Predictive models for metritis cure using farm-collected data, metabolic and inflammation biomarkers, and hemogram variables measured at diagnosis

Our objective was to evaluate the accuracy of predictive models for metritis spontaneous cure (SC) and cure among ceftiofur-treated cows using farm collected data only, and with the addition of hemogram variables and circulating concentration of metabolites, minerals, and biomarkers of inflammation measured at time of diagnosis. Data related to parity, calving related issues, body condition score (BCS), rectal temperature (RT), and days in milk (DIM) at metritis diagnosis were collected from a randomized clinical trial that included 412 metritic cows from 4 herds in TX, CA, and FL. Metritis was defined as the presence of red-brownish, watery, and fetid vaginal discharge, while cure was defined as the absence of metritis 14 d after initial diagnosis. Cows were randomly allocated to receive systemic ceftiofur therapy (2 subcutaneous doses of 6.6 mg/kg of ceftiofur crystalline-free acid on the day of diagnosis and 3 d later; CEF) or to remain untreated (CON). At enrollment (day of metritis diagnosis), blood samples were collected and submitted to cell blood count (CBC) and processed for the measurement of 13 minerals and biomarkers of metabolism and inflammation (BM). Univariable analysis to evaluate the association of farm collected data and blood assessed variables with metritis cure were performed, and variables with P ≤ 0.20 were offered to multivariable logistic regression models and retained if P ≤ 0.15. The area under the curve (AUC) for models predicting SC using farm data only and farm + BM, was 0.70 and 0.76 respectively. Cell blood count variables were not retained in the models for SC. For models predicting cure among CEF cows, the AUC was 0.75, 0.77, 0.80, and 0.80 for models using farm data only, farm + CBC, farm + BM, and farm + CBC + BM, respectively. Predictive models of metritis cure had fair accuracy, with SC models being less accurate than models predictive of cure among CEF cows. Additionally, adding BM variables marginally improved the accuracy of models using farm collected data, while CBC data did not improve the accuracy of predictive models.

Integration of statistical inferences and machine learning algorithms for prediction of metritis cure in dairy cows

The study's objectives were to identify cow-level and environmental factors associated with metritis cure to predict metritis cure using traditional statistics and machine learning algorithms. The data set used was from a previous study comparing the efficacy of different therapies and self-cure for metritis. Metritis was defined as fetid, watery, reddish-brownish discharge, with or without fever. Cure was defined as an absence of metritis signs 12 d after diagnosis. Cows were randomly allocated to receive a subcutaneous injection of 6.6 mg/kg of ceftiofur crystalline-free acid (Excede, Zoetis) at the day of diagnosis and 3 d later (n = 275); and no treatment at the time of metritis diagnosis (n = 275). The variables days in milk (DIM) at metritis diagnosis, treatment, season of the metritis diagnosis, month of metritis diagnostic, number of lactation, parity, calving score, dystocia, retained fetal membranes, body condition score at d 5 postpartum, vulvovaginal laceration score, the rectal temperature at the metritis diagnosis, fever at diagnosis, milk production from the day before to metritis diagnosis, and milk production slope up to 5, 7, and 9 DIM were offered to univariate logistic regression. Variables included in the multivariable logistic regression model were selected from the univariate analysis according to P-value. Variables were offered to the model to assess the association between these factors and metritis cure. Additionally, the univariate logistic regression variables were offered to a recursive feature elimination to find the optimal subset of features for a machine learning algorithms analysis. Cows without vulvovaginal laceration had 1.91 higher odds of curing of metritis than cows with vulvovaginal laceration. Cows that developed metritis at >7 DIM had 2.09 higher odds of being cured than cows that developed metritis at ≤7 DIM. For rectal temperature, each degree Celsius above 39.4°C led to lower odds to be cured than cows with rectal temperature ≤39.4°C. Furthermore, milk production slope and milk production difference from the day before to the metritis diagnosis were essential variables to predict metritis cure. Cows that had reduced milk production from the day before to the metritis diagnosis had lower odds to be cured than cows with moderate milk production increase. The results from the multivariable logistic regression and receiver operating characteristic analysis indicated that cows developing metritis at >7 DIM, with increase in milk production, and with a rectal temperature ≤39.40°C had increased likelihood of cure of metritis with an accuracy of 75%. The machine learning analysis showed that in addition to these variables, calving-related disorders, season, and month of metritis event were needed to predict whether the cow will cure or not from metritis with an accuracy ≥70% and F1 score (harmonic mean between precision and recall) ≥0.78. Although machine learning algorithms are acknowledged as powerful tools for predictive classification, the current study was unable to replicate its potential benefits. More research is needed to optimize predictive models of metritis cure.