Reticuloruminal Motility Monitoring for the Prediction of Peripartal Hypocalcemia in Cattle

TL;DR

This study explores using wireless sensors in cows' rumens to predict hypocalcemia risk before or after calving, showing that sensor data can predict the condition better than traditional methods.

Contribution

The study introduces a deep learning model using reticuloruminal sensor data to predict hypocalcemia with higher accuracy than simple thresholds.

Findings

Cows with low calcium levels before calving had reduced rumination times compared to healthy cows.

A deep learning model trained on external data achieved 83.2% sensitivity and 98.2% specificity in predicting hypocalcemia.

Sensor-based prediction outperformed traditional methods like rumination time thresholds.

Abstract

Currently, cow-level prediction methods of hypocalcemia risk, which are based on laboratory results, have only low to moderate predictive values. The present study explores whether data measured by a reticuloruminal bolus wireless sensor may be used for the prediction of hypocalcemia risk before or close after calving. Cattle fitted with rumen sensors were monitored during the peripartal period, and blood samples were obtained for laboratory analyses. The sensor continuously recorded rumination time, rumen motility, and reticular temperature. Correlations between total serum calcium concentrations at parturition and variously, rumination time, reticular temperature, as well as the rumen motility during the days before calving have been found, indicating a potential predictive value of these latter parameters. Furthermore, the data collected in this study were used to assess the prediction quality of a deep learning model, which relies on rumen cycles, reticular contraction duration, and reticular temperature. The model has not been trained on the data of the present study, but it outperforms a simple approach based on rumination time.

Hypocalcemia commonly affects dairy cows around calving or at the onset of lactation. An individual risk prediction would allow customized prophylactic measures and targeted intervention. This study aimed to measure concentrations of total (tCa) and ionized calcium (iCa) during the peripartal period, record rumen motility and temperature patterns, and assess the associations between patterns before calving and Ca concentration at calving. A total of 89 calvings from 47 cows and 22 heifers were monitored using reticuloruminal bolus sensors over 60 days prior to the expected calving and 60 days postpartum. Cows with low tCa (<1.8 mmol/L) or iCa (<0.8 mmol/L) a few days before parturition had reduced rumination times compared to cows with normal tCa levels (>2.2 mmol/L). Using a rumination time (RT) threshold of 480 min/day on day −1, hypocalcemia was predicted with 66.7% sensitivity and 96.8% specificity. Additionally, we evaluated a deep learning model trained on external data, which incorporated rumen cycles, reticular contraction duration, and reticular temperature. Despite not being trained on this dataset, the model surpassed the RT thresholding approach, achieving 83.2% sensitivity and 98.2% specificity for tCa-based classification. These results indicate superior performance and greater generalizability of the deep learning approach, highlighting the potential of multi-metric sensor analytics to improve early hypocalcemia risk detection.

Figures