Use of Data Mining Techniques to Determine and Predict Length of Stay of Cardiac Patients
2
조회
0
다운로드
7
인용
0
참고문헌
키워드
초록
Objectives: Predicting the length of stay (LOS) of patients in a hospital is important in providing them with better services and higher satisfaction, as well as helping the hospital management plan and managing hospital resources as meticulously as possible. We propose applying data mining techniques to extract useful knowledge and draw an accurate model to predict the LOS of heart patients. Methods: Data were collected from patients with coronary artery disease (CAD). The patient records of 4,948 patients who had suffered CAD were included in the analysis. The techniques used are classification with three algorithms, namely, decision tree, support vector machines (SVM), and artificial neural network (ANN). LOS is the target variable, and 36 input variables are used for prediction. A confusion matrix was obtained to calculate sensitivity, specificity, and accuracy. Results: The overall accuracy of SVM was 96.4% in the training set. Most single patients (64.3%) had an LOS ≤5 days, whereas 41.2% of married patients had an LOS >10 days. Moreover, the study showed that comorbidity states, such as lung disorders and hemorrhage with drug consumption have an impact on long LOS. The presence of comorbidities, an ejection fraction <2, being a current smoker, and having social security type insurance in coronary artery patients led to longer LOS than other subjects. Conclusions: All three algorithms are able to predict LOS with various degrees of accuracy. The findings demonstrated that the SVM was the best fit. There was a significant tendency for LOS to be longer in patients with lung or respiratory disorders and high blood pressure.
Abstract
Objectives: Predicting the length of stay (LOS) of patients in a hospital is important in providing them with better services and higher satisfaction, as well as helping the hospital management plan and managing hospital resources as meticulously as possible. We propose applying data mining techniques to extract useful knowledge and draw an accurate model to predict the LOS of heart patients. Methods: Data were collected from patients with coronary artery disease (CAD). The patient records of 4,948 patients who had suffered CAD were included in the analysis. The techniques used are classification with three algorithms, namely, decision tree, support vector machines (SVM), and artificial neural network (ANN). LOS is the target variable, and 36 input variables are used for prediction. A confusion matrix was obtained to calculate sensitivity, specificity, and accuracy. Results: The overall accuracy of SVM was 96.4% in the training set. Most single patients (64.3%) had an LOS ≤5 days, whereas 41.2% of married patients had an LOS >10 days. Moreover, the study showed that comorbidity states, such as lung disorders and hemorrhage with drug consumption have an impact on long LOS. The presence of comorbidities, an ejection fraction <2, being a current smoker, and having social security type insurance in coronary artery patients led to longer LOS than other subjects. Conclusions: All three algorithms are able to predict LOS with various degrees of accuracy. The findings demonstrated that the SVM was the best fit. There was a significant tendency for LOS to be longer in patients with lung or respiratory disorders and high blood pressure.
참고문헌 (35)
- Wright SP, "Factors influencing the length of hospital stay of patients with heart failure", Eur J Heart Fail, 5(2), pp.201~209 (2003)
- Gomez V, "Using data mining to describe long hospital stays", Paradigma, 3(1), pp.1~10 (2009)
- Lim A, "Methods for analyzing hospital length of stay with application to inpatients dying in Southern Thailand", Glob J Health Sci, 1(1), pp.27~38 (2009)
- Chang KC, "Prediction of length of stay of first-ever ischemic stroke", Stroke, 33(11), pp.2670~2674 (2002)
- Jiang X, "Using data mining to analyze patient discharge data for an urban hospital", Proceedings of the 2010 International Conference on Data Mining, pp.139~144 (2010)
- Isken MW, "Data mining to support simulation modeling of patient flow in hospitals", J Med Syst, 26(2), pp.179~197 (2002)
- Walczak S, "Predicting hospital length of stay with neural networks", Proceedings of the Eleventh International FLAIRS Conference, pp.333~337 (1998)
- Rowan M, "The use of artificial neural networks to stratify the length of stay of cardiac patients based on preoperative and initial postoperative factors", Artif Intell Med, 40(3), pp.211~221 (2007)
- Robinson GH, "Prediction of hospital length of stay", Health Serv Res, 1(3), pp.287~300 (1966)
- Arab M, "Analysis of factors affecting length of stay in public hospitals in Lorestan Province, Iran", Hakim Res J, 12(4), pp.27~32 (2010)
- Blais MA, "Predicting length of stay on an acute care medical psychiatric inpatient service", Adm Policy Ment Health, 31(1), pp.15~29 (2003)
- Tu JV, "Use of a neural network as a predictive instrument for length of stay in the intensive care unit following cardiac surgery", Proc Annu Symp Comput Appl Med Care, pp.666~672 (1992)
- Lin CL, "Model-based prediction of length of stay for rehabilitating stroke patients", J Formos Med Assoc, 108(8), pp.653~662 (2009)
- Wrenn J, "Estimating patient's length of stay in the Emergency Department with an artificial neural network", AMIA Annu Symp Proc, 2005, pp.1155~ (2005)
- Stoskopf C, "Predicting length of stay for patients with psychoses", Health Serv Res, 26(6), pp.743~766 (1992)
- Negassa A, "Prediction of length of stay following elective percutaneous coronary intervention", ISRN Surg, 2011, pp.714935~ (2011)
- Jilani TA, "Acute coronary syndrome prediction using data mining techniques: an application", Int J Inf Math Sci, 5(4), pp.295~299 (2009)
- Liu P, "Healthcare data mining: predicting inpatient length of stay", Proceedings of the 3rd International IEEE Conference Intelligent Systems, pp.832~837 (2006)
- Kudyba S, "Identifying factors that impact patient length of stay metrics for healthcare providers with advanced analytics", Health Informatics J, 16(4), pp.235~245 (2010)
- Rani KU, "Analysis of heart diseases dataset using neural network approach", Int J Data Min Knowl Manag Process, 1(5), pp.1~8 (2011)
- Kamath C, "Scientific data mining: a practical perspective" (2009), Society for Industrial and Applied Mathematics
- Soo-Kyoung Lee, "Application of Support Vector Machine for Prediction of Medication Adherence in Heart Failure Patients", Healthcare Informatics Research, 16(4), pp.253~259 (2010), 대한의료정보학회
- Kajabadi A, "Data mining cardiovascular risk factors", Proceedings of International Conference on Application of Information and Communication Technologies, pp.1~5 (2009)
- Suryawanshi RD, "Classification techniques of datamining to identify class of the text with fuzzy logic", Proceedings of 2012 International Conference on Information and Computer Applications, pp.263~267 (2012)
- Sitar-Taut DA, "Overview on how data mining tools may support cardiovascular disease prediction", J Appl Comput Sci, 4(8), pp.57~62 (2010)
- Wexler L, "Coronary artery calcification: pathophysiology, epidemiology, imaging methods, and clinical implications. A statement for health professionals from the American Heart Association. Writing Group", Circulation, 94(5), pp.1175~1192 (1996)
- 강진오, "Prediction of Hospital Charges for the Cancer Patients withData Mining Techniques", Healthcare Informatics Research, 15(1), pp.13~23 (2009), 대한의료정보학회
- Yaghini M, "Data mining SPSS Clementine 12.0: 4. Handling missing and Clementine outliers values" (2010), IUST
- Mullins IM, "Data mining and clinical data repositories: insights from a 667,000 patient data set", Comput Biol Med, 36(12), pp.1351~1377 (2006)
- Malliaris ME, "Revenue generation in hospital foundations: neural network versus regression model recommendations", Int J Manag Inf Syst, 15(1), pp.59~66 (2011)
- Appelros P, "Prediction of length of stay for stroke patients", Acta Neurol Scand, 116(1), pp.15~19 (2007)
- Ghoson AM, "Decision tree induction & clustering techniques in SAS Enterprise Miner, SPSS Clementine, and IBM Intelligent Miner: a comparative analysis", Int J Manag Inf Syst, 14(3), pp.57~70 (2010)
- Bellazzi R, "Predictive data mining in clinical medicine: current issues and guidelines", Int J Med Inform, 77(2), pp.81~97 (2008)
- McMullan R, "Resource utilisation, length of hospital stay, and pattern of investigation during acute medical hospital admission", Postgrad Med J, 80(939), pp.23~26 (2004)
- Vahidi R, "Factors affecting coronary artery patients hospital length of stay of Tabriz Madani hospital 2005-2006", J Health Adm, 9(25), pp.63~68 (2006)