Prediction of immunoglobulin g in lambs with artificial intelligence methods
The health, mortality and morbidity rates of neonatal ruminants depend on colostrum quality and the amount of Immunoglobulin G (IgG) absorbed. Computer-aided estimates are important as measuring IgG concentration with conventional methods is costly. In this study, artificial neural network (ANN), mu...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Kafkas University, Faculty of Veterinary Medicine
2021-01-01
|
Series: | Kafkas Universitesi Veteriner Fakültesi Dergisi |
Subjects: | |
Online Access: | https://vetdergikafkas.org/pdf.php?id=2772 |
_version_ | 1797800707122790400 |
---|---|
author | Pınar CİHAN Erhan GÖKÇE Onur ATAKİŞİ Ali Haydar KIRMIZIGÜL Hidayet Metin ERDOĞAN |
author_facet | Pınar CİHAN Erhan GÖKÇE Onur ATAKİŞİ Ali Haydar KIRMIZIGÜL Hidayet Metin ERDOĞAN |
author_sort | Pınar CİHAN |
collection | DOAJ |
description | The health, mortality and morbidity rates of neonatal ruminants depend on colostrum quality and the amount of Immunoglobulin
G (IgG) absorbed. Computer-aided estimates are important as measuring IgG concentration with conventional methods is costly.
In this study, artificial neural network (ANN), multivariate adaptive regression splines (MARS), support vector regression (SVR)
and fuzzy neural network (FNN) models were used to predict the serum IgG concentration from gamma-glutamyl transferase
(GGT) enzyme activity, total protein (TP) concentration and albumin (ALB). The correlation between parameters was examined. IgG
positively correlated with GGT and TP and negatively correlated with ALB (R = 0.75, P<0.001; R = 0.67, P<0.001; R = -0.17, P<0.01,
respectively). IgG, GGT, and TP cut-off values were determined for mortality, healthy, and morbidity in neonatal lambs by decision
tree method. IgG ≤113 mg/dL (P<0.001), GGT ≤191 mg/dL (P=0.001), and TP ≤45 g/L (P<0.001) were determined for mortality. IgG
>575 mg/dL (P=0.02), GGT >191 mg/dL (P<0.001), and TP >55 g/L (P<0.001) were determined for healthy. It has been observed that
the FNN is the most successful method for the prediction of IgG value with a correlation coefficient (R) of 0.98, root mean square
error (RMSE) of 234.4, and mean absolute error (MAE) of 175.8. |
first_indexed | 2024-03-13T04:39:20Z |
format | Article |
id | doaj.art-6793e48de43b476f9e224bed330e916c |
institution | Directory Open Access Journal |
issn | 1309-2251 |
language | English |
last_indexed | 2024-03-13T04:39:20Z |
publishDate | 2021-01-01 |
publisher | Kafkas University, Faculty of Veterinary Medicine |
record_format | Article |
series | Kafkas Universitesi Veteriner Fakültesi Dergisi |
spelling | doaj.art-6793e48de43b476f9e224bed330e916c2023-06-19T06:31:51ZengKafkas University, Faculty of Veterinary MedicineKafkas Universitesi Veteriner Fakültesi Dergisi1309-22512021-01-01271212710.9775/kvfd.2020.246422772Prediction of immunoglobulin g in lambs with artificial intelligence methodsPınar CİHAN0Erhan GÖKÇE1Onur ATAKİŞİ2Ali Haydar KIRMIZIGÜL3Hidayet Metin ERDOĞAN4Department of Computer Engineering, Faculty of Çorlu Engineering, Tekirdağ Namık Kemal University, TR-59860 Tekirdağ - TURKEYDepartment of Internal Medicine, Faculty of Veterinary Medicine, University of Kafkas, TR-36100 Kars - TURKEYDepartment of Chemistry, Faculty of Art and Science, University of Kafkas, TR-36300 Kars - TURKEYDepartment of Internal Medicine, Faculty of Veterinary Medicine, University of Kafkas, TR-36100 Kars - TURKEYDepartment of Internal Medicine, Faculty of Veterinary Medicine, University of Aksaray, TR-68100 Aksaray - TURKEYThe health, mortality and morbidity rates of neonatal ruminants depend on colostrum quality and the amount of Immunoglobulin G (IgG) absorbed. Computer-aided estimates are important as measuring IgG concentration with conventional methods is costly. In this study, artificial neural network (ANN), multivariate adaptive regression splines (MARS), support vector regression (SVR) and fuzzy neural network (FNN) models were used to predict the serum IgG concentration from gamma-glutamyl transferase (GGT) enzyme activity, total protein (TP) concentration and albumin (ALB). The correlation between parameters was examined. IgG positively correlated with GGT and TP and negatively correlated with ALB (R = 0.75, P<0.001; R = 0.67, P<0.001; R = -0.17, P<0.01, respectively). IgG, GGT, and TP cut-off values were determined for mortality, healthy, and morbidity in neonatal lambs by decision tree method. IgG ≤113 mg/dL (P<0.001), GGT ≤191 mg/dL (P=0.001), and TP ≤45 g/L (P<0.001) were determined for mortality. IgG >575 mg/dL (P=0.02), GGT >191 mg/dL (P<0.001), and TP >55 g/L (P<0.001) were determined for healthy. It has been observed that the FNN is the most successful method for the prediction of IgG value with a correlation coefficient (R) of 0.98, root mean square error (RMSE) of 234.4, and mean absolute error (MAE) of 175.8.https://vetdergikafkas.org/pdf.php?id=2772artificial neural networkdecision treefuzzy neural networkimmunoglobulin gmultivariate adaptive regression splinessupport vector regression |
spellingShingle | Pınar CİHAN Erhan GÖKÇE Onur ATAKİŞİ Ali Haydar KIRMIZIGÜL Hidayet Metin ERDOĞAN Prediction of immunoglobulin g in lambs with artificial intelligence methods Kafkas Universitesi Veteriner Fakültesi Dergisi artificial neural network decision tree fuzzy neural network immunoglobulin g multivariate adaptive regression splines support vector regression |
title | Prediction of immunoglobulin g in lambs with artificial intelligence methods |
title_full | Prediction of immunoglobulin g in lambs with artificial intelligence methods |
title_fullStr | Prediction of immunoglobulin g in lambs with artificial intelligence methods |
title_full_unstemmed | Prediction of immunoglobulin g in lambs with artificial intelligence methods |
title_short | Prediction of immunoglobulin g in lambs with artificial intelligence methods |
title_sort | prediction of immunoglobulin g in lambs with artificial intelligence methods |
topic | artificial neural network decision tree fuzzy neural network immunoglobulin g multivariate adaptive regression splines support vector regression |
url | https://vetdergikafkas.org/pdf.php?id=2772 |
work_keys_str_mv | AT pınarcihan predictionofimmunoglobulinginlambswithartificialintelligencemethods AT erhangokce predictionofimmunoglobulinginlambswithartificialintelligencemethods AT onuratakisi predictionofimmunoglobulinginlambswithartificialintelligencemethods AT alihaydarkirmizigul predictionofimmunoglobulinginlambswithartificialintelligencemethods AT hidayetmetinerdogan predictionofimmunoglobulinginlambswithartificialintelligencemethods |