Respiratory infections are a major concern in pig farming as they negatively impact animal health and productivity. Coughing is a key symptom of respiratory disease and can be classified as productive or non-productive, but human assessment often leads to inconsistencies. This study aimed to use a machine learning model to classify pig coughs and investigate their association with respiratory infections. Cough sounds from 49 fattening pigs were recorded and analyzed using a Python-based machine learning system. The model’s accuracy in detecting coughs was 0.72, compared to 0.69 for farmers. For classification of non-productive coughs, the machine learning results showed strong agreement with infection status by Mycoplasma hyopneumoniae, with a Spearman’s correlation of 0.80 and a Cohen’s Kappa of 0.79. However, the association with Porcine Circovirus type 2 was weak, with correlation and Kappa values of 0.05 and 0.037, respectively. These findings indicate that machine learning can classify pig coughs more accurately than human evaluators and that non-productive coughs are strongly linked to Mycoplasma infection but not to PCV2. This suggests the potential use of machine learning for more reliable disease monitoring and early detection in swine production.
Non-typhoidal Salmonella (NTS) is still one of the most infectious foodborne pathogens causing problematic health issues worldwide in both human and veterinary medicine. Poultry meat was one of the important sources of NTS spreading and tended to be highly resistant to antibiotics. The aim of this study was to determine the prevalence, serotypes, and antimicrobial-resistant patterns of Salmonella circulating in broiler farms and poultry slaughterhouses in an intensive farming area in the upper northern part of Thailand from August to October 2019. Fifty samples of boot swabs were collected from 50 broiler farms, 50 cecal samples, and 250 neck skin samples from slaughterhouses. Salmonella was identified by culture method and serum-agglutination and antimicrobial susceptibility testing was tested using the automated VITEK-2 compact system. This study's total prevalence of Salmonella was 53.71% (n=188/350). We found that 53% (159/300) of cecal and neck skins samples were collected from slaughterhouses and 58% (29/50) of boot swabs collected from broiler farms were positive for NTS. Twenty-four serotypes of NTS were identified, the most encountered was S. Kentucky. The antimicrobial-resistant patterns showed that all the strains were non-susceptible to amikacin, cefalexin, cephalothin, and gentamicin and were susceptible to imipenem, neomycin, and nitrofurantoin. The NTS prevalence in samples from broiler farms was slightly higher than in poultry slaughterhouses indicating that there was contamination in the farming and slaughtering process. Therefore, both hygienic measurements in poultry production and antimicrobial usage in the poultry industry should be considered.
Streptococcus suis is an important cause of disease in pigs and an emerging source of severe human infection, with increasing concerns regarding antimicrobial resistance. This study assessed the occurrence and seroprevalence of S. suis in healthy pigs and characterized the antimicrobial susceptibility, serotypes, virulence associated genes, and genomic features of colonizing isolates. A total of 58 pigs (13 farm pigs and 45 abattoir pigs) were sampled. Among 176 presumptive isolates recovered by culture, 60 were confirmed as S. suis by polymerase chain reaction (PCR) and were subsequently analyzed. Antimicrobial susceptibility was determined by the disc diffusion method, selected resistance and virulence genes were detected by conventional PCR, and two representative isolates were subjected to whole-genome sequencing (WGS) and comparative genomic analyses. Seroprevalence was determined using an indirect ELISA detecting IgG antibodies against S. suis serotype 2 antigen. S. suis was confirmed in 60/176 presumptive isolates (34.1%), most frequently from nasal swabs and tonsils, whereas no blood isolates were detected. The seropositivity rate was 65.5%. High resistance rates were observed for ceftriaxone, ampicillin, cefepime, clindamycin, and tetracycline, and multidrug resistance was common. Tetracycline- and macrolide-associated resistance genes were frequently detected. Serotypes 2/1⁄2 predominated, whereas major classical invasive virulence genes were not detected, consistent with predominantly colonizing strains. Whole genome sequencing of two representative isolates confirmed species identity and revealed substantial genomic diversity, including a markedly larger genome in a tonsillar isolate, suggesting acquisition of accessory genetic elements. These findings demonstrate that healthy pigs can harbor genetically diverse and antimicrobial resistant S. suis, highlighting the importance of continued surveillance to support antimicrobial stewardship and reduce zoonotic risk.