Using robust Bayesian network to estimate the residuals of fluoroquinolone antibiotic in soil

Prediction of antibiotic pollution and its consequences is difficult, due to the uncertainties and complexities associated with multiple related factors. This article employed domain knowledge and spatial data to construct a Bayesian network (BN) model to assess fluoroquinolone antibiotic (FQs) pollution in the soil of an intensive vegetable cultivation area. The results show: (1) The relationships between FQs pollution and contributory factors: Three factors (cultivation methods, crop rotations, and chicken manure types) were consistently identified as predictors in the topological structures of three FQs, indicating their importance in FQs pollution; deduced with domain knowledge, the cultivation methods are determined by the crop rotations, which require different nutrients (derived from the manure) according to different plant biomass. (2) The performance of BN model: The integrative robust Bayesian network model achieved the highest detection probability (pd) of high-risk and receiver operating characteristic (ROC) area, since it incorporates domain knowledge and model uncertainty. Our encouraging findings have implications for the use of BN as a robust approach to assessment of FQs pollution and for informing decisions on appropriate remedial measures.

[1]  Velimir V. Vesselinov,et al.  Maximum likelihood Bayesian averaging of airflow models in unsaturated fractured tuff using Occam and variance windows , 2010 .

[2]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[3]  M. Papich,et al.  Plasma and interstitial fluid pharmacokinetics of enrofloxacin, its metabolite ciprofloxacin, and marbofloxacin after oral administration and a constant rate intravenous infusion in dogs. , 2005, Journal of Veterinary Pharmacology and Therapeutics.

[4]  Hui Wang,et al.  Residues of veterinary antibiotics in manures from feedlot livestock in eight provinces of China. , 2010, The Science of the total environment.

[5]  R. Bouckaert Bayesian belief networks : from construction to inference , 1995 .

[6]  Gefu Zhu,et al.  Potential effect and accumulation of veterinary antibiotics in Phragmites australis under hydroponic conditions , 2013 .

[7]  J. Dewulf,et al.  Fluoroquinolone antibiotics: an emerging class of environmental micropollutants. , 2014, The Science of the total environment.

[8]  Nir Friedman,et al.  Bayesian Network Classifiers , 1997, Machine Learning.

[9]  Qixing Zhou,et al.  Occurrence and source analysis of typical veterinary antibiotics in manure, soil, vegetables and groundwater from organic vegetable bases, northern China. , 2010, Environmental pollution.

[10]  J. Martínez Antibiotics and Antibiotic Resistance Genes in Natural Environments , 2008, Science.

[11]  Louis Anthony Cox,et al.  Risk Analysis Foundations, Models, and Methods , 2001 .

[12]  Jin-feng Wang,et al.  Investigation of residual fluoroquinolones in a soil-vegetable system in an intensive vegetable cultivation area in Northern China. , 2014, The Science of the total environment.

[13]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[14]  Pat Langley,et al.  Estimating Continuous Distributions in Bayesian Classifiers , 1995, UAI.

[15]  Qiuying Chen,et al.  Eco-toxic effects of sulfadiazine sodium, sulfamonomethoxine sodium and enrofloxacin on wheat, Chinese cabbage and tomato , 2009, Ecotoxicology.

[16]  Jie Li,et al.  Influence of planting patterns on fluoroquinolone residues in the soil of an intensive vegetable cultivation area in northern China. , 2013, The Science of the total environment.

[17]  C. Rosen,et al.  Antibiotic uptake by plants from soil fertilized with animal manure. , 2005, Journal of environmental quality.

[18]  P. Dabert,et al.  Changes in concentrations of fluoroquinolones and of ciprofloxacin-resistant Enterobacteriaceae in chicken feces and manure stored in a heap. , 2012, Journal of environmental quality.

[19]  Hareton K. N. Leung,et al.  Assessment of Catastrophic Risk Using Bayesian Network Constructed from Domain Knowledge and Spatial Data , 2010, Risk analysis : an official publication of the Society for Risk Analysis.

[20]  J. Ross Quinlan,et al.  Improved Use of Continuous Attributes in C4.5 , 1996, J. Artif. Intell. Res..

[21]  Sean M. Smukler,et al.  Transition to large-scale organic vegetable production in the Salinas Valley, California , 2008 .

[22]  Guido Bugmann,et al.  Normalized Gaussian Radial Basis Function networks , 1998, Neurocomputing.

[23]  H. Ding,et al.  Population pharmacokinetics of enrofloxacin and its active metabolite ciprofloxacin in ill cows. , 2008, Journal of veterinary pharmacology and therapeutics.

[24]  G. Sposito,et al.  Inhibition of photosynthesis by a fluoroquinolone antibiotic. , 2010, Environmental science & technology.

[25]  Adrian E. Raftery,et al.  Bayesian Model Averaging: A Tutorial , 2016 .

[26]  I. Fetzer,et al.  Biodegradation of ciprofloxacin in water and soil and its effects on the microbial communities. , 2011, Journal of hazardous materials.

[27]  Sisi Zhao,et al.  A Bayesian Method to Mine Spatial Data Sets to Evaluate the Vulnerability of Human Beings to Catastrophic Risk , 2012, Risk analysis : an official publication of the Society for Risk Analysis.

[28]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

[29]  Gregory F. Cooper,et al.  A Bayesian Method for the Induction of Probabilistic Networks from Data , 1992 .

[30]  S. Kuchta,et al.  Lincomycin and Spectinomycin Concentrations in Liquid Swine Manure and Their Persistence During Simulated Manure Storage , 2009, Archives of environmental contamination and toxicology.

[31]  A. Williams,et al.  The fungus Pestalotiopsis guepini as a model for biotransformation of ciprofloxacin and norfloxacin , 2001, Applied Microbiology and Biotechnology.

[32]  S. Sathiya Keerthi,et al.  Improvements to Platt's SMO Algorithm for SVM Classifier Design , 2001, Neural Computation.

[33]  E. Turiel,et al.  Multiresidue analysis of quinolones and fluoroquinolones in soil by ultrasonic-assisted extraction in small columns and HPLC-UV , 2006 .

[34]  M. Spiteller,et al.  Fluoroquinolone antibiotics in the environment. , 2007, Reviews of environmental contamination and toxicology.

[35]  C. Solans,et al.  Determination of enrofloxacin and its primary metabolite, ciprofloxacin, in pig tissues. Application to residue studies. , 2005, Biomedical chromatography : BMC.

[36]  Jianying Hu,et al.  Trace analysis of quinolone and fluoroquinolone antibiotics from wastewaters by liquid chromatography-electrospray tandem mass spectrometry. , 2008, Journal of chromatography. A.

[37]  Wray L. Buntine A Guide to the Literature on Learning Probabilistic Networks from Data , 1996, IEEE Trans. Knowl. Data Eng..

[38]  C. N. Liu,et al.  Approximating discrete probability distributions with dependence trees , 1968, IEEE Trans. Inf. Theory.

[39]  Adrian E. Raftery,et al.  Bayesian model averaging: a tutorial (with comments by M. Clyde, David Draper and E. I. George, and a rejoinder by the authors , 1999 .