Pregnancy detection and monitoring in cattle via combined foetus electrocardiogram and phonocardiogram signal processing

Abstract

Background: Pregnancy testing in cattle is commonly invasive requiring manual rectal palpation of the reproductive tract that presents risks to the operator and pregnancy. Alternative non-invasive tests have been developed but have not gained popularity due to poor specificity, sensitivity and the inconvenience of sample handling. Our aim is to present the pilot study and proof of concept of a new non invasive technique to sense the presence and age (limited to the closest trimester of pregnancy) of the foetus by recording the electrical and audio signals produced by the foetus heartbeat using an array of specialized sensors embedded in a stand alone handheld prototype device. The device was applied to the right flank (approximately at the intercept of a horizontal line drawn through the right mid femur region of the cow and a vertical line drawn anywhere between lumbar vertebrae 3 to 5) of more than 2000 cattle from 13 different farms, including pregnant and not pregnant, a diversity of breeds, and both dairy and beef herds. Pregnancy status response is given "on the spot" from an optimized machine learning algorithm running on the device within seconds after data collection.

Results: Using combined electrical and audio foetal signals we detected pregnancy with a sensitivity of 87.6% and a specificity of 74.6% for all recorded data. Those values increase to 91% and 81% respectively by removing files with excessive noise (19%).Foetus ageing was achieved by comparing the detected foetus heart-rate with published tables. However, given the challenging farm environment of a restless cow, correct foetus ageing was achieved for only 21% of the correctly diagnosed pregnant cows.

Conclusions: In conclusion we have found that combining ECG and PCG measurements on the right flank of cattle provides a reliable and rapid method of pregnancy testing. The device has potential to be applied by unskilled operators. This will generate more efficient and productive management of farms. There is potential for the device to be applied to large endangered quadrupeds in captive breeding programs where early, safe and reliable pregnancy diagnosis can be imperative but currently difficult to achieve.

Figure 1

Prototype device unit and its parts.

Figure 2

Simultaneous recording of foetus PCG, foetus ECG and maternal ECG; Top trace depicts foetus PCG; the solid circle highlights 1st (loud) cardiac sound and the dashed circle highlights the 2nd (weak) cardiac sound. The second and third traces from the top present the foetus ECG; the solid squares highlight the foetus QRS complexes. Maternal ECG (with QRS highlighted by dashed rectangles) is presented in the lower trace.

Figure 3

Evidence of independence between maternal and foetus QRS events; Panel a: example of foetus QRS occurring just before the maternal QRS; Panel b: example of foetus QRS occurring just after the maternal QRS. The top trace in both panels depicts foetus PCG; the solid circle highlights the 1st (loud) cardiac sound and the dashed circle highlights the 2nd (weak) cardiac sound. The second and third traces from the top present the foetus ECG; solid squares highlight the foetus QRS complexes. Maternal ECG (QRS highlighted with dashed rectangles) is depicted in the bottom trace.

Figure 4

Example of use of prototype device (Courtesy of HEARD systems; the depicted subject kindly agreed to have his image published).

Figure 5

Example of data acquired from a 20-week pregnant cow using the prototype device. This device has eight channels (7 ECG and 1 PCG). The detected foetus QRS complexes are highlighted with solid squares across the ECG channels; first and second cardiac sounds are highlighted with a solid circles and dashed circles on the PCG channel respectively.