Predicting Death and Morbidity in Perforated Peptic Ulcer
Peptic ulcers are defined as defects in the gastrointestinal mucosa that extend through the muscularis mucosae. Although not being the most common complication, perforations stand out as being the complication with the highest mortality rate. To predict the probability of mortality, several scoring systems based on clinical and biochemical parameters, such as the Boey and PULP scoring system have been developed. This article explores, using data mining in the medical data available, how the scoring systems perform when trying to predict mortality and patients’ state complication. We also try to conclude, from the two scoring systems presented, which predicts better the situations described. Regarding the results, we concluded that the PULP scoring allows a better mortality prediction achieving, in this case, above 90% accuracy, however, the results may be inconclusive due to the lack of patients who died in the dataset used. Regarding the complications, we concluded that, on the other hand, the Boey system achieves better results leading to a better prediction when it comes to predicting patients’ state complication.
KeywordsData mining Dataset Scoring systems PULP Boey Death Health complications
This work has been supported by Compete: POCI-01-0145-FEDER-007043 and FCT within the Project Scope UID/CEC/00319/2013.
- 3.Irabor, D.O.: An audit of peptic ulcer surgery in Ibadan, Nigeria. West Afr. J. Med. 24(3), 242 (2005)Google Scholar
- 8.Zhao, Y.: R and Data Mining: Examples and Case Studies. Academic Press, San Diego (2012)Google Scholar
- 10.Cohen, W.W.: Fast effective rule induction. In: Machine Learning Proceedings 1995, pp. 115–123 (1995)Google Scholar
- 11.Kohavi, R.: The power of decision tables. In: European Conference on Machine Learning, pp. 174–189. Springer, Heidelberg, April 1995Google Scholar
- 13.Parsania, V., Bhalodiya, N., Jani, N.N.: Applying Naïve Bayes, BayesNet, PART, JRip and OneR Algorithms on Hypothyroid Database for Comparative Analysis (2014)Google Scholar
- 15.Quinlan, J.R.: C4.5: Programs for Machine Learning. Elsevier, Amsterdam (2014)Google Scholar
- 16.Arthur, D., Vassilvitskii, S.: k-means ++: the advantages of careful seeding. In: Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 1027–1035. Society for Industrial and Applied Mathematics, January 2007Google Scholar
- 17.Chapman, P., Clinton, J., Kerber, R., Khabaza, T., Reinartz, T., Shearer, C., Wirth, R.: CRISP-DM 1.0 Step-by-step data mining guide (2000)Google Scholar