Estimating the individual stillborn rate from easy-to-collect sow data on farm: an application of the bayesian network model

Charlotte Teixeira Costa; Gwenaël Boulbria; Christophe Dutertre; Céline Chevance; Théo Nicolazo; Valérie Normand; Justine Jeusselin; Arnaud Lebret

doi:10.1186/s40813-024-00395-5

Estimating the individual stillborn rate from easy-to-collect sow data on farm: an application of the bayesian network model

Porcine Health Manag. 2024 Oct 16;10(1):42. doi: 10.1186/s40813-024-00395-5.

Authors

Charlotte Teixeira Costa¹, Gwenaël Boulbria², Christophe Dutertre³, Céline Chevance², Théo Nicolazo², Valérie Normand², Justine Jeusselin², Arnaud Lebret²

Affiliations

¹ Rezoolution, ZA de Gohélève, Noyal-Pontivy, 56920, France. c.teixeira-costa@rezoolution.fr.
² Rezoolution, ZA de Gohélève, Noyal-Pontivy, 56920, France.
³ HumanoIA, 338 route de Philondenx, Cabidos, 64410, France.

Abstract

Background: A high number of stillborn piglets has a negative impact on production and animal welfare. It is an important contributor to piglet mortality around farrowing and continues to rise with the increase of prolificacy. The objective of this study was to build a predictive model of the stillborn rate.

Results: This study was performed on two farrow-to-finish farms and one farrow-to-wean farm located in Brittany, France. At each farm, the number of total born (TB), born alive (BA), stillborn piglets (S), the same data at the previous farrowing (TB_{n- 1}, BA_{n- 1} and S_{n- 1}), backfat thickness just before farrowing and at previous weaning and parity rank were recorded in our dataset of 3686 farrowings. Bayesian networks were used as an integrated modelling approach to investigate risk factors associated with stillbirth using BayesiaLab^® software. Our results suggest the validity of a hybrid model to predict the percentage of stillborn piglets. Three significant risk factors were identified by the model: parity rank (percentage of total mutual information: MI = 64%), S_{n- 1} (MI = 25%) and TB_{n- 1} (MI = 11%). Additionally, backfat thickness just before farrowing was also identified for sows of parity five or more (MI = 0.4%). In practice, under optimal conditions (i.e., low parity rank, less than 8% of stillborn piglets, and a prolificacy lower than 14 piglets at the previous farrowing), our model predicted a stillborn rate almost halved, from 6.5% (mean risk of our dataset) to 3.5% for a sow at the next farrowing. In contrast, in older sows with a backfat thickness less than 15 mm, more than 15% of stillborn and a prolificacy greater than 18 piglets at the previous farrowing, the risk is multiplied by 2.5 from 6.5 to 15.7%.

Conclusion: Our results highlight the impact of parity, previous prolificacy and stillborn rate on the probability of stillborn. Moreover, the importance of backfat thickness, especially in old sows, must be considered. This information can help farmers classify and manage sows according to their risk of giving birth to stillborn piglets.

Keywords: Bayesian networks; Decision-making tool; Farrowing; Predictive model; Sow; Stillborn piglets.