Whole-herd risk factors associated with wean-to-finish mortality under the conditions of a Midwestern USA swine production system

Development of a pig wean-quality score using machine-learning algorithms to characterize and classify groups with high mortality risk under field conditions

Mortality during the post-weaning phase is a critical indicator of swine production system performance, influenced by a complex interaction of multiple factors of the epidemiological triad. This study leveraged retrospective data from 1723 groups of pigs marketed within a US swine production system to develop a Wean-Quality Score (WQS) using machine learning techniques. The study evaluated three machine learning models, Random Forest, Support Vector Machine, and Gradient Boosting Machine, to classify groups having high or low 60-day mortality, where high mortality groups represented 25 % of the groups among the study population with the highest mortality values (n=431; 60-day mortality=9.98 %), and the remaining 75 % of the groups were of low mortality (n=1292; 60-day mortality=2.75 %). The best-performing model, Random Forest (RF), outperformed the other ML models in terms of accuracy (0.90), sensitivity (0.84), and specificity (0.92) metrics, and was then selected for further analysis, which consisted of creating the WQS and ranking the most important factors for classifying groups as high or low mortality. The most important factors ranked through the RF model to classify groups with high mortality were pre-weaning mortality, weaning age, average parity of litters in sow farms, and PRRS status. Additionally, stocking conditions such as stocking density and time to fill the barn were important predictors of high mortality. The WQS was developed and correlated (r = 0.74) with the actual 60-day mortality of the groups, offering a valuable tool for assessing post-weaning survivability in swine production systems before weaning. This study highlights the potential of machine learning and comprehensive data utilization to improve the assessment and management of weaned pig quality in commercial swine production, which producers can utilize to identify and intervene in groups, according to the WQS.

Risk factors associated with piglet pre-weaning mortality in a Midwestern U.S. swine production system from 2020 to 2022

Piglet pre-weaning mortality (PWM) is a significant issue in the U.S. swine industry, causing economic losses and raising sustainability and animal welfare concerns. This study conducted a multivariable analysis to identify factors associated with PWM in a Midwestern U.S. swine production system. Weekly data from 47 sow farms (7207 weaning weeks) were captured from January 2020 to December 2022. Initially, 29 variables regarding farm infrastructure, productivity parameters, health status, and interventions were selected for univariate analysis to assess their association with PWM. The initial multivariable analysis included the variables with P < 0.20 in the univariate analyses. A backward stepwise model selection was conducted by excluding variables with P > 0.05, and the final multivariable model consisted of 19 significant risk factors and 6 interaction terms. The overall average PWM for the study population was 14.02 %. Yearly variations in PWM were observed, with the highest recorded in 2020 (16.61 %) and the lowest in 2021 (15.78 %). Cohorts with a pond water source, lower farrowing rate (71.9 %), higher farrowing parity (5.1), shorter gestation length (116.2 days), and using oxytocin during farrowing had increased PWM. The higher productivity parameters such as mummies rate, stillborn rate, and average total born, the higher the PWM was. Additionally, health status and intervention-related factors were associated with PWM, where higher PWM rates were observed in herds facing porcine reproductive and respiratory syndrome virus (PRRSV) outbreaks, porcine epidemic diarrhea virus (PEDV) positive, the weeks before and during feed medication, and weeks without using Rotavirus vaccine or Rotavirus feedback. Altogether, these results corroborate that PWM is a multifactorial problem, and a better understanding of the risk factors is essential in developing strategies to improve survival rates. Therefore, this study identified the major risk factors associated with PWM for groups of pigs raised under field conditions, and the results underscore the significance of data analysis in comprehending the unique challenges and opportunities inherent to each system.

Assessment of changes in antibiotic use in grow-finish pigs after the introduction of PRRSV in a naïve farrow-to-finish system

Responsible antibiotic usage (ABU) is crucial for both animal and human health and requires constant improvement of antimicrobial stewardship (AMS). The presence of porcine reproductive and respiratory syndrome virus (PRRSV), a viral pathogen with immunosuppressive effects on swine, can intensify bacterial co-infections, alter antibiotic pharmacokinetics, and potentially lead to increased ABU. This study aimed to measure ABU changes in the grow-finish population associated with PRRSV infection and describe the antibiotic classes employed to manage clinical signs from a farrow-to-finish genetic multiplier system. Three PRRSV statuses (naïve, positive epidemic, and positive endemic) were established to classify the lots based on PRRSV circulation, with a total of 135,063 animals evaluated. The number of pig treatments per animal days at risk (PTDR) was calculated by administration route to quantify ABU across PRRSV status using negative binomial regression and non-parametric tests (P-value < 0.05). Moreover, to improve ABU comparability in the international scenario, the milligrams per population correction unit (mg/PCU) was calculated according to the European Medicines Agency guidelines. In the nursery phase, there was a statistically significant difference between PRRSV statuses for the overall PTDR (injectable and water routes of administration), with an ABU increase of 3.79 and 2.51 times the naïve PTDR for positive epidemic and endemic status, respectively. For the finishing phase, there was a statistically significant difference between PRRSV statuses in the injectable PTDR, with an ABU increase of 2.74 and 2.28 times the naïve PTDR level for positive epidemic and endemic statuses, respectively. In the nursery phase, the mean mg/PCU was 22.27 mg/PCU for naïve, 86.71 for positive epidemic, and 33.37 for positive endemic statuses; in the finishing phase, 81.31, 76.55, and 67.09 mg/PCU, respectively. The most frequently injected antibiotic in the nursery phase was ampicillin, with 49 % of total injections, followed by lincomycin (31 %) and enrofloxacin (20 %), and in the finishing phase, 72 % of injections were lincomycin, followed by enrofloxacin (28 %). The results highlight that the PRRSV outbreak in the source was associated with a grow-finish ABU increase, revealing the importance of preventing PRRSV infection to potentially decrease ABU and improve AMS within swine production systems.

Effect of pooled tracheal sample testing on the probability of Mycoplasma hyopneumoniae detection

Tracheal pooling for Mycoplasma hyopneumoniae (M. hyopneumoniae) DNA detection allows for decreased diagnostic cost, one of the main constraints in surveillance programs. The objectives of this study were to estimate the sensitivity of pooled-sample testing for the detection of M. hyopneumoniae in tracheal samples and to develop probability of M. hyopneumoniae detection estimates for tracheal samples pooled by 3, 5, and 10. A total of 48 M. hyopneumoniae PCR-positive field samples were pooled 3-, 5-, and 10-times using field M. hyopneumoniae DNA-negative samples and tested in triplicate. The sensitivity was estimated at 0.96 (95% credible interval [Cred. Int.]: 0.93, 0.98) for pools of 3, 0.95 (95% Cred. Int: 0.92, 0.98) for pools of 5, and 0.93 (95% Cred. Int.: 0.89, 0.96) for pools of 10. All pool sizes resulted in PCR-positive if the individual tracheal sample Ct value was < 33. Additionally, there was no significant decrease in the probability of detecting at least one M. hyopneumoniae-infected pig given any pool size (3, 5, or 10) of tracheal swabs. Furthermore, this manuscript applies the probability of detection estimates to various real-life diagnostic testing scenarios. Combining increased total animals sampled with pooling can be a cost-effective tool to maximize the performance of M. hyopneumoniae surveillance programs.

Evaluation of Truck Cab Decontamination Procedures following Inoculation with Porcine Epidemic Diarrhea Virus and Porcine Reproductive and Respiratory Syndrome Virus

This experiment aimed to evaluate commercially available disinfectants and their application methods against porcine epidemic diarrhea virus (PEDV) and porcine reproductive and respiratory syndrome virus (PRRSV) on truck cab surfaces. Plastic, fabric, and rubber surfaces inoculated with PEDV or PRRSV were placed in a full-scale truck cab and then treated with one of eight randomly assigned disinfectant treatments. After application, surfaces were environmentally sampled with cotton gauze and tested for PEDV and PRRSV using qPCR duplex analysis. There was a disinfectant × surface interaction (p < 0.0001), indicating a detectable amount of PEDV or PRRSV RNA was impacted by disinfectant treatment and surface material. For rubber surfaces, 10% bleach application had lower detectable amounts of RNA compared to all other treatments (p < 0.05) except Intervention via misting fumigation, which was intermediate. In both fabric and plastic surfaces, there was no evidence (p > 0.05) of a difference in detectable RNA between disinfectant treatments. For disinfectant treatments, fabric surfaces with no chemical treatment had less detectable viral RNA compared to the corresponding plastic and rubber (p < 0.05). Intervention applied via pump sprayer to fabric surfaces had less detectable viral RNA than plastic (p < 0.05). Furthermore, 10% bleach applied via pump sprayer to fabric and rubber surfaces had less detectable viral RNA than plastic (p < 0.05). Also, a 10 h downtime, with no chemical application or gaseous fumigation for 10 h, applied to fabric surfaces had less detectable viral RNA than other surfaces (p < 0.05). Sixteen treatments were evaluated via swine bioassay, but all samples failed to produce infectivity. In summary, commercially available disinfectants successfully reduced detectable viral RNA on surfaces but did not eliminate viral genetic material, highlighting the importance of bioexclusion of pathogens of interest.

Utilizing productivity and health breeding-to-market information along with disease diagnostic data to identify pig mortality risk factors in a U.S. swine production system

Aggregated diagnostic data collected over time from swine production systems is an important data source to investigate swine productivity and health, especially when combined with records concerning the pre-weaning and post-weaning phases of production. The combination of multiple data streams collected over the lifetime of the pigs is the essence of the whole-herd epidemiological investigation. This approach is particularly valuable for investigating the multifaceted and ever-changing factors contributing to wean-to-finish (W2F) swine mortality. The objective of this study was to use a retrospective dataset ("master table") containing information on 1,742 groups of pigs marketed over time to identify the major risk factors associated with W2F mortality. The master table was built by combining historical breed-to-market performance and health data with disease diagnostic records (Dx Codes) from marketed groups of growing pigs. After building the master table, univariate analyses were conducted to screen for risk factors to be included in the initial multivariable model. After a stepwise backward model selection approach, 5 variables and 2 interactions remained in the final model. Notably, the diagnosis variable significantly associated with W2F mortality was porcine reproductive and respiratory syndrome virus (PRRSV). Closeouts with clinical signs suggestive of Salmonella spp. or Escherichia coli infection were also associated with higher W2F mortality. Source sow farm factors that remained significantly associated with W2F mortality were the sow farm PRRS status, average weaning age, and the average pre-weaning mortality. After testing for the possible interactions in the final model, two interactions were significantly associated with wean-to-finish pig mortality: (1) sow farm PRRS status and a laboratory diagnosis of PRRSV and (2) average weaning age and a laboratory diagnosis of PRRS. Closeouts originating from PRRS epidemic or PRRS negative sow farms, when diagnosed with PRRS in the growing phase, had the highest W2F mortality rates. Likewise, PRRS diagnosis in the growing phase was an important factor in mortality, regardless of the average weaning age of the closeouts. Overall, this study demonstrated the utility of a whole-herd approach when analyzing diagnostic information along with breeding-to-market productivity and health information, to measure the major risk factors associated with W2F mortality in specified time frames and pig populations.

Effects of increasing omega-3 fatty acids on growth performance, immune response, and mortality in nursery pigs

Three experiments evaluated omega-3 fatty acids, provided by O3 trial feed, on nursery pig growth performance, mortality, and response to an LPS immune challenge or natural Porcine reproductive and respiratory virus (PRRSV) outbreak. In experiment 1, 350 pigs (241 × 600, DNA; initially 5.8 kg) were used. Pens of pigs were randomly assigned to one of the five dietary treatments containing increasing omega-3 fatty acids (0%, 1%, 2%, 3%, and 4% O3 trial feed) with 14 replications per treatment. On day 25, two pigs per pen were injected intramuscularly with 20 μg Escherichia coli LPS per kg BW and one pig per pen was injected with saline as a control. Body temperature was taken from all three pigs prior to and 2, 4, 6, and 12 h post-LPS challenge. Serum IL-1β and TNF-α concentrations were determined in LPS-challenged pigs 24 h prior and 4 h post-LPS challenge. There was no interaction between treatment and time for change in body temperature (P > 0.10). Overall, increasing the O3 trial feed did not affect (P > 0.10) ADG, ADFI, G:F, IL-1β, or TNF-α. In experiment 2, 1,056 pigs (PIC TR4 × [Fast LW × PIC L02] initially 7.3 kg) were used. Pens of pigs were randomly assigned to one of the four dietary treatments containing increasing omega-3 fatty acids (0%, 0.75%, 1.5%, and 3% O3 trial feed) with 12 replications per treatment. Oral fluids tested negative on days 7 and 14, but then positive for North American PRRSV virus via PCR on days 21, 28, 35, and 42. Overall, increasing O3 trial feed increased (linear, P < 0.001) ADG, ADFI, and G:F and decreased (linear, P = 0.027) total removals and mortality. In experiment 3, 91,140 pigs (DNA 600 × PIC 1050; initially 5.1 kg), originating from PRRSV-positive sow farms, were used across eight nursery sites. Each site contained five barns with two rooms per barn and ~1,100 pigs per room. Rooms of pigs were blocked by nursery site and allocated within sow source to one of the two dietary treatments (control or 3% O3 trial feed) with 40 replications per treatment. Oral fluids from 61 of the 80 rooms tested positive for North American PRRSV virus 1 wk postweaning and 78 of the 80 rooms tested positive 3 wk after weaning. Overall, O3 trial feed did not affect ADG, ADFI, or G:F but increased (P < 0.001) total removals and mortalities. In summary, increasing omega-3 fatty acids, sourced by O3 trial feed, did not improve growth performance or immune response in healthy pigs given an LPS challenge. However, it appears that if omega-3 fatty acids are fed prior to a natural PRRSV break (as in experiment 2), growth performance may be improved, and mortality reduced.

Field Implementation of Forecasting Models for Predicting Nursery Mortality in a Midwestern US Swine Production System

The performance of five forecasting models was investigated for predicting nursery mortality using the master table built for 3242 groups of pigs (~13 million animals) and 42 variables, which concerned the pre-weaning phase of production and conditions at placement in growing sites. After training and testing each model's performance through cross-validation, the model with the best overall prediction results was the Support Vector Machine model in terms of Root Mean Squared Error (RMSE = 0.406), Mean Absolute Error (MAE = 0.284), and Coefficient of Determination (R2 = 0.731). Subsequently, the forecasting performance of the SVM model was tested on a new dataset containing 72 new groups, simulating ongoing and near real-time forecasting analysis. Despite a decrease in R2 values on the new dataset (R2 = 0.554), the model demonstrated high accuracy (77.78%) for predicting groups with high (>5%) or low (<5%) nursery mortality. This study demonstrated the capability of forecasting models to predict the nursery mortality of commercial groups of pigs using pre-weaning information and stocking condition variables collected post-placement in nursery sites.

Evaluation of Precision Livestock Technology and Human Scoring of Nursery Pigs in a Controlled Immune Challenge Experiment

The objectives were to determine the sensitivity, specificity, and cutoff values of a visual-based precision livestock technology (NUtrack), and determine the sensitivity and specificity of sickness score data collected with the live observation by trained human observers. At weaning, pigs (n = 192; gilts and barrows) were randomly assigned to one of twelve pens (16/pen) and treatments were randomly assigned to pens. Sham-pen pigs all received subcutaneous saline (3 mL). For LPS-pen pigs, all pigs received subcutaneous lipopolysaccharide (LPS; 300 μg/kg BW; E. coli O111:B4; in 3 mL of saline). For the last treatment, eight pigs were randomly assigned to receive LPS, and the other eight were sham (same methods as above; half-and-half pens). Human data from the day of the challenge presented high true positive and low false positive rates (88.5% sensitivity; 85.4% specificity; 0.871 Area Under Curve, AUC), however, these values declined when half-and-half pigs were scored (75% sensitivity; 65.5% specificity; 0.703 AUC). Precision technology measures had excellent AUC, sensitivity, and specificity for the first 72 h after treatment and AUC values were >0.970, regardless of pen treatment. These results indicate that precision technology has a greater potential for identifying pigs during a natural infectious disease event than trained professionals using timepoint sampling.

Porcine respiratory disease complex: Dynamics of polymicrobial infections and management strategies after the introduction of the African swine fever

A few decades ago, porcine respiratory disease complex (PRDC) exerted a major economic impact on the global swine industry, particularly due to the adoption of intensive farming by the latter during the 1980's. Since then, the emerging of porcine reproductive and respiratory syndrome virus (PRRSV) and of porcine circovirus type 2 (PCV2) as major immunosuppressive viruses led to an interaction with other endemic pathogens (e.g., Mycoplasma hyopneumoniae, Actinobacillus pleuropneumoniae, Streptococcus suis, etc.) in swine farms, thereby exacerbating the endemic clinical diseases. We herein, review and discuss various dynamic polymicrobial infections among selected swine pathogens. Traditional biosecurity management strategies through multisite production, parity segregation, batch production, the adoption of all-in all-out production systems, specific vaccination and medication protocols for the prevention and control (or even eradication) of swine diseases are also recommended. After the introduction of the African swine fever (ASF), particularly in Asian countries, new normal management strategies minimizing pig contact by employing automatic feeding systems, artificial intelligence, and robotic farming and reducing the numbers of vaccines are suggested. Re-emergence of existing swine pathogens such as PRRSV or PCV2, or elimination of some pathogens may occur after the ASF-induced depopulation. ASF-associated repopulating strategies are, therefore, essential for the establishment of food security. The "repopulate swine farm" policy and the strict biosecurity management (without the use of ASF vaccines) are, herein, discussed for the sustainable management of small-to-medium pig farms, as these happen to be the most potential sources of an ASF re-occurrence. Finally, the ASF disruption has caused the swine industry to rapidly transform itself. Artificial intelligence and smart farming have gained tremendous attention as promising tools capable of resolving challenges in intensive swine farming and enhancing the farms' productivity and efficiency without compromising the strict biosecurity required during the ongoing ASF era.