahim, Wan Zulaikha Wan Yaacob
DOI : 10.14445/22315381/IJETT-V70I7P248

How to Cite?

Mohd Hadyan Wardhana, Abd Samad Hasan Basari, Nuzulha Khilwani Ibrahim, Wan Zulaikha Wan Yaacob, "Novel Hybrid Trauma Injury Classification based on Trauma Revise Injury Severity Score (TRISS) and Visum et Repertum (VeR) Features" International Journal of Engineering Trends and Technology, vol. 70, no. 7, pp. 462-470, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I7P248

Abstract
Trauma injury classification is crucial for refining diagnostic and increasing the accuracy of Forensic and Medicolegal services. Current approaches are considered challenging in determining the critical features. Insufficient critical features analysis causes inconsistent judgment in analyzing the degree of trauma injury among the medical consultants. The issue becomes more complicated because the dataset consists of incomplete data and outliers class problems that can affect the sampling bias. The objective of this research is to identify the features and terms of trauma injury by combining the Trauma Revise Injury Severity Score (TRISS) with Visum et Repertum (VeR) Data, develop and evaluate the Hybrid Neural Network Model (HNNM) for classifying the degree of trauma injury for an Indonesian use case. The sample data consists of the TRISS features, including physiological and anatomical information. While the VeR data was used to improve the critical features selection. The HNNM is expected to classify the persecution victim as having a minor, moderate, or major injury, as defined by the Indonesian Penal Code. HNNM is proposed based on the case studies at three hospitals in the Indonesian city of Pekanbaru. It comprises three main phases: pre-processing, development, and performance analysis. Pre-processing phases solve the drawbacks of incomplete data by performing data cleansing and normalization. Then, the features' determination is chosen by utilizing the Neural Network (NN) as a classification algorithm and the Genetic Algorithm (GA) as an optimization technique. The selected features are applied during the dataset training stages to increase the HNNM's accuracy and minimize error. GA's goal is to increase the accuracy rate and reduce error in the learning stages of NN. The development phase is accomplished with testing stages by combining the TRISS feature and the VeR dataset. The performance analysis shows the HNNM produced a 98.85% accuracy level and the Root Mean Square Error (RMSE) value at 0.077. In the validation stage, the features of the HNNM are implementable and highly acceptable by the practitioner. For future works, the HNNM needs to increase the accuracy by improving the input features, including lifestyle, habit, and job.

Keywords
Trauma Revise Injury Severity Score (TRISS), Visum et Repertum (VeR), Medicolegal Prognostic, Root Mean Square Error (RMSE), Analytical Hierarchical Process (AHP).

Reference
[1] Afandi, D, "Procedures and Techniques for Making Visum Et Repertum," University of Riau Press, 2017.
[2] Allen, C.J, Wagenaar, A.E, Horkan, D.B, Baldor, D.J, Hannay, W.M, Tashiro, J, Namias, N, and Sola, J.E, "Predictors of Mortality in Pediatric Trauma: Experiences of A Level 1 Trauma Center and An Assessment of the International Classification Injury Severity Score (ICISS)," Pediatric Surgery International, vol.32, no.7,pp.657–663, 2016.
[3] Ayon, S.I, "Neural Network Based Software Defect Prediction Using Genetic Algorithm and Particle Swarm Optimization," 1st International Conference on Advances in Science, Engineering and Robotics Technology 2019, ICASERT 2019, (Icasert), pp..3–6, 2019.
[4] A Zhari, M.R, Susanti, R, and Hilbertina, N, "the Relationship Between the Knowledge Level of Doctors and the Quality of Visum Et Repertum Injuries in West Sumatra Regional Hospitals for the Period January 2011 To December 2012," Andalas Health Journal, vol.4 , no.3, pp.696 –700, 2012.
[5] Bolón-Canedo, V, Sánchez-Maroño, N, and Alonso-Betanzos, A, "A Review of Feature Selection Methods on Synthetic Data," Knowledge and Information Systems, vol.34, no.3, pp.483–519, 2013.
[6] Fatriah, S.H, Sampurna, B, and Firmansyah, A,"Medicolegal Analysis of Criteria for Degree of Wounds According To the Criminal Code," (november), pp. 514, 2017.
[7] Hashmienejad, S.H.A. and Hasheminejad, S.M.H, "Traffic Accident Severity Prediction Using A novel Multi-Objective Genetic Algorithm," International Journal of Crashworthiness, vol.22 , no.4, pp.425–440, 2017.
[8] Hassanipour, S, Ghaem, H, Arab-Zozani, M, Seif, M, Fararouei, M, Abdzadeh, E, Sabetian, G, and Paydar, S, "Comparison of Artificial Neural Network and Logistic Regression Models for Prediction of Outcomes in Trauma Patients: A Systematic Review and Meta-Analysis," Injury, vol.50 , no.2, pp.244–250, 2019.
[9] De Jongh, M.A.C, Ter Bogt, N.C.W, Steyerberg, E.W, Polinder, S, De Munter, L, and Sewalt, C.A, "Improvement of the Performance of Survival Prediction in the Ageing Blunt Trauma Population: A Cohort Study," Plos one, vol.13, no.12, pp.E0209099, 2018.
[10] De Jongh, M.A.C, Verhofstad, M.H.J, and Leenen, L.P.H, "Accuracy of Different Survival Prediction Models in A Trauma Population," British Journal of Surgery, vol.97 , no.12, pp.1805–1813, 2010.
[11] Kang, I.H, Lee, K.H, Youk, H, Lee, J. Il, Lee, H.Y, and Bae, K.S, "Trauma and Injury Severity Score Modification for Predicting Survival of Trauma in one Regional Emergency Medical Center in Korea: Construction of Trauma and Injury Severity Score Coefficient Model," Hong Kong Journal of Emergency Medicine, vol.26 , no.4, pp.225–232, 2019.
[12] Keren, B. and Hadad, Y, "ABC Inventory Classification Using AHP and Ranking Methods Via DEA," in: 2016 Second International Symposium on Stochastic Models in Reliability Engineering, Life Science and Operations Management (SMRLO). IEEE, pp.495–501, 2016.
[13] Jayaraj T, Dr. J. Abdul Samath, "Disease Forecasting and Severity Prediction Model for COVID-19 Using Correlated Feature Extraction and Feed-Forward Artificial Neural Networks," International Journal of Engineering Trends and Technology, vol. 69, no.8, pp.126-137, 2017.
[14] Rau, C.-S, Wu, S.-C, Chuang, J.-F, Huang, C.-Y, Liu, H.-T, Chien, P.-C, and Hsieh, C.-H, " Machine Learning Models of Survival Prediction in Trauma Patients," Journal of Clinical Medicine, vol.8 , no.6, pp.799, 2019.
[15] Salah, M, Abu Samra, S, and Hosny, O, 2017. Analytical Hierarchy Process Decision Support System (AHP-DSS) for Trenchless Technology. Proceedings of the 33rd International Symposium on Automation and Robotics in Construction (ISARC), 2017.
[16] Saleh, M, Saatchi, R, Burke, D, and Lecky, F, "Computational Analysis of Factors Affecting the Probability of Survival in Trauma Injuries," Proceedings - 2017 4th International Conference on Mathematics and Computers in Sciences and in Industry, MCSI 2017, no.1 pp.114–118, 2018.
[17] R. Surendiran, M. Thangamani, C. Narmatha, M. Iswarya, "Effective Autism Spectrum Disorder Prediction To Improve the Clinical Traits Using Machine Learning Techniques", International Journal of Engineering Trends and Technology, vol. 70, no. 4, pp.343-359, 2022. Https://Doi.Org/10.14445/22315381/IJETT-V70I4P230.
[18] Saleh, M, Saatchi, R, Lecky, F, and Burke, D, "Fuzzy Logic To Determine the Likelihood of Survival for Trauma Injury Patients," Studies in Health Technology and Informatics, vol.242, pp.385–388, 2017.
[19] Sanz, J, Paternain, D, Galar, M, Fernandez, J, Reyero, D, and Belzunegui, T, "A New Survival Status Prediction System for Severe Trauma Patients Based on A Multiple Classifier System," Computer Methods and Programs in Biomedicine, vol.142, pp.1–8, 2017.
[20] Zeng, D, He, Q, Leng, B, Zheng, W, Xu, H, Wang, Y, and Guan, G, "An Improved Ant Colony Optimization Algorithm Based on Dynamically Adjusting Ant Number," IEEE International Conference on Robotics and Biomimetics (ROBIO), pp.2039–2043, 2012.