• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of dairy science >Short communication: Prediction of hyperketonemia in dairy cows in early lactation using on-farm cow data and net energy intake by partial least square discriminant analysis
【24h】

Short communication: Prediction of hyperketonemia in dairy cows in early lactation using on-farm cow data and net energy intake by partial least square discriminant analysis

机译：短期通信：使用农场母牛数据和净能量摄入的乳制奶牛在奶牛的高酮血症预测通过部分最小二乘判别分析

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The objectives of this study were (1) to evaluateif hyperketonemia in dairy cows (defined as plasmaβ-hydroxybutyrate ≥1.0 mmol/L) can be predicted usingon-farm cow data either in current or previous lactationweek, and (2) to study if adding individual netenergy intake (NEI) can improve the predictive abilityof the model. Plasma β-hydroxybutyrate concentration,on-farm cow data (milk yield, percentage of fat, proteinand lactose, fat- and protein-corrected milk yield, bodyweight, body weight change, dry period length, parity,and somatic cell count), and NEI of 424 individualcows were available weekly through lactation wk 1 to 5postpartum. To predict hyperketonemia in dairy cows,models were first trained by partial least square discriminantanalysis, using on-farm cow data in the sameor previous lactation week. Second, NEI was includedin models to evaluate the improvement of the predictabilityof the models. Through leave-one trial-outcross-validation, models were evaluated by accuracy(the ratio of the sum of true positive and true negative),sensitivity (68.2% to 84.9%), specificity (61.5% to98.7%), positive predictive value (57.7% to 98.7%), andnegative predictive value (66.2% to 86.1%) to predicthyperketonemia of dairy cows. Through lactation wk1 to 5, the accuracy to predict hyperketonemia usingdata in the same week was 64.4% to 85.5% (on-farmcow data only), 66.1% to 87.0% (model including NEI),and using data in the previous week was 58.5% to82.0% (on-farm cow data only), 59.7% to 85.1% (modelincluding NEI). An improvement of the accuracy of themodel due to including NEI ranged among lactationweeks from 1.0% to 4.4% when using data in the samelactation week and 0.2% to 6.6% when using data in theprevious lactation week. In conclusion, trained modelsvia partial least square discriminant analysis havepotential to predict hyperketonemia in dairy cows notonly using data in the current lactation week, but alsousing data in the previous lactation week. Net energyintake can improve the accuracy of the model, but onlyto a limited extent. Besides NEI, body weight, bodyweight change, milk fat, and protein content were importantvariables to predict hyperketonemia, but theirrank of importance differed across lactation weeks.
机译：本研究的目标是（1）评估如果奶牛的高蛋白质血症（定义为等离子体可以使用β-羟基丁酸≥1.0mmol/ l）在当前或以前的哺乳期间的农场牛数据一周，和（2）如果添加单个网能量摄入（NEI）可以提高预测能力模型。血浆β-羟丁酯浓度，农场牛数据（牛奶产量，脂肪百分比，蛋白质和乳糖，脂肪和蛋白质矫正乳屈服，身体体重，体重变化，干燥期长，奇偶校验，和体细胞计数），424个个体的Nei奶牛通过哺乳期WK 1至5每周提供产后。预测奶牛的高蛋白质血症，模型是由部分最小二乘判别训练的分析，使用农场牛数据相同或以前的哺乳期。其次，内历被包括在内在模型中，以评估可预测性的提高模型。通过休假 - 一个试验交叉验证，模型通过准确性评估（真正正负和真实负数的比率），敏感度（68.2％至84.9％），特异性（61.5％）98.7％），阳性预测值（57.7％至98.7％），和否定预测值（66.2％至86.1％）预测奶牛的高钾血症。通过哺乳酸红克1至5，预测高酮血症的准确性同一周的数据为64.4％至85.5％（农场仅牛数据），66.1％至87.0％（包括NEI），并使用前一周的数据为58.5％82.0％（仅限农场牛数据），59.7％至85.1％（模型包括Nei）。改善了准确性由于包括Nei的模型在哺乳期间在使用数据时，几周从1.0％到4.4％使用数据时，哺乳期和0.2％至6.6％以前的哺乳期。总之，训练有素的型号通过部分最小二乘判别分析潜在的奶牛母牛预测患者的潜力只有在当前哺乳期的数据中只使用数据，还要使用上一个哺乳期的数据。净能量摄入量可以提高模型的准确性，但只能提高模型的准确性有限的程度。除了Nei，体重，身体体重变化，乳脂和蛋白质含量很重要变量预测高酮血症，但他们的哺乳期的重要性差异不同。

著录项

  • 来源
    《Journal of dairy science》 |2020年第7期|6576-6582|共7页
  • 作者

    Wei Xu; Edoardo Saccenti; Jacques Vervoort; Bas Kemp; Rupert M. Bruckmaier; Ariette T. M. van Knegsel;

  • 作者单位

    Adaptation Physiology group Department of Animal Sciences Wageningen University and Research PO Box 338 6700 AH Wageningen the Netherlands Laboratory of Biochemistry Wageningen University and Research PO Box 338 6700 AH Wageningen the Netherlands;

    Laboratory of Systems and Synthetic Biology Wageningen University and Research Stippeneng 4 6708 WE Wageningen the Netherlands;

    Laboratory of Biochemistry Wageningen University and Research PO Box 338 6700 AH Wageningen the Netherlands;

    Adaptation Physiology group Department of Animal Sciences Wageningen University and Research PO Box 338 6700 AH Wageningen the Netherlands;

    Veterinary Physiology Vetsuisse Faculty University of Bern Bremgartenstrasse 109a CH-3001 Bern Switzerland;

    Adaptation Physiology group Department of Animal Sciences Wageningen University and Research PO Box 338 6700 AH Wageningen the Netherlands;

  • 收录信息 美国《科学引文索引》(SCI);美国《生物学医学文摘》(MEDLINE);美国《化学文摘》(CA);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    partial least square discriminant analysis; metabolic status; subclinical ketosis;

    机译：部分最小二乘判别分析;代谢地位;亚临床酮化;

相似文献

  • 外文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号