Statistical and machine learning approaches to describe factors affecting preweaning mortality of piglets

High preweaning mortality (PWM) rates for piglets are a significant concern for the worldwide pork industries, causing economic loss and well-being issues. This study focused on identifying the factors affecting PWM, overlays, and predicting PWM using historical production data with statistical and machine learning models. Data were collected from 1,982 litters from the U.S. Meat Animal Research Center, Nebraska, over the years 2016 to 2021. Sows were housed in a farrowing building with three rooms, each with 20 farrowing crates, and taken care of by well-trained animal caretakers. A generalized linear model was used to analyze the various sow, litter, environment, and piglet parameters on PWM. Then, different models (beta-regression and machine learning model: a random forest [RF]) were evaluated. Finally, the RF model was used to predict PWM and overlays for all listed contributing factors. On average, the mean birth weight was 1.44 kg, and the mean mortality was 16.1% where 5.55% was for stillbirths and 6.20% was contributed by overlays. No significant effect was found for seasonal and location variations on PWM. Significant differences were observed in the effects of litter lines on PWM (P < 0.05). Landrace-sired litters had a PWM of 16.26% (±0.13), whereas Yorkshire-sired litters had 15.91% (±0.13). PWM increased with higher parity orders (P < 0.05) due to larger litter sizes. The RF model provided the best fit for PWM prediction with a root mean squared errors of 2.28 and a correlation coefficient (r) of 0.89 between observed and predicted values. Features' importance from the RF model indicated that, PWM increased with the increase of litter size (mean decrease accuracy (MDA) = 93.17), decrease in mean birth weight (MDA = 22.72), increase in health diagnosis (MDA = 15.34), longer gestation length (MDA = 11.77), and at older parity (MDA = 10.86). However, in this study, the location of the farrowing crate, seasonal differences, and litter line turned out to be the least important predictors for PWM. For overlays, parity order was the highest importance predictor (MDA = 7.68) followed by litter size and mean birth weight. Considering the challenges to reducing the PWM in the larger litters produced in modern swine industry and the limited studies exploring multiple major contributing factors, this study provides valuable insights for breeding and production management, as well as further investigations on postural transitions and behavior analysis of sows during the lactation period.

Effects of Caffeine and Glucose Supplementation at Birth on Piglet Pre-Weaning Growth, Thermoregulation, and Survival

Piglet pre-weaning mortality of approximately 15% represents a major economic and welfare concern to the pork industry. Supplementing neonatal piglets with glucose and/or caffeine has the potential to counteract hypoxic stress experienced during parturition and provide an energy substrate, which may improve survival to weaning. This study investigated the effects of caffeine and glucose supplementation at birth, in combination or separately, on piglet growth, thermoregulatory ability, and pre-weaning survival. At birth, 398 piglets were assigned to one of four oral treatments: saline, glucose (300 mg), caffeine (30 mg), or caffeine and glucose combined (30 mg caffeine and 300 mg glucose), dissolved in 6 mL saline. Piglets were tagged at birth, and time taken to reach the udder was recorded. Rectal temperatures were recorded at 4 h and 24 h post-partum, and body weights recorded at birth and 1, 3, and 18 days of age. Colostrum intake was estimated using birth and day 1 weights, and all pre-weaning mortalities were recorded. Treatments did not affect rectal temperature, colostrum intake, or pre-weaning mortality (p > 0.05). Low birth weight piglets (<0.9 kg) treated with caffeine and glucose had increased growth between 1 and 3 days of age (p < 0.05) compared to low birth weight piglets of other treatment groups. Caffeine supplementation alone reduced overall pre-weaning growth in low birth weight piglets compared to all other treatments (p = 0.05). Oral caffeine and glucose had no significant effect on piglet performance except in low birthweight piglets, where it improved growth in the first 3 days of life. Caffeine and glucose supplementation in combination may be beneficial for low birth weight piglets.

Welfare of pigs on farm

This scientific opinion focuses on the welfare of pigs on farm, and is based on literature and expert opinion. All pig categories were assessed: gilts and dry sows, farrowing and lactating sows, suckling piglets, weaners, rearing pigs and boars. The most relevant husbandry systems used in Europe are described. For each system, highly relevant welfare consequences were identified, as well as related animal-based measures (ABMs), and hazards leading to the welfare consequences. Moreover, measures to prevent or correct the hazards and/or mitigate the welfare consequences are recommended. Recommendations are also provided on quantitative or qualitative criteria to answer specific questions on the welfare of pigs related to tail biting and related to the European Citizen's Initiative 'End the Cage Age'. For example, the AHAW Panel recommends how to mitigate group stress when dry sows and gilts are grouped immediately after weaning or in early pregnancy. Results of a comparative qualitative assessment suggested that long-stemmed or long-cut straw, hay or haylage is the most suitable material for nest-building. A period of time will be needed for staff and animals to adapt to housing lactating sows and their piglets in farrowing pens (as opposed to crates) before achieving stable welfare outcomes. The panel recommends a minimum available space to the lactating sow to ensure piglet welfare (measured by live-born piglet mortality). Among the main risk factors for tail biting are space allowance, types of flooring, air quality, health status and diet composition, while weaning age was not associated directly with tail biting in later life. The relationship between the availability of space and growth rate, lying behaviour and tail biting in rearing pigs is quantified and presented. Finally, the panel suggests a set of ABMs to use at slaughter for monitoring on-farm welfare of cull sows and rearing pigs.

Effect of alternative farrowing pens with temporary crating on the performance of lactating sows and their litters

This study was performed to development the alternative farrowing pen (AFP) and to investigate performance and behavior of lactating sows and their litter. A total of 64 multiparous sows were randomly divided into two groups and were allocated to farrowing crates (FCs) and AFPs. The AFPs contained a crate and support bars that could be folded to provide the sows with extra space on day 5 postpartum. Behavior was recorded by charge-coupled device cameras and digital video recorders, and the data were scanned every 2 min to obtain an instantaneous behavioral sample. Farrowing systems did not affect feed intake, back-fat thickness, litter size and piglet weight at birth and weaning (p > 0.05). In addition, there were no differences in the number of crushed piglets between the two farrowing systems (p > 0.05). However, the weaning-to-estrus interval was shorter in the sows of the AFPs than in thous of the FCs (p < 0.05). The sows spent most of their time lying down during the lactating period, at about 80% lateral recumbency and 10%–15% ventral recumbency. The only significant differences were in the feeding and drinking behavior between sows in the two farrowing systems (p < 0.05). The FC sows displayed more feeding and drinking behavior than the AFP sows, especially in the late lactating period (p < 0.05). Piglets in the FCs tended to spend more time walking than piglets in the AFPs (p < 0.05), whereas there were no differences in suckling and lying behavior between piglets in the two farrowing systems (p > 0.05). It is concluded that the AFPs with temporary crating until day 4 postpartum did not negatively affect performance and crushed piglet compared with the FCs. It also may improve animal welfare by allowing sows to move and turn around during the lactating period. Further research is needed to find suitable housing designs to enhance productivity and animal welfare.

Review of Temporary Crating of Farrowing and Lactating Sows

Temporary crating (TC) provides lactating sows with the opportunity to move more freely after crate opening a few days after parturition. The aim of this paper was to evaluate whether TC gives overall welfare improvement when compared to permanent crating or free farrowing. This review shows that when pens with TC allow the sows to turn during the majority of time in the farrowing unit, it is the pen design and period of confinement in a crate within it that influence the extent to which different functional and motivated behaviors can be fulfilled. This review also indicates that there are at least short-term benefits to sows when confinement is reduced, as shown by reported increases in motivated behaviors such as exploration and interactions with piglets when not permanently crated. It remains unclear whether there are any longer-term beneficial effects (until or beyond weaning) due to the paucity of studies. Furthermore, it is uncertain whether the observed short-term benefits translate to other welfare indicators. Research findings indicate no reduction in the frequency of stereotypies or body lesions and do not provide a clear answer regarding sow stress response when released from confinement. Compared to free farrowing, TC appears beneficial for reducing piglet mortality. The impact of the time of onset of TC on the farrowing process and piglet mortality have been inconsistent. While confinement before farrowing prevents nest building behavior, consequences of this for sow physiology have been ambiguous. Confining the sow briefly after farrowing may be the best compromise, allowing the sow to perform motivated nest-building behavior, but the risks of crushing during the unconfined farrowing period may increase. Subsequent crate reopening seems to increase piglet mortality but only if done earlier than 3–5 days after farrowing. The review also provides methodological considerations, a proposal for consistent and accurate terminology when describing systems and highlights gaps of knowledge. In conclusion, TC is a step forward to better pig welfare compared to the farrowing crate, as it allows some freedom of movement for sows without impairing piglet welfare. However, more comprehensive research is needed to draw sound conclusions as to whether TC is a viable transition from permanent crating to free farrowing.

Short confinement of sows after farrowing, but not pen type affects live-born piglet mortality

Over the last decades, permanent crating of farrowing and lactating sows has led to serious public concerns with regard to sow welfare. As one alternative, it has been suggested to restrict crating to the period when suckling piglets are at the highest risk to die. Therefore, the aim of this study was to investigate live-born piglet mortality with regard to different confinement periods (CFP) as well as farrowing pen types. On three research farms (A, B and C), four confinement periods were compared: In CFP 0 (control), sows were not confined at all, sows in CFP 3 were crated after the end of farrowing for three days. In CFP 4, sows were confined one day before the due date of farrowing until three days after parturition and sows in CFP 6 were crated one day before expected farrowing until five days after parturition. Furthermore, five different pen types designed for temporary crating (PT; 5.5-7.3 m²) were compared. In total, production data from 638 litters were analysed. For each piglet found dead (n = 1 580), the cause of death was determined by the farm personnel and verified by necropsy (all three farms) and additional video analysis (farms A and B only). Data were analysed using logistic mixed models with CFP 0 and pen type Fluegel as reference categories (CFP 0 was control and this pen type was present on all three farms and the largest number of litters was born in this pen type). Live-born piglet mortality was lower in temporarily crated sows than in sows without confinement (CFP 0; P < 0.015). Pairwise posthoc tests did not reveal differences between CFP 3, CFP 4 and CFP 6 (odds ratios 0.75, 0.59 and 0.69), nor between pen types. Additional factors associated with increasing live-born piglet mortality were larger litter size, higher sow parity as well as the administration of hormones around farrowing. Factors influencing mortality due to crushing were similar to those for total live-born mortality with the exception of CFP 3 not differing significantly from CFP 0. It can be concluded, that confinement of the sow for three days after farrowing is an effective measure to reduce live-born piglet mortality in the pen types tested. An extension of the confinement period to five days after parturition does not result in a further reduction of live-born mortality rate.

The effect of hessian and straw as nesting materials on sow behaviour and piglet survival and growth to weaning

Sows are strongly driven to build a nest prior to farrowing, and the performance of this behaviour is linked to the environment in which the animal is housed. The aim of this study was to investigate the impact of two nest-building materials, hessian and straw, on peri-parturient sow behaviour, plasma cortisol concentration and piglet survival and performance in farrowing crates. In the first experiment, sows (parity 1.7 ± 0.1) were allocated to four treatments: (n = 15), straw provided in the lead up to farrowing in an open farrowing pen, with the pen closed after farrowing (STRAW OPEN); (n = 14), straw provided in the lead up to farrowing in a closed farrowing pen (STRAW CLOSED); (n = 15), a closed farrowing pen with hessian sacks provided in the lead up to farrowing (HESSIAN) and; (n = 13), a closed farrowing pen with no nesting materials provided (CONTROL). A second experiment was performed on a separate farm to assess the effect of the same four treatments were applied to sows (parity 2.9 ± 0.1): SRAW OPEN (n = 68), STRAW CLOSED (n = 64), HESSIAN (n = 66) and CONTROL (n = 66), at a commercial level. The first experiment revealed that providing conventionally housed sows with straw or hessian in the lead up to parturition stimulated sows to perform nest-building behaviours similar to sows housed in an open pen with access to straw (nosing events; 16 ± 11 (CONTROL); 169 ± 36 (HESSIAN); 118 ± 29 (STRAW CLOSED); 199 ± 53 (STRAW OPEN); P < 0.05). Additionally, crated sows provided with straw had reduced cortisol levels immediately after farrowing compared to all other treatments (21.9 ± 6.1 ng/ml vs CONTROL; 49.3 ± 8.6 ng/ml; P < 0.01). Piglets born to STRAW CLOSED sows displayed the highest colostrum intake levels (404.8 ± 22.7 g vs CONTROL 361.9 ± 21.9 g; P < 0.01). The second experiment demonstrated a reduced incidence of piglet mortality both prior to fostering (0.7 ± 0.2; P = 0.001) and after fostering (0.7 ± 0.2; P = 0.001) in litters born to sows which were housed in conventional farrowing crates and provided with straw compared to CONTROL (prior to fostering 1.3 ± 0.2, and postfostering 1.1 ± 0.2). In conclusion, straw and hessian sacks are a suitable substrate for stimulating sows to exhibit nest-building behaviour under crated conditions. However, only the provision of straw in the crate environment improved piglet survival and positively affected sow welfare.

Effects of Farrowing Stall Layout and Number of Heat Lamps on Sow and Piglet Production Performance

Simple Summary

In the commercial swine industry, farrowing stalls are commonly used as a strategy to reduce piglet pre-weaning mortalities caused by sow over-lay. Farrowing stall dimensions have generally remained the same over the past 50 years in the United States, even though the sizes of both the sows and litters have increased considerably. This extensive field study investigated if sow and piglet productivity would be affected when housed in stalls of traditional layout, additional area for the piglets, or additional area for the sow. All three layouts were also tested with use of one or two supplementary heat lamps in the creep area. Results show that stall layout and number of heat lamps had no statistical impact on production outcomes. However, seasonal differences, sow parity, and number of litter mates did have significant effects. Providing larger stalls or an additional heat lamp costs more for the producer but did not yield production improvements.

Abstract

Most farrowing facilities in the United States use stalls and heat lamps to improve sow and piglet productivity. This study investigated these factors by comparing production outcomes for three different farrowing stall layouts (traditional, expanded creep area, expanded sow area) and use of one or two heat lamps. Data were collected on 427 sows and their litters over one year. Results showed no statistical differences due to experimental treatment for any of the production metrics recorded, excluding percent stillborn. Parity one sows had fewer piglets born alive (p < 0.001), lower percent mortality (p = 0.001) and over-lay (p = 0.003), and a greater number of piglets weaned (p < 0.001) with lower average daily weight gain (ADG) (p < 0.001) and more uniform litters (p = 0.001) as compared to higher parity sows. Farrowing turn, associated with group/seasonal changes, had a significant impact on most of the production metrics measured. Number of piglets born influenced the percent stillborn (p < 0.001). Adjusted litter size had a significant impact on percent mortality (p < 0.001), percent over-lay (p < 0.001), and number of piglets weaned (p < 0.001). As the number of piglets weaned per litter increased, both piglet ADG and litter uniformity decreased (p < 0.001). This information can be used to guide producers in farrowing facility design.

Impact of Non-Confinement Accommodation on Farrowing Performance: A Systematic Review and Meta-Analysis of Farrowing Crates Versus Pens

Simple Summary

The aim of this project was to review previously published research with a focus on the effects of farrowing accommodation on piglet performance. The specific design features were analysed to determine whether animals in loose housed farrowing pens or crates from loading to weaning contribute to differences in litter performance obtained from different farrowing house accommodation types. This was the first systematic review and meta-analysis conducted towards the farrowing performance of crates and pens. The relative risk of piglet mortality was 14% higher in farrowing pens than farrowing crates, which indicated that non-confinement of sows compromises post-natal piglet survival. Overall, the type of farrowing accommodation did not affect the number of stillborn piglets. However, the rate of stillborn piglets was lower in farrowing pens that were not enriched when compared with farrowing crates, also with no enrichment. There was no effect of housing type on the number of piglets born alive or the number of piglets weaned, although the sample size for the later was much smaller. Producers should anticipate an increase in mortality when piglets are reared by sows that are unconfined in the pen designs that are currently available, which supports the wider belief that crates are successful for reducing pre-weaning piglet mortality.

Abstract

There are conflicting reports regarding the effect of farrowing house accommodation on piglet performance. The aim of this investigation was to use a systematic review and meta-analyses to summarise the results of publications that focused on direct comparisons between full confinement conventional crates and various designs of loose-housed farrowing pens from loading until weaning. Literature searches in Scopus, BIOSIS Previews, Cab Abstracts, and Web of Science identified 6695 articles. Twenty-two publications were retained for the systematic review and individual meta-analyses after screening for inclusion criteria. The random effects meta-analyses were performed on crate versus pen for number of piglets born alive, number of stillborn piglets, pre-weaning mortality, and number of piglets weaned. Additionally, the modifiers of confinement length (no confinement from loading until weaning or partial confinement for shorter periods of time in the early stages post parturition), enrichment (no enrichment or enrichment provided), and pen size (small, medium, or large) were examined. There was a 14% increase in the relative risk of piglet mortality in farrowing pens when they were compared with crates (p = 0.0015). The number of stillborns per litter was not different between the pen and crate. However, when providing enrichment in the pens, there was an increase in stillborns within farrowing crates versus pens (p = 0.009). There was no overall effect on piglets that were born alive or number weaned. As there is no difference between piglets born alive and mortality is significantly higher in farrowing pens, a reduction in the number of piglets weaned was expected but not observed, which was possibly due to the lack of weaning details provided in the publications. This was the first systematic review and meta-analysis conducted on the performance of farrowing accommodation and identified that farrowing pens do compromise post-natal piglet survival. Future efforts should focus on improving sow comfort in the farrowing crate to maximize both piglet and sow welfare.

Sow stress levels and behavior and piglet performances in farrowing crates and farrowing pens with temporary crating

Farrowing pens with temporary crating have been developed as a compromise between conventional farrowing crates and pens to better accommodate the welfare of both sow and piglets during lactation. However, not much is known about the behavioral and physiological consequences of early removal of confinement on the sow and piglets during lactation. The aim of this study was to assess the effects on sow and piglet performance of temporary crating until 3-d postpartum at 2 times points, immediately after confinement removal and 25 d into lactation. Sows were crated from 5-d prepartum either to weaning (permanently crated-PC group; N =14) or to D3 (83.0 ± 1.3 h) postpartum (Temporarily crated - TC group N = 13). Sow postural changes, activity, cortisol and IgA concentrations, and piglet body weight gain and behavior were assessed on D4 and on D25 postpartum, whereas piglet mortality was assessed throughout lactation. Data were analyzed using PROC GLM and PROC GENMOD of SAS. On D4 postfarrowing, TC sows were more active (10.9% vs. 7.1%; SEM: 0.8; P = 0.002), rolled more frequently (21.3% vs. 14.4%; SEM: 1.6; P = 0.008), and had lower IgA concentrations (139.7 vs. 75.2 µg/mL; SEM: 20.3; P = 0.040) than PC sows. No effects of housing were found (P > 0.05) on standing-to-lying movement or cortisol concentrations. No differences for any variables were found (P > 0.05) on D25. Mortality, body weights, and activity levels at the udder or in the pen of pigs born to PC sows did not differ (P > 0.05) from those of piglets born to TC sows on D4 nor on D25. This study indicates that removal of confinement on the 4th-d postpartum may have had small short-term positive effects on sow behavior and stress levels (as measured by IgA), and that it did not impair piglets' behavior and performance during lactation. Therefore, this work suggests that temporary crating limited to the first 3-d postpartum might be a feasible alternative to improve welfare under intensive production conditions.

Key determinants of pig welfare: implications of animal management and housing design on livestock welfare

The present review using the pig as a model has highlighted the importance of the design of the housing system on the welfare of farm animals. It has emphasised the need for research on animal welfare in new and modified housing systems, as well as current but contentious systems, to be attentive to the design contributions of these systems to animal welfare. The review has highlighted areas for future research to safeguard sow and piglet welfare, including the following: effective environmental enrichment for gestating sows in intensive, indoor and non-bedded systems; opportunities to increase foraging and feeding times in feed-restricted gestating sows; design features that allow both access to important resources, such as feed, water and a comfortable lying area, and escape opportunities to reduce aggression and minimise risks to the welfare of group-housed sows; and less confined farrowing and lactation systems. The review also shows that animal welfare problems may be less a function of the type of housing system than of how well it operates. The skills, knowledge and motivation of stockpeople to effectively care for and manage their animals are integral to the standard of welfare experienced by their animals. Attitudes influence not only the manner in which stockpeople handle animals, but also their motivation to care for their animals. Thus, training targeting technical skills and knowledge as well as the attitudes and behaviours of stockpeople should be a primary component of the human resource management practices at a farm. While public concerns and policy debates often focus on intensive housing systems, research indicates that the design and management of both indoor and outdoor housing systems is probably more important for animal welfare than is generally recognised.

Sow housing associated with reproductive performance in breeding herds

Female pigs in breeding herds can be managed through four phases-gilt development, breeding, gestation, and lactation-during which they may be housed in group or individual pens, stalls, or on pasture. In this review, we focus on housing environments that optimize outcomes during gestation and lactation. Appropriate housing is important during early gestation, to protect embryos and to confirm pregnancy, and from mid-to-late gestation, to ensure sufficient nutrition to increase placental and fetal growth. No difference in the number of pigs born alive were reported between group housing and individual stall housing, although more risk factors for reproductive performance are associated with group housing than stall housing including genetics, bedding, floor space allowance, group size, social ranking, and parity. Furthermore, lameness in pregnant pigs is more frequent in group housing than in stall housing. Housing during lactation helps protect piglets from being crushed or from contracting disease, and can foster the transfer of enough colostrum from mother to piglets. Indeed, lactating sows in pen housing tend to have higher pre-weaning mortality and lighter litter weights than those in crated housing.

The behaviour and welfare of sows and piglets in farrowing crates or lactation pens

Temporary confinement during parturition and early postpartum may provide an intermediary step preceding loose housing that offers improvement in sow and piglet welfare. Three experiments were conducted to investigate the implications of replacing farrowing crates (FCs) with an alternative housing system from 3 days postpartum until weaning. In each experiment sows farrowed in FCs and were randomly allocated at day 3 of lactation to either a FC or a pen with increased floor space (lactation pen (LP)) until weaning. In experiment 1, piglet growth and sow and piglet skin injuries were recorded for 32 sows and 128 focal piglets in these litters. Behaviour around nursing and piglet behavioural time budgets were also recorded for 24 of these litters (96 focal piglets for time budgets). In experiment 2, measures of skin injury and behavioural time budgets were conducted on 28 sows and 112 focal piglets. The behavioural response of sows to piglet vocalisation (maternal responsiveness test (MRT)) was also assessed. In experiment 3, piglet mortality from day 3 of lactation until weaning was recorded in 672 litters over 12 months. While housing did not affect piglet weight gain in experiment 1, or piglet skin injuries in experiments 1 or 2, sows in both experiments sustained more injuries in LP than FC (experiment 1, 2.9 v. 1.4; experiment 2, 2.5 v. 0.8 lesions/sow; P0.05). Thus, housing sows and litters in LP from day 3 of lactation minimises piglet mortality while improving maternal behaviour in sows and social behaviour in piglets.