Risk assessment of human neural tube defects using a Bayesian belief network

作者: Yilan Liao , Jinfeng Wang , Yaoqin Guo , Xiaoying Zheng

DOI: 10.1007/S00477-009-0303-5

关键词: Neural tubeBayesian networkRural areaRisk assessmentStatisticsConfidence intervalComputer science

摘要: Neural tube defects (NTDs) constitute the most common type of birth defects. How much risk NTDs could an area take? The answer to this question will help people understand geographical distribution and explore its environmental causes. Most existing methods usually take spatial correlation cases into account rarely consider effect factors. However, especially in rural areas, have a little on each other across space, whereas role factors is significant. To demonstrate these points, Heshun, county with highest rate China, was selected as region interest study. Bayesian belief network used quantify probability occurred at villages no births. study indicated that proposed method easy apply high accuracy achieved 95% confidence level.

参考文章(29)
Ross D. Shachter, Daniel L. Rubin, Elizabeth S. Burnside, A Bayesian network for mammography. american medical informatics association annual symposium. pp. 106- 110 ,(2000)
Paola Sebastiani, Vikki G. Nolan, Clinton T. Baldwin, Maria M. Abad-Grau, Ling Wang, Adeboye H. Adewoye, Lillian C. McMahon, Lindsay A. Farrer, James G. Taylor, Gregory J. Kato, Mark T. Gladwin, Martin H. Steinberg, A network model to predict the risk of death in sickle cell disease Blood. ,vol. 110, pp. 2727- 2735 ,(2007) , 10.1182/BLOOD-2007-04-084921
Viroj Wiwanitkit, Estimating cancer risk due to benzene exposure in some urban areas in Bangkok Stochastic Environmental Research and Risk Assessment. ,vol. 22, pp. 135- 137 ,(2008) , 10.1007/S00477-007-0103-8
Sun-Mi Lee, Patricia A. Abbott, Bayesian networks for knowledge discovery in large datasets: basics for nurse researchers Journal of Biomedical Informatics. ,vol. 36, pp. 389- 399 ,(2003) , 10.1016/J.JBI.2003.09.022
I. Maglogiannis, E. Zafiropoulos, A. Platis, C. Lambrinoudakis, Risk analysis of a patient monitoring system using Bayesian Network modeling Journal of Biomedical Informatics. ,vol. 39, pp. 637- 647 ,(2006) , 10.1016/J.JBI.2005.10.003
Wenxue Chi, Jinfeng Wang, Xinhu Li, Xiaoying Zheng, Yilan Liao, Application of GIS-based spatial filtering method for neural tube defects disease mapping Wuhan University Journal of Natural Sciences. ,vol. 12, pp. 1125- 1130 ,(2007) , 10.1007/S11859-007-0097-6
Robert A. Canales, James O. Leckie, Application of a stochastic model to estimate children’s short-term residential exposure to lead Stochastic Environmental Research and Risk Assessment. ,vol. 21, pp. 737- 745 ,(2007) , 10.1007/S00477-006-0086-X
Afisi S Ismaila, Angelo Canty, Lehana Thabane, Comparison of Bayesian and frequentist approaches in modelling risk of preterm birth near the Sydney Tar Ponds, Nova Scotia, Canada. BMC Medical Research Methodology. ,vol. 7, pp. 39- 39 ,(2007) , 10.1186/1471-2288-7-39