Accuracy of an AI-based automated plate reading mobile application for the identification of clinical mastitis-causing pathogens in chromogenic culture media.

Using on-farm microbiological culture (OFC), based on chromogenic culture media, enables the identification of mastitis causing pathogens in about 24 h, allows rapid decision making on selective treatment and control management measures of cows with clinical mastitis (CM). However, accurate interpretation of OFC results requires trained and experienced operators, which could be a limitation for the use of OFC in dairy farms. Our hypothesis was that AI-based automated plate reading mobile application can analyze images of microorganisms' colonies in chromogenic culture media with similar diagnostic performance as a trained specialist evaluator. Therefore, the aim of the present study was to evaluate the diagnostic accuracy of an AI-based application (Rumi; OnFarm, Piracicaba, São Paulo, Brazil) for interpreting images of mastitis causing microorganism colonies grown in chromogenic culture media. For this study two trials were organized to compare the results obtained using an AI-based application Rumi with the interpretation of: (1) a trained specialist, using MALDI-TOF MS as the gold standard; (2) farm personnel users (FPU). In trial 1, a total of 476 CM milk samples, from 11 farms located in São Paulo (n = 7) and Minas Gerais (n = 4), southeast Brazil, were inoculated in chromogenic culture media plates (Smartcolor 2, OnFarm, Piracicaba, São Paulo, Brazil) by specialists under lab conditions, and digital images were recorded 24 h after incubation at 37 °C. After that, all the 476 digital images were analyzed by the Rumi and by another specialist (who only had access to the digital images) and the diagnostic accuracy indicators sensitivity (Se) and specificity (Sp) were calculated using MALDI-TOF MS microbiological identification of the isolates as the reference. In Trial 2, a total of 208 CM milk samples, from 150 farms from Brazil, were inoculated in chromogenic culture media plates by FPU, and the results of microbiological growth were visually interpreted by FPU under on-farm conditions. After visual interpretation, results were recorded using an OnFarmApp application (herd manage application for mastitis by OnFarm, Piracicaba, São Paulo, Brazil), and the images of the chromogenic culture plates were captured by the OnFarmApp to be evaluated by Rumi and Bayesian Latent Class Models were performed to compare Rumi and the FPU. In Trial 1, Rumi presented high and intermediate accuracy results, with the only exception of the low Enterococcus spp.'s Se. In comparison with the specialist, Rumi performed similarly in Se and Sp for most groups of pathogens, with the only exception of non-aureus staphylococci where Se results were lower. Both Rumi and the specialist achieved Sp results > 0.96. In Trial 2, Rumi had similar results as the FPU in the Bayesian Latent Class Model analysis. In conclusion, the use of the AI-based automated plate reading mobile application can be an alternative for visual interpretation of OFC results, simplifying the procedures for selective treatment decisions for CM based on OFC.

Association between Mastitis Occurrence in Dairy Cows and Bedding Characteristics of Compost-Bedded Pack Barns.

Compost-bedded pack barns (CB) are receiving increasing attention as a housing system that can potentially improve the welfare of dairy cows. This study characterized the frequency and profile of pathogens isolated from clinical (CM) and subclinical (SCM) mastitis in dairy cows housed in CB. It evaluated the association between mastitis occurrence and bedding characteristics in CB systems. Over six months, seven dairy herds were visited monthly for milk and bedding sample collections. Milk samples from mastitis cases were submitted to microbiological identification by matrix-assisted laser desorption ionization-time of flight (MALDI-TOF MS). Bedding samples were submitted to physical-chemical (pH, organic matter, moisture, and carbon to nitrogen ratio) and microbiological counting (total bacterial counts, coliforms, streptococci, and staphylococci) analyses. Regression analysis was used to determine the association between mastitis occurrence and CB characteristics. Our results showed that Escherichia coli and environmental streptococci were the most frequently isolated pathogens from CM cases, while Staphylococcus chromogenes and contagious pathogens (Staphylococcus aureus and Streptococcus agalactiae) were the most commonly isolated from SCM cases. Bedding moisture content was positively associated with the incidence of CM. The bedding carbon to nitrogen ratio was negatively associated with the incidence of SCM, and the bedding total bacteria counts tended to be associated with the incidence of SCM. Bedding counts of coliforms positively associated with the prevalence of SCM. Our results can support decision-makers in the dairy industry seeking strategies for bedding management and mastitis control.

Antimicrobial activities of polyhexamethylene biguanide against biofilm-producing Prototheca bovis causing bovine mastitis.

Prototheca spp. is a frequent cause of bovine mastitis and is highly resistant to commonly used disinfectants. This study aimed to: (1) evaluate the antimicrobial activity of polyhexamethylene biguanide (PHMB) against mastitis-causing Prototheca spp., and (2) evaluate the biofilm production ability of Prototheca spp. A total of 85 Prototheca bovis and 2 Prototheca blaschkeae isolates from bovine mastitis cases were submitted to biofilm production assays and antimicrobial susceptibility tests against PHMB and disinfectants commonly used in dairy herds (chlorhexidine digluconate, povidone-iodine, sodium dichloroisocyanurate, and sodium hypochlorite). The minimal inhibitory concentration (MIC) and minimal algicidal concentration (MAC) were determined by microdilution assays. We observed that PHMB (MIC90: ≥2 µg/mL and MAC90: ≥4 µg/mL) and chlorhexidine gluconate (MIC90 and MAC90: ≥2 µg/mL) presented the highest antimicrobial activity against P. bovis isolates, followed by sodium dichloroisocyanurate (MIC90 and MAC90: ≥1,400 µg/mL), sodium hypochlorite (MIC90 and MAC90: ≥2,800 µg/mL), and povidone-iodine (MIC90 and MAC90: ≥3,200 µg/mL). Concerning P. blaschkeae isolates, PHMB (MIC and MAC ≥1 µg/mL) and chlorhexidine gluconate (MIC and MAC ≥1 µg/mL) were the disinfectants that presented the lowest concentration values required to inhibit the isolates. Regarding biofilms formation, 63.5% (n = 54/85) of the P. bovis isolates were classified as strong, 28.3% (n = 24/85) moderate, and 8.2% (n = 7/85) weak biofilm producers. In contrast, the P. blaschkeae isolates were classified as weak and moderate biofilm producers. These findings suggest that PHMB has the potential to be used for teat and milking-equipment disinfection for the prevention of mastitis-causing Prototheca spp. in dairy herds.

Evaluation of Chromogenic Culture Media for Rapid Identification of Gram-Positive Bacteria Causing Mastitis.

The present study aimed to evaluate the diagnostic performance specificity (Sp), sensitivity (Se), positive predictive value (PPV), negative predictive value (NPV), and accuracy (Acc) of two chromogenic culture media for rapid identification of Gram-positive bacteria causing subclinical mastitis (SCM) in dairy cows. For this, the performance of chromogenic culture media Gram-positive (GP) and Staphylococcus (Staph) (CHROMagar ™, Paris-France) was evaluated in milk samples collected from: (1) lactating cows with SCM (n = 504), and (2) cows in the post-partum period (PP) (7 ± 3 days post-partum; n = 536). Rapid identification of Gram-positive bacteria in chromogenic media was performed by visual inspection of colony colors after 24 h of incubation at 37°C. Bacterial identification by MALDI-TOF mass spectrometry was considered the reference methodology for calculating: Acc, Se, Sp, PPV, NPV, and Cohen's Kappa coefficient of agreement (k). The chromogenic media GP showed high Acc for Strep. agalactiae/dysgalactiae identification in both samples of SCM (Se: 89.1%; Sp: 96.3% and Acc: 95.6%) and of cows in PP (Se: 100%; Sp: 99.0% and Acc: 99.1%). Similar results were observed for Strep. uberis/Enterococcus spp. identification (Se: 90.5%; Sp: 92.5% and Acc: 92.3%) in SCM samples and Se: 100%; Sp: 99.6% and Acc: 99.6% in samples of PP cows using the GP media. However, the GP chromogenic media showed low Se (25.0% in SCM samples and 50.0% in samples of cows in PP) for Staph. aureus identification, despite Sp and Acc were high (Sp: 98.3% and Acc: 95.4% in SCM and Sp samples: 99.4% and Acc: 98.9% in PP cow samples). Staph culture media showed high Acc for Staph. aureus identification (Se: 80.0%; Sp: 98.8% and Acc: 98.0% in SCM samples and Se: 66.7%; Sp: 100% and Acc: 99.6% in PP cow samples), although the low prevalence of Staph. epidermidis and Staph. saprophyticus limit inferences about the performance of identifying these pathogens in Staph media. In conclusion, despite the limitation of the GP media for identification of Staph. aureus, GP, and Staph chromogenic media obtained satisfactory diagnostic performance results for the rapid identification of the main Gram-positive pathogens associated with SCM.