Document Type : Original Article
Authors
- Ehsan Nabovati 1
- Amir Abas Azizi 1
- Ebrahim Abbasi 2
- Hassan Vakili-Arki 1
- Javad Zarei 3
- Amir Reza Razavi 4
1 PhD Candidate, Medical Informatics, Student Research Committee, Mashhad University of Medical Sciences, Mashhad, Iran
2 PhD Candidate, Medical Informatics, Cancer Informatics Research Group, BCRC(Breast Cancer Research Center), ACECR (Academic Center for Education, Culture and Research), Tehran, Iran
3 PhD Candidate, Health Information Management, Health Management and Economics Research Center, School of Health Management and Information Sciences, Iran University of Medical Sciences, Tehran, Iran
4 Assistant Professor, Medical Informatics, Mashhad University of Medical Sciences, Mashhad, Iran
Abstract
Introduction: In the past decades, machine learning algorithms have become a useful tool for data mining within huge amounts of health data to create prediction models. Burn is one of the diseases that predicting of its outcome has high importance. The aim of this study was to survey two widely used machine learning algorithms; neural network and decision tree, and compare them with logistic regression method to predict the outcome of burn patients. Methods: In this retrospective observational study, following preprocessing of the data and determining the outcome of patient (live or death), two well-known machine learning algorithms (neural network and decision tree) and logistic regression method were used to create prediction models using data from 4804 burn patients hospitalized in Taleghani Burn Center in Ahvaz during the years 2001-2007. The preprocessing of the data was performed using SPSS (Version16.0), and in the modeling phase, Clementine (Version 12.0) software was used. Moreover, 10-fold cross validation technique was used to validate the model and criteria for evaluating the performance of models were measured and compared. Results: The results showed that the neural network algorithm with accuracy of 97% resulted the most accurate model on the studied data. The decision tree model with 95% accuracy was in the second place and the logistic regression model with an accuracy of 90% was the least accurate. Moreover other evaluating criteria such as sensitivity, specificity, PPV, NPV and AUC showed that performance of the neural network model was better than the others. Conclusion: The current study shows that machine learning algorithms compared with statistical methods create more accurate models. In analyzing the current data, the model created by artificial neural network is more accurate than the other machine learning algorithm, decision tree. Keywords: Data Mining; Machine Learning; Forecasting; Decision Tree; Artificial Neural Network; Burns
Keywords
- Olaitan PB, Olaitan JO. Burns and scalds--epidemiology and prevention in a developing country. Niger J Med. 2005; 14(1):9-16.
- Herndon DN, Spies M. Modern burn care. Semin Pediatr Surg. 2001; 10(1): 28-31.
- Badger JM. Burns: the psychological aspects. Am J Nurs. 2001; 101(11): 38-4.
- Afrasiabifar A, Karimi Z. Causes and materials of burning among the patients hospitalized in Yasuj Shahid Beheshti Hospital 1380. Armaghane Danesh. 2002; 7(27): 39-46. [Article in Persian]
- Osler T, Glance LG, Hosmer DW. Simplified estimates of the probability of death after burn injuries: extending and updating the baux score. J Trauma. 2010; 68(3): 690-7.
- Tobiasen J, Hiebert JM, Edlich RF. The abbreviated burn severity index. Ann Emerg Med. 1982; 11(5): 260-2.
- Hobbs GR. Data mining and healthcare informatics. Am J Health Behav. 2001; 25(3): 285-9.
- Yoo I, Alafaireet P, Marinov M, Pena-Hernandez K, Gopidi R, Chang JF, et al. Data mining in healthcare and biomedicine: a survey of the literature. J Med Syst. 2012; 36(4): 2431-48.
- Obenshain MK. Application of data mining techniques to healthcare data. Infect Control Hosp Epidemiol. 2004; 25(8): 690-5.
- Koh HC, Tan G. Data mining applications in healthcare. J Healthc Inf Manag. 2005; 19(2): 64-72.
- Lee TT, Liu CY, Kuo YH, Mills ME, Fong JG, Hung C. Application of data mining to the identification of critical factors in patient falls using a web-based reporting system. Int J Med Inform. 2011; 80(2): 141-50.
- Estahbanati HK, Bouduhi N. Role of artificial neural networks in prediction of survival of burn patients-a new approach. Burns. 2002; 28(6): 579-86.
- Delen D, Walker G, Kadam A. Predicting breast cancer survivability: a comparison of three data mining methods. Artif Intell Med. 2005; 34(2):113-27.
- Patil BM, Joshi RC, Toshniwal D, Biradar S. A new approach: role of data mining in prediction of survival of burn patients. J Med Syst. 2011; 35(6): 1531-42.
- Oztekin A, Delen D, Kong ZJ. Predicting the graft survival for heart-lung transplantation patients: an integrated data mining methodology. Int J Med Inform. 2009; 78(12): e84-96.
- Chu CM. Artificial neural network may perform good to predict the survivability of cervical cancer. AMIA Annu Symp Proc. United States. 2006; 2006: 889.
- Cios KJ, Pedrycz W, Swiniarski RW, Kurgan LA. Data Mining: A Knowledge Discovery Approach. USA: Springer; 2007: 473-474.
- Olson DL, Delen D. Advanced Data Mining Techniques. USA: Springer; 2008: 141:143.
- Witten IH, Frank E. Data Mining: Practical Machine Learning Tools and Techniques. USA: Esevier; 2005: 149-151.
- Larose DT. Discovering Knowledge in Data: An Introduction to Data Mining. Canada: John Wiley & Sons; 2005: 128:145.
- Clementine® 12.0 Algorithms Guide. USA: SPSS Inc.; 2007: 43-55.
- Shortliffe EH. Biomedical Informatics: Computer Applications in Health Care and Biomedicine. USA: Springer; 2006: 91-94.
)