Hostname: page-component-78c5997874-94fs2 Total loading time: 0 Render date: 2024-11-17T18:11:57.849Z Has data issue: false hasContentIssue false
  • English
  • Français

Towards practical application of sensors for monitoring animal health; design and validation of a model to detect ketosis

Published online by Cambridge University Press:  19 May 2017

Machteld Steensels ,
Ephraim Maltz ,
Claudia Bahr ,
Daniel Berckmans ,
Aharon Antler  and
Ilan Halachmi
Machteld Steensels
Affiliation:
Institute of Agricultural Engineering – Agricultural Research Organization (ARO) – The Volcani Center, PO Box 6, Bet-Dagan 50250, Israel Department of Biosystems (BIOSYST), KU Leuven, Kasteelpark Arenberg 30 – bus 2456, 3001 Heverlee, Belgium
Ephraim Maltz
Affiliation:
Institute of Agricultural Engineering – Agricultural Research Organization (ARO) – The Volcani Center, PO Box 6, Bet-Dagan 50250, Israel
Claudia Bahr
Affiliation:
Department of Biosystems (BIOSYST), KU Leuven, Kasteelpark Arenberg 30 – bus 2456, 3001 Heverlee, Belgium
Daniel Berckmans
Affiliation:
Department of Biosystems (BIOSYST), KU Leuven, Kasteelpark Arenberg 30 – bus 2456, 3001 Heverlee, Belgium
Aharon Antler
Affiliation:
Institute of Agricultural Engineering – Agricultural Research Organization (ARO) – The Volcani Center, PO Box 6, Bet-Dagan 50250, Israel
Ilan Halachmi*
Affiliation:
Institute of Agricultural Engineering – Agricultural Research Organization (ARO) – The Volcani Center, PO Box 6, Bet-Dagan 50250, Israel
*
*For correspondence; e-mail: halachmi@volcani.agri.gov.il
Get access Rights & Permissions [Opens in a new window]

Abstract

The objective of this study was to design and validate a mathematical model to detect post-calving ketosis. The validation was conducted in four commercial dairy farms in Israel, on a total of 706 multiparous Holstein dairy cows: 203 cows clinically diagnosed with ketosis and 503 healthy cows. A logistic binary regression model was developed, where the dependent variable is categorical (healthy/diseased) and a set of explanatory variables were measured with existing commercial sensors: rumination duration, activity and milk yield of each individual cow. In a first validation step (within-farm), the model was calibrated on the database of each farm separately. Two thirds of the sick cows and an equal number of healthy cows were randomly selected for model validation. The remaining one third of the cows, which did not participate in the model validation, were used for model calibration. In order to overcome the random selection effect, this procedure was repeated 100 times. In a second (between-farms) validation step, the model was calibrated on one farm and validated on another farm. Within-farm accuracy, ranging from 74 to 79%, was higher than between-farm accuracy, ranging from 49 to 72%, in all farms. The within-farm sensitivities ranged from 78 to 90%, and specificities ranged from 71 to 74%. The between-farms sensitivities ranged from 65 to 95%. The developed model can be improved in future research, by employing other variables that can be added; or by exploring other models to achieve greater sensitivity and specificity.

Keywords

Dairy cowketosissensorsrumination durationactivitymilk yieldlogistic regression model
Type
Research Article
Information
Journal of Dairy Research , Volume 84 , Issue 2 , May 2017 , pp. 139 - 145
Copyright
Copyright © Proprietors of Journal of Dairy Research 2017 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Bareille, N, Beaudeau, F, Billon, S, Robert, A & Faverdin, P 2003 Effects of health disorders on feed intake and milk production in dairy cows. Livestock Production Science 83 53–62 Google Scholar
DeVries, TJ, Beauchemin, KA, Dohme, F & Schwartzkopf-Genswein, KS 2009 Repeated ruminal acidosis challenges in lactating dairy cows at high and low risk for developing acidosis: feeding, ruminating and lying behavior. Journal of Dairy Science 92 5067–5078 Google Scholar
Dohoo, IR & Martin, SW 1984 Subclinical ketosis – prevalence and associations with production and disease. Canadian Journal of Comparative Medicine-Revue Canadienne De Medecine Comparee 48 1–5 Google ScholarPubMed
Duffield, TF, Kelton, DF, Leslie, KE, Lissemore, KD & Lumsden, JH 1997 Use of test day milk fat and milk protein to detect subclinical ketosis in dairy cattle in Ontario. Canadian Veterinary Journal-Revue Veterinaire Canadienne 38 713–718 Google ScholarPubMed
Edwards, JL & Tozer, PR 2004 Using activity and milk yield as predictors of fresh cow disorders. Journal of Dairy Science 87 524–531 Google Scholar
Forslund, KB, Ljungvall, OA & Jones, BV 2010 Low cortisol levels in blood from dairy cows with ketosis: a field study. Acta Veterinaria Scandinavica 52 31–36 Google Scholar
Gillund, P, Reksen, O, Grohn, YT & Karlberg, K 2001 Body condition related to ketosis and reproductive performance in Norwegian dairy cows. Journal of Dairy Science 84 1390–1396 Google Scholar
Hansen, SW, Norgaard, P, Pedersen, LJ, Jorgensen, RJ, Mellau, LSB & Enemark, JD 2003 The effect of subclinical hypocalcaemia induced by Na2EDTA on the feed intake and chewing activity of dairy cows. Veterinary Research Communications 27 193–205 Google Scholar
Hosmer, DW & Lemeshow, S 2000 Applied Logistic Regression. New York, NY, USA: John Wiley & Sons Google Scholar
Huzzey, JM, Veira, DM, Weary, DM & von Keyserlingk, MAG 2007 Prepartum behavior and dry matter intake identify dairy cows at risk for metritis. Journal of Dairy Science 90 3220–3233 Google Scholar
Kahn, CM & Line, SE 2010 Metabolic disorders. In Merck Veterinary Manual, 10th edition, Kahn, CM & LIne, SE (ed), pp. 897–938. Merck & Co. Inc, New Jersey, USA Google Scholar
Krogh, MA, Toft, N & Enevoldsen, C 2011 Latent class evaluation of a milk test, a urine test, and the fat-to-protein percentage ratio in milk to diagnose ketosis in dairy cows. Journal of Dairy Science 94 2360–2367 Google Scholar
Lark, RM, Nielsen, BL & Mottram, TT 1999 A time series model of daily milk yields and its possible use for detection of a disease (ketosis). Animal Science 69 573–582 Google Scholar
LeBlanc, SJ, Leslie, KE & Duffield, TF 2005 Metabolic predictors of displaced abomasum in dairy cattle. Journal of Dairy Science 88 159–170 Google Scholar
Maplesden, DC 1954 Propylene glycol in the treatment of ketosis. Canadian Journal of Comparative Medicine and Veterinary Science 18 287 Google Scholar
Nielsen, NI & Ingvartsen, KL 2004 Propylene glycol for dairy cows – a review of the metabolism of propylene glycol and its effects on physiological parameters, feed intake, milk production and risk of ketosis. Animal Feed Science and Technology 115 191–213 CrossRefGoogle Scholar
Nielsen, NI, Friggens, NC, Chagunda, MGG & Ingvartsen, KL 2005 Predicting risk of ketosis in dairy cows using in-line measurements of beta-hydroxybutyrate: a biological model. Journal of Dairy Science 88 2441–2453 Google Scholar
Nir (Markusfeld), O 2003 What are production diseases, and how do we manage them. Acta Veterinaria Scandinavica Suppl. 98 21–32 Google Scholar
NRC 2001 Nutrient Requirements of Dairy Cattle. NRC, Washington, DC Google Scholar
Rajala-Schultz, PJ, Grohn, YT & McCulloch, CE 1999 Effects of milk fever, ketosis, and lameness on milk yield in dairy cows. Journal of Dairy Science 82 288–294 Google Scholar
Simensen, E, Halse, K, Gillund, P & Lutnaes, B 1990 Ketosis treatment and milk yield in dairy cows related to milk acetoacetate levels. Acta Veterinaria Scandinavica 31 433–440 Google Scholar
Steensels, M, Bahr, C, Berckmans, D, Halachmi, I, Antler, A & Maltz, E 2012 Lying patterns of high producing healthy dairy cows after calving in commercial herds as affected by age, environmental conditions and production. Applied Animal Behaviour Science 136 88–95 CrossRefGoogle Scholar
Steensels, M, Antler, A, Bahr, C, Berckmans, D, Maltz, E & Halachmi, I 2016 A decision-tree model to detect post-calving diseases based on rumination, activity, milk yield, body weight and voluntary visits to the milking robot. Animal 10 1493–1500 Google Scholar
Steensels, M, Maltz, E, Bahr, C, Berckmans, D, Antler, A & Halachmi, I 2017 Towards practical application of rumination duration and activity data; the effect of post-calving health problems on rumination duration, activity and milk yield. Journal of Dairy Research 84 Google Scholar
Stengärde, L, Hultgren, J, Tråvén, M, Holtenius, K & Emanuelson, U 2012 Risk factors for displaced abomasum or ketosis in Swedish dairy herds. Preventive Veterinary Medicine 103 280–286 Google Scholar
Tatone, EH 2016 A multi-faceted approach to the exploration of ketosis in dairy cattle: detection, treatment & risk factors. PhD Thesis, University of Guelph, accessed at https://atrium.lib.uoguelph.ca/xmlui/handle/10214/9765 Google Scholar
Tolkamp, BJ, Haskell, MJ, Langford, FM, Roberts, DJ & Morgan, CA 2010 Are cows more likely to lie down the longer they stand? Applied Animal Behaviour Science 124 1–10 Google Scholar
Veenhuizen, JJ, Drackley, JK, Richard, MJ, Sanderson, TP, Miller, LD & Young, JW 1991 Metabolic changes in blood and liver during development and early treatment of experimental fatty liver and ketosis in cows. Journal of Dairy Science 74 4238–4253 Google Scholar
Walsh, RB, Walton, JS, Kelton, DF, LeBlanc, SJ, Leslie, KE & Duffield, TF 2007 The effect of subclinical ketosis in early lactation on reproductive performance of postpartum dairy cows. Journal of Dairy Science 90 2788–2796 Google Scholar