The usage of the autoregressive integrated moving average model for forecasting milk production in Egypt (2022–2025) Mohamed Omar, Fardos Hassan, Sara Shahin, Marwa shahat Open Veterinary Journal, 2024 Background: Milk considered one of the most important capital goods and essential source of animal protein in the diet of Egyptian family, as well as an effective mean to improve economic condition of farmers, considering this importance in view, the policy makers need accurate and advance information regarding future supply for planning on both short and long term. Aim: The study aims to forecast the production of milk in Egypt during the period from 2022 to 2025 using Autoregressive Integrated Moving Average (ARIMA) model using time series data of milk production (1970-2021) obtained from Central Agency for public mobilization and statistics (CAPMS). Methods: Augmented Dickey-Fullar Unit Root test, Partial autocorrelation function (PACF) and Autocorrelation function (ACF) of the time series sequence were used to judge the stationarity of the data. After confirming the stationarity of the data, the appropriate ARIMA model was selected based on certain statistical parameters like significant coefficients, values of adjusted R-squared, Akaike information criteria, Schwarz criterion and Standard Error of regression. After the selection of model based on the previous parameters the verification of model was employed through checking the residuals by Correlogram-Q-Statistics test. Results: The most fitted model to predict the future levels of milk production in Egypt was ARIMA (1, 1, and 3). Conclusion: Using ARIMA (1, 1, 3) model, it could be forecasted that the production of milk in Egypt would show increasing trend from 6152.606 thousand tons in 2022 to 6360.829 thousand tons in 2025.
A COMBINED APPROACH OF MULTIPLE CORRESPONDENCE ANALYSIS AND HIERARCHICAL CLUSTER ANALYSIS FOR PROFILING RELATIONSHIPS AMONG CATEGORICAL RISK PREDICTORS: A BLUETONGUE CASE STUDY Iman E. El-Araby, Sherif A. Moawed, Fardos A. M. Hassan, Hagar F. Gouda Slovenian Veterinary Research, 2023 Bluetongue (BT) is a non-contagious virus in the Reoviridae family that infects both wild and domestic animals. It causes economic losses and reduces infected animals' production and reproduction. A total of 233 apparently healthy animals were screened for BT. Profiles of health condition of animals were identified using multiple correspondence analysis (MCA) and hierarchical cluster analysis (HCA), and the impact of the change in disease condition of animals was explored by examining the subjective evaluation of the impact of risk factors like (age, sex, season, species, and locality) with regard to BT disease providing an insight into a dataset through information visualization and it presents a useful application for visualizing associations amongst variable categories. The first two MCA dimensions retained up to 27% of the total inertia contained in the data. The positive BT results, summer, and old animals categories were loaded in the first dimension, while negative cases, Al-mounfia and winter categories were related to the second dimension. HCA identified three clusters. Cluster 1 was characterized by frequent and largely exclusive seronegative BT animals 91.67 % of animals in the cluster were seronegative, negative BTV category is the most important and related to cluster 1 with positive v-test=8.75. Cluster 3 can named a cluster of seropositive BT, up to 88% of cases were seropositive. We can conclude that seropositive BT is associated with summer and old age categories, whereas seronegative BT is associated with young age and winter categories, and thus MCA and HCA provide convenient and easy-to-interpret analytical tools for assessing categorical data relationships.
Impact of resveratrol-loaded liposomal nanocarriers on heat-stressed broiler chickens: Effects on performance, sirtuin expression, oxidative stress regulators, and muscle building factors Asmaa T. Y. Kishawy, Doaa Ibrahim, Elshimaa M. Roushdy, Amira Moustafa, Fatma Eldemery, et al. Frontiers in Veterinary Science, 2023 Climate change is considered to be the primary cause of heat stress (HS) in broiler chickens. Owing to the unique properties of extracted polyphenols, resveratrol-loaded liposomal nanoparticles (Resv-Lipo NPs) were first explored to mitigate the harmful effects of HS. The dietary role of Resv-Lipo NPs in heat-stressed birds was investigated based on their growth performance, antioxidative potential, and the expression of heat shock proteins, sirtuins, antioxidant, immune, and muscle-building related genes. A total of 250 1-day-old Ross 308 broiler chickens were divided into five experimental groups (5 replicates/group, 10 birds/replicate) for 42 days as follows: the control group was fed a basal diet and reared in thermoneutral conditions, and the other four HS groups were fed a basal diet supplemented with Resv-Lipo NPsI, II, and III at the levels of 0, 50, 100, and 150 mg/kg diet, respectively. The results indicated that supplementation with Resv-Lipo NP improved the growth rate of the HS group. The Resv-Lipo NP group showed the most significant improvement in body weight gain (p < 0.05) and FCR. Additionally, post-HS exposure, the groups that received Resv-Lipo NPs showed restored functions of the kidney and the liver as well as improvements in the lipid profile. The restoration occurred especially at higher levels in the Resv-Lipo NP group compared to the HS group. The elevated corticosterone and T3 and T4 hormone levels in the HS group returned to the normal range in the Resv-Lipo NPsIII group. Additionally, the HS groups supplemented with Resv-Lipo NPs showed an improvement in serum and muscle antioxidant biomarkers. The upregulation of the muscle and intestinal antioxidant-related genes (SOD, CAT, GSH-PX, NR-f2, and HO-1) and the muscle-building genes (myostatin, MyoD, and mTOR) was observed with increasing the level of Resv-Lipo NPs. Heat stress upregulated heat shock proteins (HSP) 70 and 90 gene expression, which was restored to normal levels in HS+Resv-Lipo NPsIII. Moreover, the expression of sirtuin 1, 3, and 7 (SIRT1, SIRT3, and SIRT7) genes was increased (p < 0.05) in the liver of the HS groups that received Resv-Lipo NPs in a dose-dependent manner. Notably, the upregulation of proinflammatory cytokines in the HS group was restored in the HS groups that received Resv-Lipo NPs. Supplementation with Resv-Lipo NPs can mitigate the harmful impact of HS and consequently improve the performance of broiler chickens.
Comparison of machine learning models for bluetongue risk prediction: a seroprevalence study on small ruminants Hagar F. Gouda, Fardos A. M. Hassan, Eman E. El-Araby, Sherif A. Moawed BMC Veterinary Research, 2022 Background Bluetongue (BT) is a disease of concern to animal breeders, so the question on their minds is whether they can predict the risk of the disease before it occurs. The main objective of this study is to enhance the accuracy of BT risk prediction by relying on machine learning (ML) approaches to help in fulfilling this inquiry. Several risk factors of BT that affect the occurrence and magnitude of animal infection with the virus have been reported globally. Additionally, risk factors, such as sex, age, species, and season, unevenly affect animal health and welfare. Therefore, the seroprevalence study data of 233 apparently healthy animals (125 sheep and 108 goats) from five different provinces in Egypt were used to analyze and compare the performance of the algorithms in predicting BT risk. Results Logistic regression (LR), decision tree (DT), random forest (RF), and a feedforward artificial neural network (ANN) were used to develop predictive BT risk models and compare their performance to the base model (LR). Model performance was assessed by the area under the receiver operating characteristics curve (AUC), accuracy, true positive rate (TPR), false positive rate (FPR), false negative rate (FNR), precision, and F1 score. The results indicated that RF performed better than other models, with an AUC score of 81%, ANN of 79.6%, and DT of 72.85%. In terms of performance and prediction, LR showed a much lower value (AUC = 69%). Upon further observation of the results, it was discovered that age and season were the most important predictor variables reported in classification and prediction. Conclusion The findings of this study can be utilized to predict and control BT risk factors in sheep and goats, with better diagnostic discrimination in terms of accuracy, TPR, FNR, FPR, and precision of ML models over traditional and commonly used LR models. Our findings advocate that the implementation of ML algorithms, mainly RF, in farm decision making and prediction is a promising technique for analyzing cross-section studies, providing adequate predictive power and significant competence in identifying and ranking predictors representing potential risk factors for BT.
Machine Learning Based Prediction for Solving Veterinary Data Problems: A Review Journal of Advanced Veterinary Research, 2022
Effects of different feeding regimens with protease supplementation on growth, amino acid digestibility, economic efficiency, blood biochemical parameters, and intestinal histology in broiler chickens Shimaa A. Amer, Rasha R. Beheiry, Doaa M. Abdel Fattah, Elshimaa M. Roushdy, Fardos A. M. Hassan, et al. BMC Veterinary Research, 2021 Background This study was conducted to estimate the impacts of using varied feeding regimens with or without protease supplementation on the growth performance, apparent amino acid ileal digestibility (AID%), economic efficiency, intestinal histology, and blood biochemical parameters of broiler chickens. Three hundred one-day-old chicks (Ross 308 broiler) were randomly allotted to a 3 × 2 factorial design. The experimental design consisted of three feeding regimens; FR1: a recommended protein SBM diet, FR2: a low-protein SBM diet, and FR3: a low-protein diet with the inclusion of 5% DDGS and 5% SFM, with or without protease supplementation (250 mg/kg). Results Increased feed intake and feed conversion ratio were observed in the FR3 treatment during the starter stage and decreased body weight and body weight gain during the grower stage. However, there was no significant effect of the different feeding regimens, protease supplementation, or interaction on the overall performance. The economic value of diets also remained unaffected by the different feeding regimens, protease supplementation, or interaction. Protease supplementation resulted in lowering the AID% of tryptophan and leucine. Reduced AID% of methionine was evident in the FR2 + VE and FR3 − VE treatments. Histological findings substantiated the FR3 treatment mediated a decrease in the duodenal and jejunal villous height (VH), jejunal villous width (VW), and ileal VW, whereas, increase in the ileal crypt depth (CD). The FR2 + VE treatment reduced the VH:CD ratio in the duodenum. The duodenal CD and the jejunal goblet cell count were reduced as a consequence of protease supplementation. The FR3 + VE treatment documented a rise in duodenal CD, while an increase in the jejunal goblet cell count was observed in the FR3 − VE treatment. The FR3 treatment enhanced the IgM serum levels compared to the FR1 and FR2 treatments. IgM serum levels were also elevated following protease supplementation. FR3 + VE treatment increased IgM serum levels. The highest serum ALP was found in the FR3 treatment, whereas the lowest level was obtained in the FR2 treatment. Conclusion Low-protein SBM-based diets could be used without affecting the birds’ growth. Altered morphometric measures of the intestine and increased IgM and ALP levels indicated the low-protein SBM/DDGS-SFM diet-induced damage of the intestinal histoarchitecture and immune system of birds. These different diets and protease supplementation failed to affect economic efficiency positively.
Growth performance, tissue precipitation, metallothionein and cytokine transcript expression and economics in response to different dietary zinc sources in growing rabbits Fardos A. M. Hassan, Asmaa T. Y. Kishawy, Amira Moustafa, Elshimaa M. Roushdy Journal of Animal Physiology and Animal Nutrition, 2021 The impact of different dietary zinc sources on the growth, serum metabolites, tissue zinc content, economics and relative expression of cytokine and metallothionein genes was evaluated in this study. A total of 120 35-day-old male New Zealand White (NZW) rabbits were randomly distributed into four dietary experimental groups with 10 replicates per group and 3 animals per replicate. The control group was fed basal diet with a Zn-free vitamin-mineral premix; the other three groups received control basal diet supplemented with 50 mg/kg level with zinc oxide (ZnO; as inorganic source), Zn-methionine (Zn-Met; as organic source) and zinc oxide nanoparticles (nano-ZnO). The results indicated that Zn-Met and nano-ZnO groups significantly improved body weight, daily weight gain (DWG), feed conversion ratio (FCR) and nutrient digestibility, as well as decreased mortality, compared to ZnO and control groups. Zn-Met and nano-ZnO significantly reduced serum total cholesterol but did not affect serum proteins and liver function. Nano-ZnO supplemented group also recorded the highest value of serum alkaline phosphatase (ALP), insulin-like growth factor (IGF-1) and lysozymes compared to other groups. Nano-ZnO supplementation had increased hepatic Zn and Cu content and decreased faecal Zn content. Also nano-ZnO group recorded higher expression levels of genes encoding for metallothionein I and metallothionein II, interleukin-2 and interferon-γ in the liver of rabbits. The findings of this study demonstrated zinc nanoparticles, and organic zinc supplementation had improved growth performance and health status of growing rabbits than inorganic zinc oxide.