Machine learning approaches to predict and detect early-onset of digital dermatitis in dairy cows using sensor data.

The present study aimed to employ machine learning algorithms based on sensor behavior data for (1) early-onset detection of digital dermatitis (DD) and (2) DD prediction in dairy cows. Our machine learning model, which was based on the Tree-Based Pipeline Optimization Tool (TPOT) automatic machine learning method, for DD detection on day 0 of the appearance of the clinical signs has reached an accuracy of 79% on the test set, while the model for the prediction of DD 2 days prior to the appearance of the first clinical signs, which was a combination of K-means and TPOT, has reached an accuracy of 64%. The proposed machine learning models have the potential to help achieve a real-time automated tool for monitoring and diagnosing DD in lactating dairy cows based on sensor data in conventional dairy barn environments. Our results suggest that alterations in behavioral patterns can be used as inputs in an early warning system for herd management in order to detect variances in the health and wellbeing of individual cows.

Differential Strain-dependent Ovarian and Metabolic Responses in a Mouse Model of PCOS.

Several mouse models have been developed to study polycystic ovarian syndrome (PCOS), a leading cause of infertility in women. Treatment of mice with DHT for 90 days causes ovarian and metabolic phenotypes similar to women with PCOS. We used this 90-day DHT treatment paradigm to investigate the variable incidence and heterogeneity in 2 inbred mouse strains, NOD/ShiLtJ and 129S1/SvlmJ. NOD mice naturally develop type 1 diabetes, and recent meta-analysis found increased androgen excess and PCOS in women with type 1 diabetes. The 129S1 mice are commonly used in genetic manipulations. Both NOD and 129S1 DHT-treated mice had early vaginal opening, increased anogenital distance, and altered estrus cycles compared with control animals. Additionally, both NOD and 129S1 mice had reduced numbers of corpora lutea after DHT exposure, whereas NOD mice had decreased numbers of preantral follicles and 129S1 mice had reduced numbers of small antral follicles. NOD mice had increased body weight, decreased white adipocyte size, and improved glucose sensitivity in response to DHT, whereas 129S1 mice had increased body weight and white adipocyte size. NOD mice had increased expression of Adiponectin, Cidea, Srebp1a, and Srebp1b and 129S1 mice had decreased Pparg in the white adipose tissues, whereas both NOD and 129S1 mice had increased expression of Glut4 and Prdm16, suggesting DHT may differentially affect glucose transport, thermogenesis, and lipid storage in white adipose tissue. DHT causes different ovarian and metabolic responses in NOD and 129S1 mice, suggesting that strain differences may allow further elucidation of genetic contributions to PCOS.