K E Lawrence, R G Clark, H V Henderson, K Govindaraju, C Balcomb
{"title":"downner cows:对旧数据集的重新分析。","authors":"K E Lawrence, R G Clark, H V Henderson, K Govindaraju, C Balcomb","doi":"10.1080/00480169.2022.2155262","DOIUrl":null,"url":null,"abstract":"<p><strong>Aims: </strong>To compare the performance of two predictive models for the survival of downer cows.</p><p><strong>Methods: </strong>The first model had been developed in 1987 using a dataset containing missing values, while the second, new model was developed on the same dataset but using modern data imputation and analytical methods. Missing data were imputed using multiple imputation by chained equations and a logistic regression model fitted to the imputed data, with survival or not as the outcome variable. The predictive ability of the model built on the imputed data was contrasted with the original prognostic model by testing them both on a second smaller but complete data set, collected contemporaneously with the development of the original model but from a different region of New Zealand. Sensitivity, specificity, accuracy, and cut point for the two models were calculated.</p><p><strong>Results: </strong>The original 1987 model had a slightly higher accuracy than that of the new one with a sensitivity of 0.85 (95% CI = 0.72-0.94) and a specificity of 0.82 (95% CI = 0.7-0.91), using a cut point for the probability of survival = 0.313.</p><p><strong>Conclusions: </strong>The original prognostic formula published by Clark <i>et al</i>. in 1987 performed as well as a modern model built on an imputed data set.</p><p><strong>Clinical relevance: </strong>The use of a prognostic test based on the Clark model should remain an important part of the clinical examination of downer cows by New Zealand veterinarians.<b>Abbreviations:</b> AUC: Area under the curve; AST: Aspartate transaminase activity; CK: Creatine phosphokinase activity; GAM: Generalised additive model; NSAID: Non-steroidal-anti-inflammatory drugs; PCV: Packed cell volume.</p>","PeriodicalId":19322,"journal":{"name":"New Zealand veterinary journal","volume":null,"pages":null},"PeriodicalIF":1.1000,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Downer cows: a reanalysis of an old data set.\",\"authors\":\"K E Lawrence, R G Clark, H V Henderson, K Govindaraju, C Balcomb\",\"doi\":\"10.1080/00480169.2022.2155262\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Aims: </strong>To compare the performance of two predictive models for the survival of downer cows.</p><p><strong>Methods: </strong>The first model had been developed in 1987 using a dataset containing missing values, while the second, new model was developed on the same dataset but using modern data imputation and analytical methods. Missing data were imputed using multiple imputation by chained equations and a logistic regression model fitted to the imputed data, with survival or not as the outcome variable. The predictive ability of the model built on the imputed data was contrasted with the original prognostic model by testing them both on a second smaller but complete data set, collected contemporaneously with the development of the original model but from a different region of New Zealand. Sensitivity, specificity, accuracy, and cut point for the two models were calculated.</p><p><strong>Results: </strong>The original 1987 model had a slightly higher accuracy than that of the new one with a sensitivity of 0.85 (95% CI = 0.72-0.94) and a specificity of 0.82 (95% CI = 0.7-0.91), using a cut point for the probability of survival = 0.313.</p><p><strong>Conclusions: </strong>The original prognostic formula published by Clark <i>et al</i>. in 1987 performed as well as a modern model built on an imputed data set.</p><p><strong>Clinical relevance: </strong>The use of a prognostic test based on the Clark model should remain an important part of the clinical examination of downer cows by New Zealand veterinarians.<b>Abbreviations:</b> AUC: Area under the curve; AST: Aspartate transaminase activity; CK: Creatine phosphokinase activity; GAM: Generalised additive model; NSAID: Non-steroidal-anti-inflammatory drugs; PCV: Packed cell volume.</p>\",\"PeriodicalId\":19322,\"journal\":{\"name\":\"New Zealand veterinary journal\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.1000,\"publicationDate\":\"2023-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"New Zealand veterinary journal\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://doi.org/10.1080/00480169.2022.2155262\",\"RegionNum\":4,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"VETERINARY SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"New Zealand veterinary journal","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1080/00480169.2022.2155262","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"VETERINARY SCIENCES","Score":null,"Total":0}
引用次数: 1
摘要
目的:比较两种预测模型对奶牛产仔存活率的影响。方法:第一个模型是在1987年使用一个包含缺失值的数据集建立的,第二个模型是在同一数据集上使用现代数据输入和分析方法建立的。缺失数据通过链式方程和拟合的逻辑回归模型进行多重输入,以生存与否为结果变量。建立在输入数据上的模型的预测能力与原始预测模型进行了对比,通过在第二个较小但完整的数据集上进行测试,该数据集与原始模型的开发同时收集,但来自新西兰的不同地区。计算两种模型的灵敏度、特异度、准确度和切点。结果:1987年原始模型的准确性略高于新模型,灵敏度为0.85 (95% CI = 0.72-0.94),特异性为0.82 (95% CI = 0.7-0.91),使用切点为生存概率= 0.313。结论:Clark等人于1987年发表的原始预测公式与建立在估算数据集上的现代模型表现一样好。临床相关性:使用基于克拉克模型的预后测试应该仍然是新西兰兽医对昏睡牛临床检查的重要组成部分。AUC:曲线下面积;AST:天冬氨酸转氨酶活性;CK:肌酸磷酸激酶活性;广义加性模型;非甾体抗炎药;PCV:填充细胞体积。
Aims: To compare the performance of two predictive models for the survival of downer cows.
Methods: The first model had been developed in 1987 using a dataset containing missing values, while the second, new model was developed on the same dataset but using modern data imputation and analytical methods. Missing data were imputed using multiple imputation by chained equations and a logistic regression model fitted to the imputed data, with survival or not as the outcome variable. The predictive ability of the model built on the imputed data was contrasted with the original prognostic model by testing them both on a second smaller but complete data set, collected contemporaneously with the development of the original model but from a different region of New Zealand. Sensitivity, specificity, accuracy, and cut point for the two models were calculated.
Results: The original 1987 model had a slightly higher accuracy than that of the new one with a sensitivity of 0.85 (95% CI = 0.72-0.94) and a specificity of 0.82 (95% CI = 0.7-0.91), using a cut point for the probability of survival = 0.313.
Conclusions: The original prognostic formula published by Clark et al. in 1987 performed as well as a modern model built on an imputed data set.
Clinical relevance: The use of a prognostic test based on the Clark model should remain an important part of the clinical examination of downer cows by New Zealand veterinarians.Abbreviations: AUC: Area under the curve; AST: Aspartate transaminase activity; CK: Creatine phosphokinase activity; GAM: Generalised additive model; NSAID: Non-steroidal-anti-inflammatory drugs; PCV: Packed cell volume.
期刊介绍:
The New Zealand Veterinary Journal (NZVJ) is an international journal publishing high quality peer-reviewed articles covering all aspects of veterinary science, including clinical practice, animal welfare and animal health.
The NZVJ publishes original research findings, clinical communications (including novel case reports and case series), rapid communications, correspondence and review articles, originating from New Zealand and internationally.
Topics should be relevant to, but not limited to, New Zealand veterinary and animal science communities, and include the disciplines of infectious disease, medicine, surgery and the health, management and welfare of production and companion animals, horses and New Zealand wildlife.
All submissions are expected to meet the highest ethical and welfare standards, as detailed in the Journal’s instructions for authors.