Comparing models for quantitative risk assessment: an application to the European Registry of foreign body injuries in children

被引:10
作者
Berchialla, Paola [1 ]
Scarinzi, Cecilia [2 ]
Snidero, Silvia [2 ]
Gregori, Dario [3 ]
机构
[1] Univ Turin, Dept Clin & Biol Sci, I-10124 Turin, Italy
[2] Univ Turin, Dept Stat & Appl Math Diego de Castro, I-10124 Turin, Italy
[3] Univ Padua, Dept Cardiac Thorac & Vasc Sci, Unit Biostat Epidemiol & Publ Hlth, Via Loredan 18, I-35121 Padua, Italy
关键词
Bayesian Network; children; classification trees; foreign body injuries; quantitative risk assessment; PROJECT; SAFETY;
D O I
10.1177/0962280213476167
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
Risk Assessment is the systematic study of decisions subject to uncertain consequences. An increasing interest has been focused on modeling techniques like Bayesian Networks since their capability of (1) combining in the probabilistic framework different type of evidence including both expert judgments and objective data; (2) overturning previous beliefs in the light of the new information being received and (3) making predictions even with incomplete data. In this work, we proposed a comparison among Bayesian Networks and other classical Quantitative Risk Assessment techniques such as Neural Networks, Classification Trees, Random Forests and Logistic Regression models. Hybrid approaches, combining both Classification Trees and Bayesian Networks, were also considered. Among Bayesian Networks, a clear distinction between purely data-driven approach and combination of expert knowledge with objective data is made. The aim of this paper consists in evaluating among this models which best can be applied, in the framework of Quantitative Risk Assessment, to assess the safety of children who are exposed to the risk of inhalation/insertion/aspiration of consumer products. The issue of preventing injuries in children is of paramount importance, in particular where product design is involved: quantifying the risk associated to product characteristics can be of great usefulness in addressing the product safety design regulation. Data of the European Registry of Foreign Bodies Injuries formed the starting evidence for risk assessment. Results showed that Bayesian Networks appeared to have both the ease of interpretability and accuracy in making prediction, even if simpler models like logistic regression still performed well.
引用
收藏
页码:1244 / 1259
页数:16
相关论文
共 42 条
[1]  
[Anonymous], 1992, RISK PERCEPTION
[2]  
[Anonymous], 1991, PROBABILISTIC REASON
[3]  
[Anonymous], COMMUNICATION ACM
[4]   Perspectives on risk: review and discussion of the basis for establishing a unified and holistic approach [J].
Aven, T ;
Kristensen, V .
RELIABILITY ENGINEERING & SYSTEM SAFETY, 2005, 90 (01) :1-14
[5]   Comparing the predictive value of neural network models to logistic regression models on the risk of death for small-cell lung cancer patients [J].
Bartfay, E ;
Mackillop, WJ ;
Pater, JL .
EUROPEAN JOURNAL OF CANCER CARE, 2006, 15 (02) :115-124
[6]   Predicting severity of foreign body injuries in children in upper airways: An approach based on regression trees [J].
Berchialla, Paola ;
Snidero, Silvia ;
Stancu, Alexandru ;
Scarinzi, Cecilia ;
Corradetti, Roberto ;
Gregori, Dario .
RISK ANALYSIS, 2007, 27 (05) :1255-1263
[7]   SmcHD1, containing a structural-maintenance-of-chromosomes hinge domain, has a critical role in X inactivation [J].
Blewitt, Marnie E. ;
Gendrel, Anne-Valerie ;
Pang, Zhenyi ;
Sparrow, Duncan B. ;
Whitelaw, Nadia ;
Craig, Jeffrey M. ;
Apedaile, Anwyn ;
Hilton, Douglas J. ;
Dunwoodie, Sally L. ;
Brockdorff, Neil ;
Kay, Graham F. ;
Whitelaw, Emma .
NATURE GENETICS, 2008, 40 (05) :663-669
[8]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[9]   Framework for evaluation of physiologically-based pharmacokinetic models for use in safety or risk assessment [J].
Clark, LH ;
Setzer, RW ;
Barton, HA .
RISK ANALYSIS, 2004, 24 (06) :1697-1717
[10]  
Cover T. M, 2006, ELEMENTS INFORM THEO, P748