DairyNZ Ltd., Newstead, Hamilton 3240, New Zealand.
J Dairy Sci. 2012 Jun;95(6):3045-56. doi: 10.3168/jds.2011-4934.
This study tested the hypothesis that a commercially available system for detecting estrus based on cow activity would perform similarly to that of typical, visual assessment of mounting indicators placed on the tail head of the cow. The hypothesis was applied to a large, pasture-grazed, seasonal-calving dairy herd, and the technology was tested as a stand-alone system. One of 2 types of commercially available collar-mounted activity meters was fitted to 635 cows, and the activity data collected during the 37-d artificial breeding period were analyzed. The first collar-mounted activity meter monitored activity only (AO collars), whereas the second meter measured activity and rumination characteristics (AR collars). Only activity data were used in the current study. Activity-based estrus alerts were initially identified using the default activity threshold value recommended by the manufacturer, but a range of activity threshold values was then analyzed to determine their effect on estrus detection performance. Milk progesterone data and insemination records were used to identify gold standard positive (n = 835) and negative (n = 22,660) estrus dates, to which activity alerts were compared. Visual assessment of mounting indicators resulted in a manual detection performance of 91.3% sensitivity (SN), 99.8% specificity (SP), and 94.5% positive predictive value (PPV). The AR collars achieved 76.9, 99.4, and 82.4% for SN, SP, and PPV, whereas the AO collars achieved 62.4, 99.3, and 76.6% for SN, SP, and PPV, respectively. The observed performance of the activity systems may be underestimated due to test design and applied assumptions, including determining the date of estrus. Lowering the activity threshold from the default value improved sensitivity but the number of false positive alerts was considered to become unmanageable from a practical perspective as sensitivity reached peak values. Time window analysis, receiver operating characteristic curves, and curves of SN and PPV were found to be useful in the analysis and interpretation of results. They generate relevant performance data that allow for meaningful comparisons between similar studies. Although the 2 activity systems tested did not perform to the high level of manual estrus detection found in this study, the potential exists for these systems to be a valuable tool on farms with lower estrus detection performance or for farmers managing larger herds.
本研究检验了这样一个假设，即基于奶牛活动的商业化发情检测系统在检测奶牛尾巴上安装的典型发情指示物方面的性能与传统的视觉评估相似。该假设适用于一个大型的、牧场放牧的、季节性产犊的奶牛场，并且该技术被作为一个独立的系统进行了测试。两种市售的颈圈式活动计中的一种被安装在 635 头奶牛身上，在 37 天的人工授精期内收集活动数据，并进行分析。第一种颈圈式活动计只监测活动（AO 颈圈），而第二种计则测量活动和反刍特征（AR 颈圈）。本研究仅使用了活动数据。最初使用制造商推荐的默认活动阈值来识别基于活动的发情警报，但随后分析了一系列活动阈值，以确定它们对发情检测性能的影响。牛奶孕酮数据和授精记录被用于确定金标准的发情日期（阳性：n = 835，阴性：n = 22660），并将其与活动警报进行比较。安装在奶牛尾巴上的发情指示物的手动检测性能为 91.3%的敏感性（SN）、99.8%的特异性（SP）和 94.5%的阳性预测值（PPV）。AR 颈圈的 SN、SP 和 PPV 分别为 76.9%、99.4%和 82.4%，AO 颈圈的 SN、SP 和 PPV 分别为 62.4%、99.3%和 76.6%。由于测试设计和应用的假设，包括确定发情日期，活动系统的观察性能可能被低估。从默认值降低活动阈值可以提高敏感性，但从实际角度来看，假阳性警报的数量可能变得难以管理，因为敏感性达到峰值。时间窗口分析、接收者操作特征曲线以及 SN 和 PPV 曲线被发现对分析和解释结果非常有用。它们生成了相关的性能数据，允许在类似的研究之间进行有意义的比较。尽管测试的 2 种活动系统的性能没有达到本研究中手动发情检测的高水平，但这些系统有可能成为发情检测性能较低的农场或管理更大牛群的农民的有价值的工具。
