Classification of porcine reproductive and respiratory syndrome clinical impact in Ontario sow herds using machine learning approaches

被引:2
作者
Chadha, Akshay [1 ]
Dara, Rozita [1 ]
Pearl, David L. [2 ]
Gillis, Daniel [1 ]
Rosendal, Thomas [3 ]
Poljak, Zvonimir [2 ]
机构
[1] Univ Guelph, Sch Comp Sci, Guelph, ON, Canada
[2] Univ Guelph, Ontario Vet Coll, Dept Populat Med, Guelph, ON, Canada
[3] Natl Vet Inst, SVA, Uppsala, Sweden
基金
加拿大自然科学与工程研究理事会;
关键词
PRRS; pathogenicity; classifcation; machine learning; ORF5; gene; SYNDROME VIRUS PRRSV; SWINE HERDS; MORTALITY; ASSOCIATION; GENETICS; DISEASE; SIGNS;
D O I
10.3389/fvets.2023.1175569
中图分类号
S85 [动物医学(兽医学)];
学科分类号
0906 ;
摘要
Since the early 1990s, porcine reproductive and respiratory syndrome (PRRS) virus outbreaks have been reported across various parts of North America, Europe, and Asia. The incursion of PRRS virus (PRRSV) in swine herds could result in various clinical manifestations, resulting in a substantial impact on the incidence of respiratory morbidity, reproductive loss, and mortality. Veterinary experts, among others, regularly analyze the PRRSV open reading frame-5 (ORF-5) for prognostic purposes to assess the risk of severe clinical outcomes. In this study, we explored if predictive modeling techniques could be used to identify the severity of typical clinical signs observed during PRRS outbreaks in sow herds. Our study aimed to evaluate four baseline machine learning (ML) algorithms: logistic regression (LR) with ridge and lasso regularization techniques, random forest (RF), k-nearest neighbor (KNN), and support vector machine (SVM), for the clinical impact classification of ORF-5 sequences and demographic data into high impact and low impact categories. First, baseline classifiers were evaluated using different input representations of ORF-5 nucleotides, amino acid sequences, and demographic data using a 10-fold cross-validation technique. Then, we designed a consensus voting ensemble approach to aggregate the different types of input representations for genetic and demographic data for classifying clinical impact. In this study, we observed that: (a) for abortion and pre-weaning mortality (PWM), different classifiers gained improvement over baseline accuracy, which showed the plausible presence of both genotypic-phenotypic and demographic-phenotypic relationships, (b) for sow mortality (SM), no baseline classifier successfully established such linkages using either genetic or demographic input data, (c) baseline classifiers showed good performance with a moderate variance of the performance metrics, due to high-class overlap and the small dataset size used for training, and (d) the use of consensus voting ensemble techniques helped to make the predictions more robust and stabilized the performance evaluation metrics, but overall accuracy did not substantially improve the diagnostic metrics over baseline classifiers.
引用
收藏
页数:10
相关论文
共 52 条
[11]   Biomedical informatics and machine learning for clinical genomics [J].
Diao, James A. ;
Kohane, Isaac S. ;
Manrai, Arjun K. .
HUMAN MOLECULAR GENETICS, 2018, 27 (R1) :R29-R34
[12]   Porcine reproductive and respiratory syndrome (PRRS): A review, with emphasis on pathological, virological and diagnostic aspects [J].
Done, SH ;
Paton, DJ ;
White, MEC .
BRITISH VETERINARY JOURNAL, 1996, 152 (02) :153-174
[13]   Detection of PRRSV circulation in herds without clinical signs of PRRS: Comparison of five age groups to assess the preferred age group and sample size [J].
Duinhof, T. F. ;
van Schaik, G. ;
van Eschl, E. J. B. ;
Wellenberg, G. J. .
VETERINARY MICROBIOLOGY, 2011, 150 (1-2) :180-184
[14]   Machine learning, medical diagnosis, and biomedical engineering research - commentary [J].
Foster, Kenneth R. ;
Koprowski, Robert ;
Skufca, Joseph D. .
BIOMEDICAL ENGINEERING ONLINE, 2014, 13
[15]   ExPASy: the proteomics server for in-depth protein knowledge and analysis [J].
Gasteiger, E ;
Gattiker, A ;
Hoogland, C ;
Ivanyi, I ;
Appel, RD ;
Bairoch, A .
NUCLEIC ACIDS RESEARCH, 2003, 31 (13) :3784-3788
[16]   Enhanced Regulatory Sequence Prediction Using Gapped k-mer Features [J].
Ghandi, Mahmoud ;
Lee, Dongwon ;
Mohammad-Noori, Morteza ;
Beer, Michael A. .
PLOS COMPUTATIONAL BIOLOGY, 2014, 10 (07)
[17]   Associations between genetics, farm characteristics and clinical disease in field outbreaks of porcine reproductive and respiratory syndrome virus [J].
Goldberg, TL ;
Weigel, RM ;
Hahn, EC ;
Scherba, G .
PREVENTIVE VETERINARY MEDICINE, 2000, 43 (04) :293-302
[18]   Complete genome analysis of RFLP 184 isolates of porcine reproductive and respiratory syndrome virus [J].
Han, Jun ;
Wang, Yue ;
Faaberg, Kay S. .
VIRUS RESEARCH, 2006, 122 (1-2) :175-182
[19]   Polymorphic genetic characterization of the ORF7 gene of porcine reproductive and respiratory syndrome virus (PRRSV) in China [J].
Hao, Xiaofang ;
Lu, Zengjun ;
Kuang, Wendong ;
Sun, Pu ;
Fu, Yu ;
Wu, Lei ;
Zhao, Qing ;
Bao, Huifang ;
Fu, Yuanfang ;
Cao, Yimei ;
Li, Pinghua ;
Bai, Xingwen ;
Li, Dong ;
Liu, Zaixin .
VIROLOGY JOURNAL, 2011, 8
[20]   Comparison of host genetic factors influencing pig response to infection with two North American isolates of porcine reproductive and respiratory syndrome virus [J].
Hess, Andrew S. ;
Islam, Zeenath ;
Hess, Melanie K. ;
Rowland, Raymond R. R. ;
Lunney, Joan K. ;
Doeschl-Wilson, Andrea ;
Plastow, Graham S. ;
Dekkers, Jack C. M. .
GENETICS SELECTION EVOLUTION, 2016, 48