Evaluation of applying statistical process control techniques to daily average feeding behaviors to detect disease in automatically fed group-housed preweaned dairy calves

Whitney A Knauer, Sandra M Godden, A. Dietrich, D. M. Hawkins, R. E. James

Research output: Contribution to journalArticlepeer-review

23 Scopus citations


Group housing and computerized feeding of preweaned dairy calves are gaining in popularity among dairy producers, yet disease detection remains a challenge for this management system. The aim of this study was to investigate the application of statistical process control charting techniques to daily average feeding behavior to predict and detect illness and to describe the diagnostic test characteristics of using this technique to find a sick calf compared with detection by calf personnel. This prospective cross-sectional study was conducted on 10 farms in Minnesota (n = 4) and Virginia (n = 6) utilizing group housing and computerized feeding from February until October 2014. Calves were enrolled upon entrance to the group pen. Calf personnel recorded morbidity and mortality events. Farms were visited either every week (MN) or every other week (VA) to collect calf enrollment data, computer-derived feeding behavior data, and calf personnel–recorded calf morbidity and mortality. Standardized self-starting cumulative sum (CUSUM) charts were generated for each calf for each daily average feeding behavior, including drinking speed (mL/min), milk consumption (L/d), and visits to the feeder without a milk meal (no.). A testing subset of 352 calves (176 treated, 176 healthy) was first used to find CUSUM chart parameters that provided the highest diagnostic test sensitivity and best signal timing, which were then applied to all calves (n = 1,052). Generalized estimating equations were used to estimate the diagnostic test characteristics of a single negative mean CUSUM chart signal to detect a sick calf for a single feeding behavior. Combinations of feeding behavior signals were also explored. Single signals and combinations of signals that included drinking speed provided the most sensitive and timely signal, finding a sick calf up to an average (±SE) of 3.1 ± 8.8 d before calf personnel. However, there was no clear advantage to using CUSUM charting over calf observation for any one feeding behavior or combination of feeding behaviors when predictive values were considered. The results of this study suggest that, for the feeding behaviors monitored, the use of CUSUM control charts does not provide sufficient sensitivity or predictive values to detect a sick calf in a timely manner compared with calf personnel. This approach to examining daily average feeding behaviors cannot take the place of careful daily observation.

Original languageEnglish (US)
Pages (from-to)8135-8145
Number of pages11
JournalJournal of Dairy Science
Issue number9
StatePublished - Sep 2018

Bibliographical note

Funding Information:
We thank our collaborator dairy farms for their willingness to participate in this project as well as Aaron Rendahl (College of Veterinary Medicine, University of Minnesota, St. Paul) and Yiwen Sun (Department of Statistics, University of Minnesota, Minneapolis) for their help with data management and coding of the control charting. The field work in Minnesota was funded by the University of Minnesota College of Veterinary Medicine Population Systems Signature Program. The Virginia component of this study was funded through the Virginia State Dairymen's Association and Land O'Lakes Animal Milk Products (Shoreview, MN). Salary support for Whitney Knauer was provided by USDA (Washington, DC) grant no. 2012-38420-30221.

Publisher Copyright:
© 2018 American Dairy Science Association


  • calf health
  • feeding behavior
  • group housing
  • statistical process control


Dive into the research topics of 'Evaluation of applying statistical process control techniques to daily average feeding behaviors to detect disease in automatically fed group-housed preweaned dairy calves'. Together they form a unique fingerprint.

Cite this