Statistical and machine learning approaches to describe factors affecting pre-weaning mortality of piglets

Authors: RAHMAN, TOWFIQUR - University Of Nebraska; BROWN-BRANDL, TAMI - University Of Nebraska; Rohrer, Gary; SHI, YEYIN - University Of Nebraska; SHARMA, S. RAJ - University Of Nebraska; MANTHENA, VAMSI - University Of Nebraska

Submitted to: Translational Animal Science
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 10/3/2023
Publication Date: N/A
Citation: N/A

Interpretive Summary: High pre-weaning mortality (PWM) rates for piglets are a significant concern for the worldwide pork industries. This issue is an economic loss for producers and a well-being concern for the industry. Factors contributing to PWM include number of mummies and stillborns, health condition of sows and piglets, environmental factors, congenital abnormalities, and overlaying by sow. Understanding which factors contribute the most to PWM will enable producers and scientists to focus their efforts in specific areas to improve production efficiency. The present study focuses on determining the effects of different factors on the occurrence of PWM and predicting PWM using machine learning models. Data were collected from 1,982 litters located at the US Meat Animal Research Center (USMARC). Production records for each litter included parity, season, location of the pen, gestation length, litter line (Yorkshire, Landrace sired), health records, number of piglets stillborn, piglets born alive, litter size, and mean birth weight. On average, the mean birth weight was 1.44 kg, mortality was 16.1% and overlay percentage was 6.2%. There were no significant effects found for season and location in a room on PWM. The effects for litter lines were significantly different for PWM and percent overlays. Landrace-sired piglets have 17.1% PWM and 6.5% overlays which is greater than Yorkshire-sired PWM of 15.7% and overlay of 6.4%. PWM increased with greater parity with fourth parity sows having PWM of 18.2%. Low birth weight and greater litter size significantly increased mortality. Most important factors to predict PWM were litter size, mean birth weight, number of health diagnoses, gestation length and parity. Considering the challenge to reduce pre-weaning mortality and limited studies exploring multiple major contributing factors, this study is valuable for creating a greater understanding of the inter-related factors contributing to PWM in commercial swine production. Increasing mean birth weight and gestation length while maintaining high health standards are important areas of research that should be conducted to reduce piglet mortality in commercial swine production. In addition, greater oversight of older parity sows from birth until 3 days post-farrowing could improve survival of young piglets.

Technical Abstract: High pre-weaning mortality (PWM) rates for piglets are a significant concern for the worldwide pork industries. This issue is an economic loss for producers and a well-being concern for the industry. There are factors contributing to PWM, including number of mummies and stillborns, health condition of sows and piglets, environmental factors, congenital abnormalities, and overlaying by sow. The present study focuses on determining the effects of different factors on the occurrence of PWM and predicting PWM using machine learning models. Data were collected from 2016-2021 on 1,982 litters located at the U.S. Meat Animal Research Center (USMARC). Sows were housed in a farrowing building with 3 separate rooms, each with 20 farrowing crates with care provided by trained animal caretakers. Production records for each litters included parity, season, location of the pen, gestation length, litter lines (Yorkshire, Landrace sired), health records, and number of piglets stillborn, born alive, litter size, and mean birth weight. A statistical model was used to determine the effect of piglet mortality for different production parameters. In addition, three different machine learning models were used to predict PWM and overlays including all listed contributing factors. On average, the mean birth weight was 1.44 kg, mortality was 16.1% and overlay percentage was 6.2%. There were no significant effects found for seasonal variation and location in a room on PWM. The effects for litter lines were significantly different for PWM and percent overlays. Landrace-sired piglets have 17.1% PWM and 6.5% overlays which is greater than Yorkshire-sired PWM of 15.7% and overlay of 6.4%. Among different parities, PWM increased with greater parity. Third and fourth parity sows had higher PWM of 16.8% and 18.2%, respectively. Similarly, low birth weight and greater litter size significantly increased mortality. The best machine learning model fit the dataset well with a correlation coefficient between observed PWM and predicted PWM of 0.94. Most important factors for PWM in the machine learning model were litter size, mean birth weight, number of health diagnoses, gestation length and parity. For overlays, important factors were parity, litter size and mean birth weight. Considering the challenge to reduce pre-weaning mortality and limited studies exploring multiple major contributing factors, this study is valuable for creating a greater understanding of the inter-related factors contributing to PWM in commercial swine production.