HIV 환자 입원 예측 연구를 위한 베이시안 네트워크 활용
Application of a 3 Bayesian Network to Predict Hospitalization among HIV Adults
1
조회
0
다운로드
0
인용
0
참고문헌
초록
Abstract
Objective: The purpose of this study was to explore the potential application of a Bayesian network, an emerging data mining technique, in predicting outcomes using large healthcare databases. Methods: The HIV Cost and Services Utilization Study(HCSUS) dataset, consisting of 2,864 HIV positive adults in the US, was used. A total of 35 variables were selected including one output variable defined as more than one hospitalization in six months representing a sub-optimal pattern of healthcare utilization in HIV care. The HUGIN Researcher 6.2 was used to develop a Bayesian network model with two learning algorithms: 1) Necessary Path Condition(NPC) to construct a Bayesian network structure, and 2) Expectation-Maximization(EM) algorithm to estimate parameters. Results: The area under the Receiver Operating Characteristic(ROC) curve was .72. The accuracy of the prediction model was .66. Sensitivity and specificity were .65 and .66, respectively.Conclusion: The Bayesian network showed fair performance in this prediction problem. This study provides researchers new insight into working with large sets of data, which continue to grow in a number of cases and variables. The repeated testing and refinement of the Bayesian network modeling techniques with other health outcomes in large databases is recommended.
참고문헌 (26)
- "Knowledge discovery in large data sets A primer for data mining applications in health . Nursing Informatics", pp.139~148 (2000)
- "Medical data mining and knowledge discovery." (2001), Physica-Verlag
- "Advances in knowledge discovery and data mining" (1996), MIT Press
- "Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes", 49, pp.1225~1232 (1996)
- "Neural networks in clinical medicine,", 16((4):), pp.386~398 (1996)
- "Bayesian networks for data mining", 1, pp.79~119 (1997)
- "Probabilistic networks and expert systems" (1999), Springer
- "Bayesian networks for knowledge discovery Advances in knowledge discovery and data mining The MIT Press", pp.273~305 (1996), CA: The MIT Press
- "Probabilistic reasoning in intelligent systems Networks of plausible inference,San Francisco, CA" (1988), Morgan Kaufmann Publishers
- "Learning Bayesian networks: The combination of knowledge and statistical dataMSR-TR-94-09 Microsoft Research" (1995)
- "A comparison of three techniques for rapid model development An application in patient risk-stratification", pp.443~447 (1996)
- "Diagnosing community-acquired pneumonia with a Bayesian network", pp.632~636 (1998)
- "A Bayesian network for mammography", pp.106~110 (2000)
- "Variations in the care of HIV-infected adults in the United States Results from the HIV Cost and Services Utilization Study", 281((24):), pp.2305~2315
- "Bayesian networks for knowledge discovery in large datasets Basics for nurse researchers", (4(5)), pp.389~399 (2003)
- "An introduction to Bayesian networks" (1996), UCL Press
- "Introduction to health services", pp.87~109 (1999), Delmar Publisher
- "Equity of access to medical care", pp.4~27
- "Indicators and predictors of health services utilization Introduction to health services", pp.46~70 (1993), Delmar Publisher Inc
- "Health services utilization models Handbook of health behavior research I", pp.153~172 (1997), Plenum Press
- "Handling missing data in survey research", 5((3), pp.215~238 (1996)
- "The EM algorithm for graphical association models with missing data", 19, pp.191~201 (1995)
- "Missing data in nursing research Review of issues and treatment strategies", ;2((1):), pp.31~38 (2003)
- "Goodness of fit tests for the multiple logistic regression model Communications in Statistics 1980", pp.1043~1069
- "Conditions for the optimality of the simple Bayesian Classifier Proceeding of the Thirteenth International Conference on Machine Learning 1996", pp.105~112
- "Transforming classifier score into accurate multiclass probability estimates Proceedings of the Eighth International Conference on Knowledge Discovery and Data Mining 2002", pp.694~699 (2002)