AI–Powered Nanosensing of Lactate in Dairy Cows

Early detection of metabolic diseases, including lactic acidosis, is crucial for effective livestock health management. This study presents the development of a nanosensor platform using graphene nanosheets and lactate oxidase (LOx) enzyme to detect lactate and hydrogen peroxide (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathrm{H}_{2} \mathrm{O}_{2}$</tex>) concentrations within a minute. Machine learning (ML) techniques, including polynomial regression and random forest (RF) regression, were used to optimize sensor calibration. Polynomial regression (degrees 3 and 4) achieved perfect accuracy (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$r^{2}=1.00$</tex>), while RF regression demonstrated strong predictive performance (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$r^{2}=0.857$</tex>). These results underscore the lactate sensor's potential for precise, reliable detection in complex biological fluids, providing an advantage over traditional methods in dairy cattle health monitoring.