Clinical Decision Support for Disease Classification based on the Tests Association

Authors: Sung Ho Ha, Seong Hyeon Joo, Eun Kyung Kwon

Abstract:

Until recently, researchers have developed various tools and methodologies for effective clinical decision-making. Among those decisions, chest pain diseases have been one of important diagnostic issues especially in an emergency department. To improve the ability of physicians in diagnosis, many researchers have developed diagnosis intelligence by using machine learning and data mining. However, most of the conventional methodologies have been generally based on a single classifier for disease classification and prediction, which shows moderate performance. This study utilizes an ensemble strategy to combine multiple different classifiers to help physicians diagnose chest pain diseases more accurately than ever. Specifically the ensemble strategy is applied by using the integration of decision trees, neural networks, and support vector machines. The ensemble models are applied to real-world emergency data. This study shows that the performance of the ensemble models is superior to each of single classifiers.

Keywords: Diagnosis intelligence, ensemble approach, data mining, emergency department

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1082985

References:

[1] Abdullah U, Ahmad J, Ahmed A (2008) Analysis of effectiveness of apriori algorithm in medical billing data mining, in Proceedings of 4th International Conference on Emerging Technologies.
[2] Bassan R, Scofano M, Gamarski R, Dohmann HF, Pimenta L, Volschan A, Araujo M, Clare C, Fabricio M, Sanmartin CH, Mohallem K, Gaspar S, Macaciel R (2000) Chest pain in the emergency room: Importance of a systematic approach. Arquivos Brasileiros de Cardiologia 74(1):13-29.
[3] Butler KH, Swencki SA (2006) Chest pain: a clinical assessment. Radiologic Clinics of North America 44(2):165-179.
[4] Ceglowski R, Churilov L, Wasserthiel J (2007) Combining data mining and discrete event simulation for a value-added view of a hospital emergency department. Journal of the Operational Research Society 58:246-254.
[5] Cios KJ, Moore GW (2002) Uniqueness of medical data mining. Artificial intelligence in medicine 26(1-2):1-24.
[6] Conforti D, Guido R (2005) Kernel-based support vector machine classifiers for early detection of myocardial infarction. Optimization Methods and Software 20(2-3):401-413.
[7] Conroy RM et al. (2003) Estimation of ten-year risk of fatal cardiovascular disease in Europe: the SCORE project. European Heart Journal 24(11):987-1003.
[8] Duguay C, Chetouane F (2007) Modeling and improving emergency department systems using discrete event simulation. Simulation 834):311-320.
[9] Ellenius J, Groth T (2000) Transferability of neural network-based decision support algorithms for early assessment of chest-pain patients. International Journal of Medical Informatics 60(1):1-20.
[10] Erhardt L, Herlitz J, Bossaert L, Halinen M, Keltari M, Koster R, Marcassa C, Quinn T, van Weert H (2002) Task force on the management of chest pain. European Heat Journal 23:1153-1176.
[11] Fayyad UM (1997) Data mining and knowledge discovery in databases: implications for scientific databases, in Proceedings of Ninth International Conference on Scientific and Statistical Database Management.
[12] Fromm RE, Gibbs LR, McCallum WG, Niziol C, Babcock JC, Gueler AC, Levine RL (1993) Critical care in the emergency department: a time-based study. Critical Care Medicine 21(7):970-976.
[13] Giudici P (2003) Applied Data Mining: Statistical Methods for Business and Industry. John Wiley & Sons, Hoboken.
[14] Guven A, Kara S (2006) Classification of electro-oculogram signals using artificial neural network. Expert Systems with Applications 31(1):199-205.
[15] Jegelevicius D, Lukosevicius A, Paunksnis A, Barzdziukas V (2002) Application of data mining technique for diagnosis of posterior Uveal Melanoma. Informatica 13(4):455-464.
[16] Kannel WB, Vasan RS (2009) Is age really a non-modifiable cardiovascular risk factor. American Journal of Cardiology 104(9):1307-1310.
[17] Kantardzic MM, Zurada J (2005) Next Generation of Data-Mining Applications. John Wiley & Sons, Hoboken.
[18] Kenneth HB, Sharon AS (2006) Chest pain: A clinical assessment. Radiologic Clinics of North America 44:165-179.
[19] Khan FS, Anwer RM, Torgersson O, Falkman G (2008) Data mining in oral medicine using decision trees. World Academy of Science, Engineering and Technology 37:225-230.
[20] Kononenko I (2001) Machine learning for medical diagnosis: history, state of the art and perspective. Artificial Intelligence in Medicine 23(1):89-109.
[21] Lin WT, Wang ST, Chiang TC, Shi YX, Chen WY, Chen HM (2010) Abnormal diagnosis of emergency department triage explored with data mining technology: An emergency department at a medical center in Taiwan taken as an example. Expert Systems with Applications 37(4):2733-2741.
[22] Majumder SK, Ghosh N, Gupta PK (2005) Support vector machine for optical diagnosis of cancer. Journal of Biomedical Optics 10(2):24-34.
[23] Martinez-Selles M, Bueno H, Sacrist├ín A, Estévez A, Ortiz J, Gallego L, Fern├índez-Avilés F (2008) Chest pain in the emergency department: incidence, clinical characteristics and risk stratification. Revista Espanola de Cardiologia 61(9):953-959.
[24] Masuda G, Sakamoto N, Yamamoto R (2002) A framework for dynamic evidence based medicine using data mining, in Proceedings of 15th IEEE Symposium on Computer-Based Medical Systems.
[25] Mitchell TM (1999) Machine Learning and Data Mining. Communications of the ACM 42(11):30-36.
[26] Motoda H, Ohara K (2009) Apriori. in: V. Kumar (Eds.), The Top Ten Algorithms in Data Mining. Chapman & Hall/CRC, FL, 61-92.
[27] Qiao DD (2009) Clinical diagnosis of life threatening chest diseases: based on 156 cases. Journal of Chinese Modern Medicine.
[28] Quinlan JR (1993) C4.5: programs for machine learning. Morgan Kaufmann Publishers.
[29] Ramakrishnan N (2009) C4.5. in: V. Kumar (Eds.), The Top Ten Algorithms in Data Mining. Chapman & Hall/CRC, FL, 1-19.
[30] Ren H (2007) Clinical diagnosis of chest pain. Chinese Journal for Clinicians 36:5-7.
[31] Riccardo B, Blaz Z (2008) Predictive data mining in clinical medicine: current issues and guidelines. International Journal of Medical Informatics 77:81-97.
[32] Ridker PM, Hennekens CH, Buring JE, Rifai N (2000) C-reactive protein and other markers of inflammation in the prediction of cardiovascular disease in women. New England Journal of Medicine 342:836-843.
[33] Rossille D, Cuggia M, Arnault A, Bouget J, Le Beux P (2008) Managing an emergency department by analyzing HIS medical data: a focus on elderly patient clinical pathways. Health Care Management Science 11(2):139-146.
[34] Shmueli G, Patel NR, Bruce PC (2007) Data Mining for Business Intelligence: Concepts, Techniques, and Applications in Microsoft Office Excel with XLMiner. John Wiley & Sons, Hoboken.
[35] Statistics Korea (2010), http://www.kostat.go.kr/.
[36] Tan Y, Yin GF, Li GB, Chen JY (2007) Mining compatibility rules from irregular Chinese traditional medicine database by Apriori algorithm. Journal of Southwest JiaoTong University 15(4).
[37] Velagaleti RS, Massaro J, Vasan RS, Robins SJ, Kannel WB, Levy D (2009) Relations of lipid concentrations to heart failure incidence: the Framingham Heart Study. Circulation 120(23):2345-2351.
[38] Yun YP (2008) Application and research of data mining based on C4.5 Algorithm. Harbin University of Science and Technology.
[39] Zaki MJ (2004) Mining non-redundant association rules. Data Mining and Knowledge Discovery 9(3):223-248.