Improving Ovine Behavioral Pain Diagnosis by Implementing Statistical Weightings Based on Logistic Regression and Random Forest Algorithms
Recently, the Unesp-Botucatu sheep acute pain scale (USAPS) was created, refined, and psychometrically validated as a tool that offers fast, robust, and simple application. Evidence points to an improvement in pain diagnosis when the importance of the behavioral items of an instrument is statistical...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Animals |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-2615/12/21/2940 |
_version_ | 1797469399502815232 |
---|---|
author | Pedro Henrique Esteves Trindade João Fernando Serrajordia Rocha de Mello Nuno Emanuel Oliveira Figueiredo Silva Stelio Pacca Loureiro Luna |
author_facet | Pedro Henrique Esteves Trindade João Fernando Serrajordia Rocha de Mello Nuno Emanuel Oliveira Figueiredo Silva Stelio Pacca Loureiro Luna |
author_sort | Pedro Henrique Esteves Trindade |
collection | DOAJ |
description | Recently, the Unesp-Botucatu sheep acute pain scale (USAPS) was created, refined, and psychometrically validated as a tool that offers fast, robust, and simple application. Evidence points to an improvement in pain diagnosis when the importance of the behavioral items of an instrument is statistically weighted; however, this has not yet been investigated in animals. The objective was to investigate whether the implementation of statistical weightings using machine learning algorithms improves the USAPS discriminatory capacity. A behavioral database, previously collected for USAPS validation, of 48 sheep in the perioperative period of laparoscopy was used. A multilevel binomial logistic regression algorithm and a random forest algorithm were used to determine the statistical weights and classify the sheep as to whether they needed analgesia or not. The quality of the classification, estimated by the area under the curve (AUC) and its 95% confidence interval (CI), was compared between the USAPS versions. The USAPS AUCs weighted by multilevel binomial logistic regression (96.59 CI: [95.02–98.15]; <i>p</i> = 0.0004) and random forest algorithms (96.28 CI: [94.17–97.85]; <i>p</i> = 0.0067) were higher than the original USAPS AUC (94.87 CI: [92.94–96.80]). We conclude that the implementation of statistical weights by the two machine learning algorithms improved the USAPS discriminatory ability. |
first_indexed | 2024-03-09T19:20:52Z |
format | Article |
id | doaj.art-384d13fdd6fd43b6989954aedcdcb25e |
institution | Directory Open Access Journal |
issn | 2076-2615 |
language | English |
last_indexed | 2024-03-09T19:20:52Z |
publishDate | 2022-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Animals |
spelling | doaj.art-384d13fdd6fd43b6989954aedcdcb25e2023-11-24T03:24:16ZengMDPI AGAnimals2076-26152022-10-011221294010.3390/ani12212940Improving Ovine Behavioral Pain Diagnosis by Implementing Statistical Weightings Based on Logistic Regression and Random Forest AlgorithmsPedro Henrique Esteves Trindade0João Fernando Serrajordia Rocha de Mello1Nuno Emanuel Oliveira Figueiredo Silva2Stelio Pacca Loureiro Luna3Department of Veterinary Surgery and Animal Reproduction, School of Veterinary Medicine and Animal Science, São Paulo State University, Botucatu 05508-270, SP, BrazilDepartment of Quantitative Analytics, Escola Superior de Propaganda e Marketing (ESPM), São Paulo 04018-010, SP, BrazilDepartment of Veterinary Surgery and Animal Reproduction, School of Veterinary Medicine and Animal Science, São Paulo State University, Botucatu 05508-270, SP, BrazilDepartment of Veterinary Surgery and Animal Reproduction, School of Veterinary Medicine and Animal Science, São Paulo State University, Botucatu 05508-270, SP, BrazilRecently, the Unesp-Botucatu sheep acute pain scale (USAPS) was created, refined, and psychometrically validated as a tool that offers fast, robust, and simple application. Evidence points to an improvement in pain diagnosis when the importance of the behavioral items of an instrument is statistically weighted; however, this has not yet been investigated in animals. The objective was to investigate whether the implementation of statistical weightings using machine learning algorithms improves the USAPS discriminatory capacity. A behavioral database, previously collected for USAPS validation, of 48 sheep in the perioperative period of laparoscopy was used. A multilevel binomial logistic regression algorithm and a random forest algorithm were used to determine the statistical weights and classify the sheep as to whether they needed analgesia or not. The quality of the classification, estimated by the area under the curve (AUC) and its 95% confidence interval (CI), was compared between the USAPS versions. The USAPS AUCs weighted by multilevel binomial logistic regression (96.59 CI: [95.02–98.15]; <i>p</i> = 0.0004) and random forest algorithms (96.28 CI: [94.17–97.85]; <i>p</i> = 0.0067) were higher than the original USAPS AUC (94.87 CI: [92.94–96.80]). We conclude that the implementation of statistical weights by the two machine learning algorithms improved the USAPS discriminatory ability.https://www.mdpi.com/2076-2615/12/21/2940animal welfareartificial intelligencepain assessmentsheep |
spellingShingle | Pedro Henrique Esteves Trindade João Fernando Serrajordia Rocha de Mello Nuno Emanuel Oliveira Figueiredo Silva Stelio Pacca Loureiro Luna Improving Ovine Behavioral Pain Diagnosis by Implementing Statistical Weightings Based on Logistic Regression and Random Forest Algorithms Animals animal welfare artificial intelligence pain assessment sheep |
title | Improving Ovine Behavioral Pain Diagnosis by Implementing Statistical Weightings Based on Logistic Regression and Random Forest Algorithms |
title_full | Improving Ovine Behavioral Pain Diagnosis by Implementing Statistical Weightings Based on Logistic Regression and Random Forest Algorithms |
title_fullStr | Improving Ovine Behavioral Pain Diagnosis by Implementing Statistical Weightings Based on Logistic Regression and Random Forest Algorithms |
title_full_unstemmed | Improving Ovine Behavioral Pain Diagnosis by Implementing Statistical Weightings Based on Logistic Regression and Random Forest Algorithms |
title_short | Improving Ovine Behavioral Pain Diagnosis by Implementing Statistical Weightings Based on Logistic Regression and Random Forest Algorithms |
title_sort | improving ovine behavioral pain diagnosis by implementing statistical weightings based on logistic regression and random forest algorithms |
topic | animal welfare artificial intelligence pain assessment sheep |
url | https://www.mdpi.com/2076-2615/12/21/2940 |
work_keys_str_mv | AT pedrohenriqueestevestrindade improvingovinebehavioralpaindiagnosisbyimplementingstatisticalweightingsbasedonlogisticregressionandrandomforestalgorithms AT joaofernandoserrajordiarochademello improvingovinebehavioralpaindiagnosisbyimplementingstatisticalweightingsbasedonlogisticregressionandrandomforestalgorithms AT nunoemanueloliveirafigueiredosilva improvingovinebehavioralpaindiagnosisbyimplementingstatisticalweightingsbasedonlogisticregressionandrandomforestalgorithms AT steliopaccaloureiroluna improvingovinebehavioralpaindiagnosisbyimplementingstatisticalweightingsbasedonlogisticregressionandrandomforestalgorithms |