Prediction of Hospital Charges for the Cancer Patients withData Mining Techniques
2
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
Objective: Predictions of hospital charges for cancer patients are very important, because they provide a basis for allocating medical resources in the hospital and for establishing national medical policies. But previous studies to predict hospital charges were mainly based on statistical analysis, which has used only a small aspect among huge medical data so that the prediction power was limited. Thus we developed four data mining models, including two artificial neural network (ANN) models and two classification and regression tree (CART) models, to predict both the total amount of hospital charges and the amount paid by the insurance of cancer patients and compared their efficacies. Methods: The data was generated from 400,625 medical records of 1,605 cancer patients who had been hospitalized to Kyung Hee University Hospital from March 1, 2003 to February 29, 2004. Clementine 8.1 program was used to build four data mining prediction models, two for the total amount and two for the amount paid by insurance. The variables included all of the data fields of standard medical record form of Korea. The neural network model used feed-forward back propagation method, which had 2 hidden layers. For decision tree model, RELIEFF method was used and the maximum tree depth was set to 30. We divided the dataset into 67% of training dataset and 33% of test dataset, using stratified sampling. Linear correlation coefficient and gain chart were compared. Results: The ANN models showed better linear correlation coefficient than the CART models in predicting both the total amount (0.824 vs. 0.791) and the amount paid by insurance (0.838 vs. 0.699). The estimated accuracy of ANN model was more than 98% to predict both total amount and amount paid by insurance. The CART model for total amount showed that the relative importance of the variables were duration of admission(0.073), number of consultation(0.061), and treatment group 16(0.06). The CART model for the amount paid by insurance showed that the relative importance of the cariables were duration of admission (0.09), number of ICU admission (0.063), and number of consultations (0.062). The percent gain of ANN model shows better %gain than CART to predict total amount but to predict amount paid by insurance, ANN showed similar pattern to CART Conclusion: The ANN models showed better prediction accuracy than CART models. However, the CART models, which serve different information from ANN model, can be used to allocate limited medical resources effectively and efficiently. For the purpose of establishing medical policies and strategies, using those models together is warranted.
Abstract
Objective: Predictions of hospital charges for cancer patients are very important, because they provide a basis for allocating medical resources in the hospital and for establishing national medical policies. But previous studies to predict hospital charges were mainly based on statistical analysis, which has used only a small aspect among huge medical data so that the prediction power was limited. Thus we developed four data mining models, including two artificial neural network (ANN) models and two classification and regression tree (CART) models, to predict both the total amount of hospital charges and the amount paid by the insurance of cancer patients and compared their efficacies. Methods: The data was generated from 400,625 medical records of 1,605 cancer patients who had been hospitalized to Kyung Hee University Hospital from March 1, 2003 to February 29, 2004. Clementine 8.1 program was used to build four data mining prediction models, two for the total amount and two for the amount paid by insurance. The variables included all of the data fields of standard medical record form of Korea. The neural network model used feed-forward back propagation method, which had 2 hidden layers. For decision tree model, RELIEFF method was used and the maximum tree depth was set to 30. We divided the dataset into 67% of training dataset and 33% of test dataset, using stratified sampling. Linear correlation coefficient and gain chart were compared. Results: The ANN models showed better linear correlation coefficient than the CART models in predicting both the total amount (0.824 vs. 0.791) and the amount paid by insurance (0.838 vs. 0.699). The estimated accuracy of ANN model was more than 98% to predict both total amount and amount paid by insurance. The CART model for total amount showed that the relative importance of the variables were duration of admission(0.073), number of consultation(0.061), and treatment group 16(0.06). The CART model for the amount paid by insurance showed that the relative importance of the cariables were duration of admission (0.09), number of ICU admission (0.063), and number of consultations (0.062). The percent gain of ANN model shows better %gain than CART to predict total amount but to predict amount paid by insurance, ANN showed similar pattern to CART Conclusion: The ANN models showed better prediction accuracy than CART models. However, the CART models, which serve different information from ANN model, can be used to allocate limited medical resources effectively and efficiently. For the purpose of establishing medical policies and strategies, using those models together is warranted.
참고문헌 (19)
- "National Health Insurance Statistics"[URL]
- Seok-JunYoon, "Estimation of the Burden of Major Cancers in Korea", Journal of Korean Medical Science, 17(5), pp.604~610 (2002), 대한의학회
- Hirano S, "Multiscale analysis of long time-seriesmedical databases", AMIAAnnu Symp Proc., pp.289~293 (2003)
- Ismae lMB, "Acomparison of neural network models for the prediction of the cost of care for acute coronary syndrome patients", Proc AMIA Symp., pp.533~537 (1998)
- Demsar J, "Feature mining and predictive model construction from severe trauma patient's data", Int J Med Inform., 63(1), pp.41~50 (2001)
- Brooks SE, "Health care cost and utilization project analysis of comorbid illness and complications for patients undergoing hysterectomy for endometrial carcinoma", Cancer., 92(4), pp.950~958 (2001)
- Penberthy L, "Predictors ofMedicare costs in elderly beneficiaries with breast, colorectal, lung, or prostate cancer", Health Care Manag Sci., 2(3), pp.149~160 (1999)
- Tollestrup K, "The excess costs of breast cancer health care in Hispanic and non-Hispanic female members of a managed care organization", Breast Cancer Res Treat, 66(1), pp.25~31 (2001)
- Dayhoff JE, "Artificial neural networks: opening the black box", Cancer, 91(8), pp.1615~1635 (2001)
- Goss E, "Improving Health Care Organizational Management Through Neural Network Learning", Health CareManag Sci., 5(3), pp.221~227 (2002)
- Marshall AH, "Addressing bed costs for the elderly: a new methodology for modelling patient outcomes and length of stay", Health Care Manag Sci., 7(1), pp.27~33 (2004)
- Chae YM, "Data mining approach to policy analysis in a health insurance domain", Int JMed Inform., 62(2), pp.103~111 (2001)
- Lee Seung Mi, "Comparison of Hospital Charge Prediction Models for Colorectal Cancer Patients: Neural Network vs. Decision Tree Models", Journal of Korean Medical Science, 19(5), pp.677~681 (2004), 대한의학회
- Chien CW, "The application of artificial neural networks and decision treemodel in predicting post-operative complication for gastric cancer patients", Hepatogastroenterology, 55(84), pp.1140~1145 (2008)
- Goss EP, "Improving health care organizational management through neural network learning", Health Care Manag Sci., 5(3), pp.221~227 (2002)
- Fogel DB, "Evolving artificial neural networks for screening features from mammograms", Artif Intell Med., 14(3), pp.317~326 (1998)
- Kononenko I, "Machine learning for medical diagnosis: history, state of the art and perspective", Artif Intell Med., 23(1), pp.89~109 (2001)
- Bojarczuk CC, "A constrained-syntax genetic programming system for discovering classification rules: application to medical data sets", Artif Intell Med., 30(1), pp.27~48 (2004)
- Breault JL, "Data mining a diabetic data warehouse", Artif Intell Med., 26(1), pp.37~54 (2002)