Aryal, A. | bioRxiv Science

bioRxiv2024

Evaluating machine learning algorithms to predict lameness in dairy cattle

Dairy cattle lameness represents one of the common concerns in intensive and commercial dairy farms. Lameness is characterized by gait-related behavioral changes in cows and multiple approaches are being utilized to associate these changes with lameness conditions including data from accelerometers, and other precision technologies. The objective was to evaluate the use of machine learning algorithms for the identification of lameness conditions in dairy cattle. In this study, 310 multiparous Holstein dairy cows from a herd in Northern Colorado were affixed with a leg-based accelerometer (Icerobotics(R) Inc, Edinburg, Scotland) to obtain the lying time (min/d), daily steps count (n/d), and daily change (n/d). Subsequently, study cows were monitored for 4 months and cows submitted for claw trimming (CT) were differentiated as receiving corrective claw trimming (CCT) or as being diagnosed with a lameness disorder and consequent therapeutic claw trimming (TCT) by a certified hoof trimmer. Cows not submitted to CT were considered healthy controls. A median filter was applied to smoothen the data by reducing inherent variability. Three different machine learning (ML) models were defined to fit each algorithm which included the conventional features (containing daily lying, daily steps, and daily change derived from the accelerometer), slope features (containing features extracted from each variable in Conventional feature), or all features (3 simple features and 3 slope features). Random forest (RF), Naive Bayes (NB), Logistic Regression (LR), and Time series (ROCKET) were used as ML predictive approaches. For the classification of cows requiring CCT and TCT, ROCKET classifier performed better with accuracy (> 90%), ROC-AUC (> 74%), and F1 score (> 0.61) as compared to other algorithms. Slope features derived in this study increased the efficiency of algorithms as the better-performing models included All features explored. However, further classification of diseases into infectious and non-infectious events was not effective because none of the algorithms presented satisfactory model accuracy parameters. For the classification of observed cow locomotion scores into severely lame and moderately lame conditions, the ROCKET classifier demonstrated satisfactory accuracy (> 0.85), ROC-AUC (> 0.68), and F1 scores (> 0.44). We conclude that ML models using accelerometer data are helpful in the identification of lameness in cows but need further research to increase the granularity and accuracy of classification.

animal behavior and cognition↗

bioRxiv2022

Nutrient limitation mimics artemisinin tolerance in malaria

Mounting evidence demonstrates that nutritional environment can alter pathogen drug sensitivity. While the nutrient-rich media used for standard in vitro culture contains supra-physiological nutrient concentrations, pathogens encounter a relatively restrictive environment in vivo. We assessed the effect of nutrient limitation on the protozoan parasite that causes malaria and demonstrated that short-term growth under physiologically-relevant mild nutrient stress (or "metabolic priming") triggers increased tolerance of the potent antimalarial drug dihydroartemisinin (DHA). We observed beneficial effects using both short-term survival assays and longer-term proliferation studies, where metabolic priming increases parasite survival to a level previously defined as DHA resistant (>1% survival). We performed these assessments by either decreasing single nutrients that have distinct roles in parasite metabolism or using a media formulation with reductions in many nutrients that simulates the human plasma environment. We determined that priming-induced DHA tolerance was restricted to parasites that had newly invaded the host red blood cell but the effect was not dependent on genetic background. The molecular mechanisms of this intrinsic effect mimic aspects of genetic artemisinin tolerance, including translational repression, autophagy, and protein export. This finding suggests regardless of the impact on survival rates, environmental stress could stimulate changes that ultimately directly contribute to drug tolerance. Because metabolic stress is likely to occur more frequently in vivo compared to the stable in vitro environment, priming-induced drug tolerance has ramifications for how in vitro results translate to in vivo studies. Improving our understanding of how pathogens adjust their metabolism to impact survival of current and future drugs is an important avenue of research to prevent and slow the spread of resistance.

microbiology↗