Regression analysis to predict growth performance from dietary net energy in growing-finishing pigs

Modeling energy partition patterns of growing pigs fed diets with different net energy levels based on machine learning

The objectives of this study were to evaluate the energy partition patterns of growing pigs fed diets with different net energy (NE) levels based on machine learning methods, and to develop prediction models for the NE requirement of growing pigs. Twenty-four Duroc × Landrace × Yorkshire crossbred barrows with an initial body weight of 24.90 ± 0.46 kg were randomly assigned to 3 dietary treatments, including the low NE group (2,325 kcal/kg), the medium NE group (2,475 kcal/kg), and the high NE group (2,625 kcal/kg). The total feces and urine produced from each pig during each period were collected, to calculate the NE intake, NE retained as protein (NEp), and NE retained as lipid (NEl). A total of 240 sets of data on the energy partition patterns of each pig were collected, 75% of the data in the dataset was randomly selected as the training dataset, and the remaining 25% was set as the testing dataset. Prediction models for the NE requirement of growing pigs were developed using algorithms including multiple linear regression (MR), artificial neural networks (ANN), k-nearest neighbor (KNN), and random forest (RF), and the prediction performance of these models was compared on the testing dataset. The results showed pigs in the low NE group showed a lower average daily gain, lower average daily feed intake, lower NE intake, but greater feed conversion ratio compared to pigs in the high NE group in most growth stages. In addition, pigs in the 3 treatment groups did not show a significant difference in NEp in all growth stages, while pigs in the medium and high NE groups showed greater NEl compared to pig in the low NE group in growth stages from 25 to 55 kg (P < 0.05). Among the developed prediction models for NE intake, NEp, and NEl, the ANN models demonstrated the most optimal prediction performance with the smallest root mean square error (RMSE) and the largest R2, while the RF models had the worst prediction performance with the largest RMSE and the smallest R2. In conclusion, diets with varied NE concentrations within a certain range did not affect the NEp of growing pigs, and the models developed with the ANN algorithm could accurately achieve the NE requirement prediction in growing pigs.

Effect of added calcium carbonate without and with benzoic acid on weanling pig growth performance, fecal dry matter, and blood Ca and P concentrations

The objective of these studies was to determine the effects of increasing levels of calcium carbonate (CaCO₃) with and without benzoic acid on weanling pig growth performance, fecal dry matter (DM), and blood Ca and P concentrations. In experiment 1, 695 pigs (DNA Line 200 × 400, initially 5.9 ± 0.02 kg) were used in a 28 d study. Pigs were weaned at approximately 21 d of age and randomly assigned to pens and then pens were allotted to one of five dietary treatments. Treatment diets were fed from weaning (day 0) to day 14, with a common diet fed from days 14 to 28. Dietary treatments were formulated to provide 0%, 0.45%, 0.90%, 1.35%, and 1.80% added CaCO₃ at the expense of ground corn. From days 0 to 14 (treatment period), average daily gain (ADG) and G:F decreased (linear, P ≤ 0.01) as CaCO₃ increased. From days 14 to 28 (common period) and for the overall experiment (days 0 to 28), there was no evidence of differences in growth performance between treatments. For fecal DM, there was a trend (quadratic, P = 0.091) where pigs fed with the highest CaCO₃ diets had the greatest fecal DM. Experiment 2 used 360 pigs (DNA Line 200 × 400, initially 6.2 ± 0.03 kg) in a 38 d study. Upon arrival to the nursery facility, pigs were randomly assigned to pens and then pens were allotted to one of six dietary treatments. Dietary treatments were fed in three phases with treatment diets fed from days 0 to 10 and days 10 to 24, and a common phase 3 diet fed from days 24 to 38. Dietary treatments were formulated to provide 0.45%, 0.90%, and 1.35% added CaCO₃ with or without 0.5% benzoic acid (VevoVitall, DSM Nutritional Products, Parsippany, NJ) added at the expense of ground corn. There was no evidence (P > 0.05) for any CaCO₃ by benzoic acid interactions. For the experimental period (days 0 to 24), there was a tendency for benzoic acid to increase ADG (P = 0.056), average daily feed intake (ADFI; P = 0.071), and gain-to-feed ratio (G:F; linear, P = 0.014) as CaCO₃ decreased. During the common period (days 24 to 38), pigs previously fed benzoic acid had increased (P = 0.045) ADG and marginally increased (P = 0.091) ADFI. For the overall study, pigs fed benzoic acid had increased ADG (P = 0.011) and ADFI (P = 0.030), marginally increased G:F (P = 0.096) and final body weight (P = 0.059). Serum Ca decreased (linear, P < 0.001) as CaCO₃ decreased in the diet. These data show that decreasing the CaCO₃ content in the nursery diet immediately after weaning may improve ADG and G:F. Dietary addition of benzoic acid may also provide beneficial effects on ADG and ADFI, regardless of dietary Ca level.

Meta-analysis of energy intake of growing-finishing pigs in China

Data from 655 treatments of 116 studies were used in a meta-analysis to determine the daily digestible energy (DE), metabolizable energy (ME) and net energy (NE) intake of Chinese growing-finishing pigs, and to predict feed efficiency responses to change in dietary DE, ME and NE. Three alternative functions (i.e., polynomial, Bridges and asymptotic function) were employed for fitting daily DE, ME or NE intakes to mean body weight. The results showed that the three models from the current study provided reasonable fit (all R²  > 0.83) for the energy intake data. However, under the same energy system, the polynomial function had the smallest Akaike's information criteria (AIC) and residual standard deviation (RSD), followed by Bridges and asymptotic functions. The three model-generated energy intakes of growing pigs were significantly less than that of the Chinese Feeding Standard of Swine, but similar to that of the National Research Council (2012), while the values of finishing pigs were greater than both standards. Compared with those that predict feed efficiency based on DE or ME, the equation with NE as a predictor had the minimized AIC and RSD. It was also found that feed efficiency increased with increasing dietary energy density (DED), but this response varied with pig body weight, and the lighter pigs were more sensitive to DED than heavier pigs.

Effects of high-protein distillers dried grains on growth performance of nursery pigs

A total of 300 pigs (DNA 400 × 200, Columbus, NE), initially 11.1 kg, were used in a study to evaluate the effects of increasing amounts of high-protein distillers dried grains (HP DDG) on growth performance and to estimate its energy value relative to corn. Pigs were weaned, placed in pens with five pigs each, and fed a common diet for 21 d after weaning. Then, pens were assigned to treatments in a randomized complete block design. There were 5 treatments with 12 replicates per treatment. Treatments consisted of 0, 10, 20, 30, or 40% HP DDG, formulated by changing only the amounts of corn and feed-grade amino acids. Pigs were weighed weekly for 21 d to evaluate average daily gain (ADG), average daily feed intake (ADFI), and gain-to-feed ratio (G:F). Caloric efficiency was obtained by multiplying ADFI by kcal of net energy (NE) per kg of diet and dividing by ADG. The NE values for corn and soybean meal were obtained from NRC (2012), and initial estimates for HP DDG NE were derived from the Noblet et al. (1994) equation. The energy of HP DDG was estimated based on caloric efficiency relative to the diet without HP DDG. Pigs fed diets with increasing HP DDG had a linear decrease (P < 0.01) in ADG, ADFI, and final body weight. There was a tendency for a quadratic response (P = 0.051) in G:F, with the greatest G:F observed for pigs fed diets with 40% HP DDG. There was a linear reduction (P < 0.05) in caloric efficiency with increasing amounts of HP DDG, indicating the initial NE estimate of HP DDG was underestimated. The use of caloric efficiency to estimate the energy value of HP DDG presents several limitations. This approach assumes that the NE values of corn and soybean meal are accurate and does not take into account possible changes in body composition, which can influence the G:F response as leaner pigs are more efficient. In conclusion, increasing HP DDG in the diet linearly decreased ADG and ADFI. Using caloric efficiency to estimate energy content relative to corn, the HP DDG used in this study was estimated to be 97.3% of the energy value of corn. Direct or indirect calorimetry is needed to confirm this value.

Effect of Different Amounts of Hybrid Barley in Diets on the Growth Performance and Selected Biochemical Parameters of Blood Serum Characterizing Health Status in Fattening Pigs

Simple Summary

The aim of the present study was to determine the effect of dietary hybrid barley and/or wheat on production parameters, selected biochemical parameters of blood serum characterizing health status in fattening pigs. The use of hybrid barley as the basic ingredient of diets for fattening pigs provided similar production parameters as those obtained with wheat. No significant differences were noted in case of performance results and meatiness of fatteners. However, usage of hybrid barley with high level in diet decreased level of total cholesterol and LDL (low-density lipoprotein fraction) fraction in blood. It means that barley had a beneficial effect on blood lipid indices.

Abstract

The aim of the study was to determine the effect of dietary hybrid barley and/or wheat on production parameters, selected biochemical parameters of blood serum characterizing health status in fattening pigs. In group I, hybrid barley constituted 80% of feed; in II—wheat and hybrid barley were used, each in amount of 40% feed; in III—contained 80% of wheat. No significant differences were noted in case of performance results (body weight gains, feed intake, and feed conversion ratio) and meatiness of fatteners. All estimated biochemical indices determined in serum were within normal range. Usage of 80% hybrid barley decreased concentration of total cholesterol, low-density lipoprotein fraction (LDL), and triglycerides in blood (p < 0.05). However, high-density lipoprotein fraction (HDL) content increased (p < 0.01) up to 1.04 mmol·dm⁻³, comparing to the group with 80% of wheat (0.84 mmol·dm⁻³). Summarized, the diet with high level of barley had a beneficial effect on blood lipid indices, what indicate a good health status of all animals.

The Implications of Nutritional Strategies that Modify Dietary Energy and Lysine for Growth Performance in Two Different Swine Production Systems

Simple Summary

Reducing dietary energy is a common practice for dealing with the price volatility of high energy sources, such as fats and oils, which are the costliest constraints in swine feed formulation. Theoretically, pigs can overcome a reduced energy density by increasing feed intake; however, as other factors like fibrous ingredients limit feed intake physically rather than metabolically, reducing dietary energy could also entail a lower energy intake. The expected effect on feed intake also influences lysine intake, and therefore, when NE trials are conducted, it is necessary to ensure that lysine is not a limiting factor for growth. In the present work, the effects of two dietary energy and lysine levels were tested in a factorial arrangement. The same approach of different levels was analyzed in two different swine production systems targeting different carcass traits. The experiment showed that in one system, reducing energy density did not impair growth; however, in the other system, it limited growth slightly by limiting fat deposition. Although reducing energy density increased feed intake, pigs could not reach a similar energy intake, and consequently were more efficient using energy for growth.

Abstract

This work aimed to determine the impacts of lowering dietary net energy (NE) density in two swine production systems that produce pigs with different carcass traits. To ensure that dietary lysine was not limiting growth, two studies were conducted in a 2 × 2 factorial arrangement with NE and standardized ileal digestible lysine (SID Lys) as experimental factors. A total of 1248 pigs were used in each study, Pietrain (Exp. 1, males non-castrated) or Duroc (Exp. 2, males castrated) sired. Reducing NE resulted in a greater feed intake; however, this was not sufficient to reach the same NE intake. While in Exp. 1 a 3.2% lower NE intake did not impair average daily gain (ADG; p = 0.220), in Exp. 2 a 4.7% lower NE intake reduced ADG by 1.4% (p = 0.027). Furthermore, this effect on ADG entailed a reduced ham fat thickness (p = 0.004) of the first marketed pigs. Increasing SID Lys only had a positive effect in Exp. 1, but no significant interaction between NE and SID Lys was reported (p ≥ 0.100). Therefore, dietary NE can be reduced without impairing growth performance when pigs can increase feed intake sufficiently, and thus, limit energy deficiencies.

Estimate of the energy value of soybean meal relative to corn based on growth performance of nursery pigs

Background

Two experiments were conducted to determine the effects of increasing amounts of soybean meal (SBM) in swine diets and estimate the energy value of SBM.

Methods

A total of 2233 pigs (PIC 337 × 1050, Hendersonville, TN) and 3796 pigs (PIC 359 × C40), initially 11.0 kg and 17.6 kg body weight (BW), were used in Exp. 1 and 2, respectively. In Exp. 1, pigs were placed in 92 pens each containing 20 to 27 pigs. In Exp. 2, pigs were placed in 84 pens each containing 37 to 43 pigs. Treatments were assigned in a randomized complete block design with BW as the blocking factor. Dietary treatments consisted of 21%, 27%, 33%, or 39% SBM in Exp. 1 and 17.5%, 22%, 26.5%, 31%, 35.5%, or 40% SBM in Exp. 2, obtained by changing the inclusion rate of feed-grade amino acids and corn grain. For Exp. 1, representative samples of corn grain, SBM, and distillers dried grains with solubles were analyzed for total AA content prior to diet formulation. For Exp. 2, diets were formulated using NRC (2012) nutrient loadings. Treatment diets were fed for 21 and 22 d (Exp. 1 and 2) and there were 23 replicates in Exp. 1 and 14 replicates in Exp. 2. Pigs were weighed and feed disappearance measured weekly to calculate average daily gain (ADG), average daily feed intake (ADFI), gain-to-feed ratio (G:F), and caloric efficiency (CE). Data were analyzed with block as a random effect and treatment as a fixed effect, and contrasts were constructed to test the linear and quadratic effects of increasing SBM.

Results

In Exp. 1, there was a tendency (linear, P = 0.092) for a decrease in ADFI as SBM increased. There was a tendency (P = 0.090) for a quadratic response for ADG, with a decrease in ADG observed with 39% SBM inclusion. Pigs fed diets with increasing SBM had a tendency (quadratic, P = 0.069) for an increase in G:F up to 33% SBM and an improvement (linear, P = 0.001; quadratic, P = 0.063) in CE with increasing SBM. Using CE to estimate the energy of SBM relative to corn, a value of 105.4% of corn energy or 2816 kcal/kg NE was determined using all data points. When removing the CE value of the 39% SBM treatment due to the quadratic tendency, SBM was estimated to have 121.1% of corn energy or 3236 kcal/kg NE. In Exp. 2, there was a decrease (linear, P = 0.001) in ADFI. Pigs fed increasing SBM had a tendency (linear, P = 0.065) for reduced ADG but an improvement (linear, P = 0.001) in G:F and CE as SBM increased. The energy value of SBM was estimated as 124.7% of corn energy or 3332 kcal/kg NE.

Conclusions

The results suggest that feeding increasing levels of SBM improves G:F and CE. The energy value of SBM was estimated to be between 105% and 125% of corn, which is much greater than the NRC (2012) would indicate.

Diet formulation method influences the response to increasing net energy in finishing pigs

An experiment was conducted to compare the effects of increasing dietary net energy (NE) in finishing pig diets while either maintaining a standardized ileal digestible lysine:NE ratio (SID Lys:NE) or maintaining SID Lys as a constant percentage of the diet across increasing energy densities. A total of 150 pigs (Line 600 × 241; DNA, Columbus, NE; initially 35.7 kg) were used in a 91-d study. Pigs were blocked by sex and weight and randomly assigned to 1 of 5 treatments with 2 pigs per pen and 15 pens per treatment. Treatments included a low-energy control diet that was corn-soybean meal-based with added soybean hulls, and a 2 × 2 factorial arrangement of treatments with main effects of increasing dietary NE (medium or high by adding choice white grease) and formulation method (with a SID Lys:NE ratio or maintaining the same percentage SID Lys). Linear and quadratic contrasts were made using the control diet and the medium- and high-energy diets within each formulation method. Pigs and feeders were weighed approximately every 30 d to calculate average daily gain (ADG), average daily feed intake (ADFI), and gain-to-feed ratio (G:F). At the end of the experiment, pigs were sent to a commercial processing facility for carcass data collection. From days 0 to 34 and 34 to 61, ADG and SID Lys intake increased as NE increased (linear, P < 0.05) in pigs fed diets with a Lys:NE ratio, but not for those fed the same percentage Lys. As NE increased, NE intake and G:F increased (P < 0.01) in pigs fed diets with either formulation method. From days 61 to 91, increasing NE had no effect (P > 0.10) on ADG. There was no change in G:F in pigs fed diets with the same percentage Lys (P > 0.10), but G:F decreased then increased (quadratic, P < 0.01) in response to increasing NE in pigs fed diets with a SID Lys:NE ratio. Overall, increasing dietary NE increased (linear, P < 0.001) daily NE intake and G:F (linear, P < 0.018) with either formulation method. However, SID Lys intake, ADG, and hot carcass weight only increased (linear, P < 0.01) when a SID Lys:NE ratio was maintained. Increasing NE without maintaining a constant SID Lys:NE ratio increased backfat depth (quadratic, P = 0.01), whereas it did not in pigs fed diets with a SID Lys:NE ratio. In conclusion, increasing dietary energy density increased NE intake and G:F regardless of formulation method. However, a SID Lys:NE ratio must be maintained to achieve increased ADG and minimize fat deposition.

Meta-regression analysis to predict the influence of branched-chain and large neutral amino acids on growth performance of pigs1

A meta-analysis was conducted to evaluate the effects of branched-chain amino acids (BCAA), their interactions, and interactions with large neutral amino acids (LNAA) to develop prediction equations for growth performance of pigs. Data from 25 papers, published from 1995 to 2018, for a total of 44 trials and 210 observations were recorded in a database. Diets were reformulated using the NRC (2012) loading values to estimate nutrient concentrations. The response variables were average daily gain (ADG), average daily feed intake (ADFI), and gain-to-feed ratio (G:F). The predictor variables tested included average body weight (BW), crude protein, neutral detergent fiber, Ile:Lys, Leu:Lys, Val:Lys, BCAA:Lys, Ile:Leu, Val:Leu, Ile:Val, (Ile+Val):Leu, Trp:Lys, Leu:Trp, Ile:Trp, Val:Trp, BCAA:Trp, Met:Lys, Leu:Met, Ile:Met, Val:Met, BCAA:Met, His:Lys, Leu:His, Ile:His, Val:His, BCAA:His, Thr:Lys, Leu:Thr, Ile:Thr, Val:Thr, BCAA:Thr, (Phe+Tyr):Lys, Leu:(Phe+Tyr), Ile:(Phe+Tyr), Val:(Phe+Tyr), BCAA:(Phe+Tyr), LNAA:Lys, Leu:LNAA, Ile:LNAA, Val:LNAA, and BCAA:LNAA. Amino acids were expressed on standardized ileal digestible basis. The MIXED procedure of SAS (SAS Institute Inc., Cary, NC) was used to develop the equations. The inverse of squared SEM was used to account for heterogeneous errors using the WEIGHT statement. Models were selected with a step-wise manual forward selection. In order to be included in the final model, predictor variables had to be statistically significant (P < 0.05) and provide an improvement of at least 2 points in Bayesian information criterion. The optimum equations were: ADG, g = - 985.94 + (15.2499 × average BW (kg)) - (0.08885 × average BW × average BW) + (1.063 × Leu:Lys) + (20.2659 × Ile:Lys) - (0.1479 × Ile:Lys × Ile:Lys) + (9.2243 × (Ile+Val):Leu) - (0.03321 × (Ile+Val):Leu × (Ile+Val):Leu) - (0.4413 × Ile:Trp); G:F, g/kg = 648.3 - (6.2974 × average BW (kg)) + (0.02051 × average BW × average BW) + (0.5396 × Ile:Lys) + (1.7284 × Val:Lys) - (0.00795 × Val:Lys × Val:Lys) - (1.7594 × Met:Lys); and ADFI, kg = predicted ADG/predicted G:F. Overall, the prediction equations suggest that increasing Leu:Lys negatively impacts ADG due to a reduction in G:F and ADFI caused by insufficient levels of other BCAA and LNAA relative to Leu. According to the model, the addition of Val, Ile, and Trp, alone or in combination, has the potential to counteract the negative effects of high dietary Leu concentrations on growth performance.

Methodologies on estimating the energy requirements for maintenance and determining the net energy contents of feed ingredients in swine: a review of recent work

In the past two decades, a considerable amount of research has focused on the determination of the digestible (DE) and metabolizable energy (ME) contents of feed ingredients fed to swine. Compared with the DE and ME systems, the net energy (NE) system is assumed to be the most accurate estimate of the energy actually available to the animal. However, published data pertaining to the measured NE content of ingredients fed to growing pigs are limited. Therefore, the Feed Data Group at the Ministry of Agricultural Feed Industry Centre (MAFIC) located at China Agricultural University has evaluated the NE content of many ingredients using indirect calorimetry. The present review summarizes the NE research works conducted at MAFIC and compares these results with those from other research groups on methodological aspect. These research projects mainly focus on estimating the energy requirements for maintenance and its impact on the determination, prediction, and validation of the NE content of several ingredients fed to swine. The estimation of maintenance energy is affected by methodology, growth stage, and previous feeding level. The fasting heat production method and the curvilinear regression method were used in MAFIC to estimate the NE requirement for maintenance. The NE contents of different feedstuffs were determined using indirect calorimetry through standard experimental procedure in MAFIC. Previously generated NE equations can also be used to predict NE in situations where calorimeters are not available. Although popular, the caloric efficiency is not a generally accepted method to validate the energy content of individual feedstuffs. In the future, more accurate and dynamic NE prediction equations aiming at specific ingredients should be established, and more practical validation approaches need to be developed.

Development of equations to predict the influence of floor space on average daily gain, average daily feed intake and gain : feed ratio of finishing pigs

Floor space allowance for pigs has substantial effects on pig growth and welfare. Data from 30 papers examining the influence of floor space allowance on the growth of finishing pigs was used in a meta-analysis to develop alternative prediction equations for average daily gain (ADG), average daily feed intake (ADFI) and gain : feed ratio (G : F). Treatment means were compiled in a database that contained 30 papers for ADG and 28 papers for ADFI and G : F. The predictor variables evaluated were floor space (m2/pig), k (floor space/final BW0.67), Initial BW, Final BW, feed space (pigs per feeder hole), water space (pigs per waterer), group size (pigs per pen), gender, floor type and study length (d). Multivariable general linear mixed model regression equations were used. Floor space treatments within each experiment were the observational and experimental unit. The optimum equations to predict ADG, ADFI and G : F were: ADG, g=337.57+(16 468×k)-(237 350×k 2)-(3.1209×initial BW (kg))+(2.569×final BW (kg))+(71.6918×k×initial BW (kg)); ADFI, g=833.41+(24 785×k)-(388 998×k 2)-(3.0027×initial BW (kg))+(11.246×final BW (kg))+(187.61×k×initial BW (kg)); G : F=predicted ADG/predicted ADFI. Overall, the meta-analysis indicates that BW is an important predictor of ADG and ADFI even after computing the constant coefficient k, which utilizes final BW in its calculation. This suggests including initial and final BW improves the prediction over using k as a predictor alone. In addition, the analysis also indicated that G : F of finishing pigs is influenced by floor space allowance, whereas individual studies have concluded variable results.

Effects of amino acids and energy intake during late gestation of high-performing gilts and sows on litter and reproductive performance under commercial conditions

The objective of this study was to determine the effects of AA and energy intake during late gestation on piglet birth weight and reproductive performance of high-performing (14.5 total born) gilts and sows housed under commercial conditions. At d 90 of gestation, a total of 1,102 females (PIC 1050) were housed in pens by parity group (gilts or sows) with approximately 63 gilts and 80 sows in each pen, blocked by BW within each pen, and each female was randomly assigned to dietary treatments within BW block. Dietary treatments consisted of combinations of 2 standardized ileal digestible (SID) AA intakes (10.7 or 20.0 g/d SID Lys and other AA met or exceeded the NRC [2012] recommendations) and 2 energy intakes (4.50 or 6.75 Mcal/d intake of NE) in a 2 × 2 factorial arrangement. Data were analyzed using generalized linear mixed models specified to recognize pen as the experimental unit for parity and the individual female as the experimental unit for dietary treatments. Results indicate an overall positive effect of high energy intake on BW gain during late gestation, although this effect was more manifest under conditions of high, as opposed to low, AA intake (interaction, < 0.001). Furthermore, the magnitude of BW gain response to increased energy intake was greater ( < 0.001) for sows compared with gilts. Sows fed high energy intake had a reduced probability of piglets born alive ( < 0.004) compared with those fed low energy, but no evidence for differences was found in gilts. This can be explained by an increased probability ( = 0.002) of stillborns in sows fed high energy intake vs. sows fed low energy intake. There were no evidences for differences among dietary treatments in litter birth weight and individual piglet birth weight of total piglets born. However, individual born alive birth weight was approximately 30 ± 8.2 g heavier ( = 0.011) for females fed high, as opposed to low, energy intake. Furthermore, piglets born alive were approximately 97 ± 9.5 g heavier ( < 0.001) for sows than for gilts. Preweaning mortality was decreased ( = 0.034) for females fed high AA intake compared with females fed low AA intake regardless of energy level. In conclusion, 1) BW gain of gilts and sows depended not only on energy but also on AA intake, 2) sows fed increased amount of energy had an increased stillborn rate, and 3) increased energy intake during late gestation had a positive effect on individual piglet birth weight with no evidence for such an effect for AA intake.