Exploring machine learning algorithms for early prediction of clinical mastitis

Augmenting Telepostpartum Care With Vision-Based Detection of Breastfeeding-Related Conditions: Algorithm Development and Validation

BACKGROUND

Breastfeeding benefits both the mother and infant and is a topic of attention in public health. After childbirth, untreated medical conditions or lack of support lead many mothers to discontinue breastfeeding. For instance, nipple damage and mastitis affect 80% and 20% of US mothers, respectively. Lactation consultants (LCs) help mothers with breastfeeding, providing in-person, remote, and hybrid lactation support. LCs guide, encourage, and find ways for mothers to have a better experience breastfeeding. Current telehealth services help mothers seek LCs for breastfeeding support, where images help them identify and address many issues. Due to the disproportional ratio of LCs and mothers in need, these professionals are often overloaded and burned out.

OBJECTIVE

This study aims to investigate the effectiveness of 5 distinct convolutional neural networks in detecting healthy lactating breasts and 6 breastfeeding-related issues by only using red, green, and blue images. Our goal was to assess the applicability of this algorithm as an auxiliary resource for LCs to identify painful breast conditions quickly, better manage their patients through triage, respond promptly to patient needs, and enhance the overall experience and care for breastfeeding mothers.

METHODS

We evaluated the potential for 5 classification models to detect breastfeeding-related conditions using 1078 breast and nipple images gathered from web-based and physical educational resources. We used the convolutional neural networks Resnet50, Visual Geometry Group model with 16 layers (VGG16), InceptionV3, EfficientNetV2, and DenseNet169 to classify the images across 7 classes: healthy, abscess, mastitis, nipple blebs, dermatosis, engorgement, and nipple damage by improper feeding or misuse of breast pumps. We also evaluated the models' ability to distinguish between healthy and unhealthy images. We present an analysis of the classification challenges, identifying image traits that may confound the detection model.

RESULTS

The best model achieves an average area under the receiver operating characteristic curve of 0.93 for all conditions after data augmentation for multiclass classification. For binary classification, we achieved, with the best model, an average area under the curve of 0.96 for all conditions after data augmentation. Several factors contributed to the misclassification of images, including similar visual features in the conditions that precede other conditions (such as the mastitis spectrum disorder), partially covered breasts or nipples, and images depicting multiple conditions in the same breast.

CONCLUSIONS

This vision-based automated detection technique offers an opportunity to enhance postpartum care for mothers and can potentially help alleviate the workload of LCs by expediting decision-making processes.

Performance comparison of machine learning models used for predicting subclinical mastitis in dairy cows: Bagging, boosting, stacking, and super-learner ensembles versus single machine learning models

Mastitis has a substantial impact on the dairy industry across the world, causing dairy producers to suffer losses due to the reduced quality and quantity of produced milk. A further problem, related to this issue, is the excessive use of antibiotics that leads to the development of resistance in different bacterial strains. The growing consumer awareness oriented toward food safety and rational use of antibiotics has promoted the search for new methods of early identification of cows that may be at risk of developing the disease. Subclinical mastitis does not cause any visible changes to the udder or milk, and therefore it is more difficult to detect than clinical mastitis. The collection of large amounts of data related to milk performance of cows allows using machine learning (ML) methods to build models that could be used for classifying cows into healthy and at risk of subclinical mastitis. The data used for the purpose of this study included information from routine milk recording procedures. The dataset consisted of 19,856 records of 2,227 Polish Holstein-Friesian cows from 3 herds. The authors decided to use the approach of building ensemble ML models, in particular bagging, boosting, stacking, and super-learner models, and comparing them for accuracy of identification of disease-affected cows against single ML models based on the support vector machines, logistic regression, Gaussian Naive Bayes, k-nearest neighbors, and decision tree algorithms. The models were trained and evaluated based on the information recorded for herd 1 and using an 80:20 train-test split ratio according to animal ID (to avoid data leakage). The information recorded for herds 2 and 3 was only used to evaluate on unseen data models developed using the herd 1 dataset. Among the single ML models, the support vector machines model was found to be the most accurate in predicting subclinical mastitis at subsequent test day when used both for the training set (mean F1-score of 0.760) and the testing sets containing data for herds 1, 2, and 3 (F1-score of 0.778, 0.790, and 0.741 respectively). The gradient boosting model was found to be the best performing model among the ensemble ML models (F1-score of 0.762, 0.779, 0.791, and 0.723 for the training set and the testing sets, respectively). The super-learner model, featuring the most advanced design and logistic regression in the meta layer, achieved the highest mean F1-score of 0.775 during the cross validation; however, it was characterized by a slightly worse prediction accuracy of the testing sets (mean F1-score of 0.768, 0.790, and 0.693 for herds 1, 2 and 3 respectively). The study findings confirm the promising role of ensemble ML methods, which were found to be slightly superior with respect to most of the single ML models.

The Prediction of Clinical Mastitis in Dairy Cows Based on Milk Yield, Rumination Time, and Milk Electrical Conductivity Using Machine Learning Algorithms

In commercial dairy farms, mastitis is associated with increased antimicrobial use and associated resistance, which may affect milk production. This study aimed to develop sensor-based prediction models for naturally occurring clinical bovine mastitis using nine machine learning algorithms with data from 447 mastitic and 2146 healthy cows obtained from five commercial farms in Northeast China. The variables were related to daily activity, rumination time, and daily milk yield of cows, as well as milk electrical conductivity. Both Z-standardized and non-standardized datasets pertaining to four specific stages of lactation were used to train and test prediction models. For all four subgroups, the Z-standardized dataset yielded better results than those of the non-standardized one, with the multilayer artificial neural net algorithm showing the best performance. Variables of importance had a similar rank in this algorithm, indicating the consistency of these variables as predictors for bovine mastitis in commercial farms with similar automatic systems. Moreover, the peak milk yield (PMY) of mastitic cows was significantly higher than that of healthy cows (p < 0.005), indicating that high-yielding cattle are more prone to mastitis. Our results show that machine learning algorithms are effective tools for predicting mastitis in dairy cows for immediate intervention and management in commercial farms.

The use of machine learning to predict somatic cell count status in dairy cows post-calving

Udder health remains a priority for the global dairy industry to reduce pain, economic losses, and antibiotic usage. The dry period is a critical time for the prevention of new intra-mammary infections and it provides a point for curing existing intra-mammary infections. Given the wealth of udder health data commonly generated through routine milk recording and the importance of udder health to the productivity and longevity of individual cows, an opportunity exists to extract greater value from cow-level data to undertake risk-based decision-making. The aim of this research was to construct a machine learning model, using routinely collected farm data, to make probabilistic predictions at drying off for an individual cow's risk of a raised somatic cell count (hence intra-mammary infection) post-calving. Anonymized data were obtained as a large convenience sample from 108 UK dairy herds that undertook regular milk recording. The outcome measure evaluated was the presence of a raised somatic cell count in the 30 days post-calving in this observational study. Using a 56-farm training dataset, machine learning analysis was performed using the extreme gradient boosting decision tree algorithm, XGBoost. External validation was undertaken on a separate 28-farm test dataset. Statistical assessment to evaluate model performance using the external dataset returned calibration plots, a Scaled Brier Score of 0.095, and a Mean Absolute Calibration Error of 0.009. Test dataset model calibration performance indicated that the probability of a raised somatic cell count post-calving was well differentiated across probabilities to allow an end user to apply group-level risk decisions. Herd-level new intra-mammary infection rate during the dry period was a key driver of the probability that a cow had a raised SCC post-calving, highlighting the importance of optimizing environmental hygiene conditions. In conclusion, this research has determined that probabilistic classification of the risk of a raised SCC in the 30 days post-calving is achievable with a high degree of certainty, using routinely collected data. These predicted probabilities provide the opportunity for farmers to undertake risk decision-making by grouping cows based on their probabilities and optimizing management strategies for individual cows immediately after calving, according to their likelihood of intra-mammary infection.

Risk prediction model of clinical mastitis in lactating dairy cows based on machine learning algorithms

Mastitis is the most common disease among dairy cows and is known to have negative effects on both animal welfare and the profitability of dairy farms. Early detection of clinical mastitis cases is considered the best option for preventing cows from developing mastitis. In this study, we developed clinical mastitis prediction models that only required inputting common indicators from the automatic milking system. We utilized multidimensional data from the cow mastitis database of Afimilk (China) Agricultural Technology Co., Ltd. to predict mastitis in dairy cows. All data were screened for the period of 0-150 days of lactation. The data included parity, lactation day, period, mean and standard deviation of milk yield, of electrical conductivity, and of lying time, which were taken as input features. The classification of whether cows suffer from clinical mastitis was determined as output. We analyzed 426 cows with clinical mastitis and 2087 healthy cows by using four machine learning algorithms: Decision Tree, Random Forest, Back Propagation neural networks, and Support Vector Machines. In these four algorithms, the accuracy ranged from 94% to 98%, while the running times varied widely from seconds to minutes. The decision tree prediction model achieved an accuracy of 98% and the precision rate for healthy cows was 99%, while for mastitis cows it was 97%. Machine learning algorithms have played an important role in predicting cow mastitis, with the Decision Tree algorithm showing great performance and higher accuracy in our research.

The Relationship between Reticuloruminal Temperature, Reticuloruminal pH, Cow Activity, and Clinical Mastitis in Dairy Cows

We hypothesized that reticuloruminal temperature, pH as well as cow activity can be used as parameters for the early diagnosis of clinical mastitis in dairy cows. Therefore, we aimed to detect the relationship between these factors and the disease. We randomly selected cows with clinical mastitis and clinically healthy cows (HG) out of 600 milking cows. We recorded the following parameters during the experiment: reticulorumen temperature (RR temp.), reticulorumen pH (RR pH), and cow activity. We used smaXtec boluses (smaXtec animal care technology^®, Graz, Austria). In this investigation, reticulorumen data obtained seven days before diagnosis were compared to HG data from the same time period. CM cows were observed on the same days as the healthy cows. The healthy group's RR pH was 7.32% higher than that of cows with CM. Reticulorumen temperature was also 1.25% higher in the CM group than in the control group. The healthy group had a higher average value for walking activity, which was 17.37% higher than the CM group. The data of reticulorumen pH changes during 24 h showed that during the day, the pH changed from 5.53 to 5.83 in the CM group. By contrast, pH changed from 6.05 to 6.31 in the control group. The lowest reticulorumen pH in the CM group was detected on the third day before diagnosis, which was 15.76% lower than the highest reticulorumen pH detected on the sixth day before diagnosis. The lowest reticulorumen pH in CM cows was detected at 0 and 1 days before diagnosis and it was 1.45% lower than the highest reticulorumen pH detected on the second day before diagnosis. The lowest walking activity in the CM group was detected 0 days before diagnosis, which was 50.60% lower than on the fifth day before diagnosis. Overall, the results confirmed our hypothesis that reticuloruminal temperature, reticuloruminal pH, and cow activity could be used as parameters for the early diagnosis of clinical mastitis in dairy cows.

Multivariable time series classification for clinical mastitis detection and prediction in automated milking systems

In this study, we developed a machine learning framework to detect clinical mastitis (CM) at the current milking (i.e., the same milking) and predict CM at the next milking (i.e., one milking before CM occurrence) at the quarter level. Time series quarter-level milking data were extracted from an automated milking system (AMS). For both CM detection and prediction, the best classification performance was obtained from the decision tree-based ensemble models. Moreover, applying models on a data set containing data from the current milking and past 9 milkings before the current milking showed the best accuracy for detecting CM; modeling with a data set containing data from the current milking and past 7 milkings before the current milking yielded the best results for predicting CM. The models combined with oversampling methods resulted in specificity of 95 and 93% for CM detection and prediction, respectively, with the same sensitivity (82%) for both scenarios; when lowering specificity to 80 to 83%, undersampling techniques facilitated models to increase sensitivity to 95%. We propose a feasible machine learning framework to identify CM in a timely manner using imbalanced data from an AMS, which could provide useful information for farmers to manage the negative effects of CM.

Evaluation of reticuloruminal temperature for the prediction of clinical mastitis in dairy cows challenged with Streptococcus uberis

Automated monitoring devices have become increasingly utilized in the dairy industry, especially for monitoring or predicting disease status. While multiple automated monitoring devices have been developed for the prediction of clinical mastitis (CM), limitations in performance or applicability remain. The aims of this study were to (1) detect variations in reticuloruminal temperature (RRT) relative to an experimental intramammary challenge with Streptococcus uberis and (2) evaluate alerts generated automatically based on variation in RRT to predict initial signs of CM in the challenged cows based on severity of clinical signs and the concentration of bacteria (cfu/mL) in the infected quarter separately. Clinically healthy Holstein cows without a history of CM in the 60 d before the experiment (n = 37, parity 1 to 5, ≥120 d in milk) were included if they were microbiologically negative and had a somatic cell count under 200,000 cells/mL based on screening of quarter milk samples 1 wk before challenge. Each cow received an intra-reticuloruminal automated monitoring device before the trial and was challenged with 2,000 cfu of Strep. uberis 0140J in 1 rear quarter. Based on interrupted time series analysis, intramammary challenge with Strep. uberis increased RRT by 0.54°C [95% confidence interval (CI): 0.41, 0.66] at 24 h after the challenge, which remained elevated until the end of the study. Alerts based on RRT correctly classified 78.3% (95% CI: 65.8, 87.9) of first occurrences of CM at least 24 h in advance, with a sensitivity of 70.0% (95% CI: 50.6, 85.3) and a specificity of 86.7% (95% CI: 69.3, 96.2). The accuracy of CM for a given severity score was 90.9% (95% CI: 70.8, 98.9) for mild cases, 85.2% (95% CI: 72.9, 93.4) for moderate cases, and 92.9% (95% CI: 66.1, 99.8) for severe cases. Test characteristics of the RRT alerts to predict initial signs of CM improved substantially after bacterial count in the challenged quarter reached 5.0 log₁₀ cfu/mL, reaching a sensitivity of 73.5% (95% CI: 55.6, 87.1) and a specificity of 87.5% (95% CI: 71.0, 96.5). Overall, the results of this study indicated that RRT was affected by the intramammary challenge with Strep. uberis and the RRT-generated alerts had similar accuracy as reported for other sensors and algorithms. Further research that includes natural infections with other pathogens as well as different variations in RRT to determine CM status is warranted.

Applying Machine Learning Algorithms for the Classification of Mink Infected with Aleutian Disease Using Different Data Sources

Simple Summary

Aleutian disease (AD) is a major infectious disease found in mink farms, and it causes financial losses to the mink industry. Controlling AD often requires a counterimmunoelectrophoresis (CIEP) method, which is relatively expensive for mink farmers. Therefore, predicting AD infected mink without using CIEP records will be important for controlling AD in mink farms. In the current study, we applied nine machine learning algorithms to classify AD-infected mink. We indicated that the random forest could be used to classify AD-infected mink (accuracy of 0.962) accurately. This result could be used for implementing machine learning in controlling AD in the mink farms.

Abstract

American mink (Neogale vison) is one of the major sources of fur for the fur industries worldwide, whereas Aleutian disease (AD) is causing severe financial losses to the mink industry. A counterimmunoelectrophoresis (CIEP) method is commonly employed in a test-and-remove strategy and has been considered a gold standard for AD tests. Although machine learning is widely used in livestock species, little has been implemented in the mink industry. Therefore, predicting AD without using CIEP records will be important for controlling AD in mink farms. This research presented the assessments of the CIEP classification using machine learning algorithms. The Aleutian disease was tested on 1157 individuals using CIEP in an AD-positive mink farm (Nova Scotia, Canada). The comprehensive data collection of 33 different features was used for the classification of AD-infected mink. The specificity, sensitivity, accuracy, and F1 measure of nine machine learning algorithms were evaluated for the classification of AD-infected mink. The nine models were artificial neural networks, decision tree, extreme gradient boosting, gradient boosting method, K-nearest neighbors, linear discriminant analysis, support vector machines, naive bayes, and random forest. Among the 33 tested features, the Aleutian mink disease virus capsid protein-based enzyme-linked immunosorbent assay was found to be the most important feature for classifying AD-infected mink. Overall, random forest was the best-performing algorithm for the current dataset with a mean sensitivity of 0.938 ± 0.003, specificity of 0.986 ± 0.005, accuracy of 0.962 ± 0.002, and F1 value of 0.961 ± 0.088, and across tenfold of the cross-validation. Our work demonstrated that it is possible to use the random forest algorithm to classify AD-infected mink accurately. It is recommended that further model tests in other farms need to be performed and the genomic information needs to be used to optimize the model for implementing machine learning methods for AD detection.

The Early Prediction of Common Disorders in Dairy Cows Monitored by Automatic Systems with Machine Learning Algorithms

We use multidimensional data from automated monitoring systems and milking systems to predict disorders of dairy cows by employing eight machine learning algorithms. The data included the season, days in milking, parity, age at the time of disorders, milk yield (kg/day), activity (unitless), six variables related to rumination time, and two variables related to the electrical conductivity of milk. We analyze 131 sick cows and 149 healthy cows with identical lactation days and parity; all data are collected on the same day, which corresponds to the diagnosis day for disordered cows. For disordered cows, each variable, except the ratio of rumination time from daytime to nighttime, displays a decreasing/increasing trend from d-7 or d-3 to d0 and/or d-1, with the d0, d-1, or d-2 values reaching the minimum or maximum. The test data sensitivity for three algorithms exceeded 80%, and the accuracies of the eight algorithms ranged from 65.08% to 84.21%. The area under the curve (AUC) of the three algorithms was >80%. Overall, Rpart best predicts the disorders with an accuracy, precision, and AUC of 81.58%, 92.86%, and 0.908, respectively. The machine learning algorithms may be an appropriate and powerful decision support and monitoring tool to detect herds with common health disorders.

MILK LIPIDS AND SUBCLINICAL MASTITIS

This article deals with the process of obtaining quality raw milk by analyzing its lipid composition. The lipid composition of raw milk depends on many factors, among which, first of all, is the species, the composition of the diet and the physiological state of the breast. In recent years, a large amount of data has accumulated on the fluctuations of certain lipid parameters of milk depending on the type, age, lactation, diet, time of year, exercise, animal husbandry technology, physiological state of the lactating organism in general and breast status in particular. Factors of regulation of fatty acid composition of raw milk: genetically determined parameters of quality and safety; fatty acid composition of the diet; synthesis of fatty acids by microorganisms of the digestive tract; synthesis of fatty acids in the breast; physiological state of the breast. The milk of each species of productive animals has its own specific lipid profile and is used in the formulation of certain dairy products to obtain the planned technological and nutritional parameters. Diagnosis of productive animals for subclinical mastitis involves the use of auxiliary (thermometry, thermography, electrical conductivity) and laboratory research methods: counting the number of somatic cells; use of specialized tests; microbiological studies of milk; biochemical studies of milk. The biochemical component in the diagnosis of subclinical forms of mastitis is underestimated. An increase in body temperature implies an increase in the intensity of heat release during the oxidation of substrates, sometimes due to a decrease in the intensity of synthesis of energy-intensive compounds. There are simply no other sources of energy in the body. The situation is the same with certain parts of the metabolism, which are aimed at the development of protective reactions to the etiological factor aimed at the defeat of the breast. That is why the biochemical composition of breast secretions in the absence of clinical signs of mastitis undergoes biochemical changes and the task of scientists is to develop mechanisms for clear tracking of such changes, identification of animals with subclinical forms of mastitis and effective treatment.

MasPA: A Machine Learning Application to Predict Risk of Mastitis in Cattle from AMS Sensor Data

Mastitis is a common disease that prevails in cattle owing mainly to environmental pathogens; they are also the most expensive disease for cattle in dairy farms. Several prevention and treatment methods are available, although most of these options are quite expensive, especially for small farms. In this study, we utilized a dataset of 6600 cattle along with several of their sensory parameters (collected via inexpensive sensors) and their prevalence to mastitis. Supervised machine learning approaches were deployed to determine the most effective parameters that could be utilized to predict the risk of mastitis in cattle. To achieve this goal, 26 classification models were built, among which the best performing model (the highest accuracy in the shortest time) was selected. Hyper parameter tuning and K-fold cross validation were applied to further boost the top model’s performance, while at the same time avoiding bias and overfitting of the model. The model was then utilized to build a GUI application that could be used online as a web application. The application can predict the risk of mastitis in cattle from the inhale and exhale limits of their udder and their temperature with an accuracy of 98.1% and sensitivity and specificity of 99.4% and 98.8%, respectively. The full potential of this application can be utilized via the standalone version, which can be easily integrated into an automatic milking system to detect the risk of mastitis in real time.

Novel ways to use sensor data to improve mastitis management

Current sensor systems are used to detect cows with clinical mastitis. Although, the systems perform well enough to not negatively affect the adoption of automatic milking systems, the performance is far from perfect. An important advantage of sensor systems is the availability of multiple measurements per day. By clearly defining the need for detection of subclinical mastitis (SCM) and clinical mastitis (CM) from the farmers' management perspective, detection and management of SCM and CM may be improved. Sensor systems may also be used for other aspects of mastitis management. In this paper we have defined 4 mastitis situations that could be managed with the support of sensor systems. Because of differences in the associated management and the epidemiology of these specific mastitis situations, the required demands for performance of the sensor systems do differ. The 4 defined mastitis situations with the requirements of performance are the following: (1) Cows with severe CM needing immediate attention. Sensor systems should have a very high sensitivity (>95% and preferably close to 100%) and specificity (>99%) within a narrow time window (maximum 12 h) to ensure that close to all cows with true cases of severe CM are detected quickly. Although never studied, it is expected that because of the effects of severe CM, such a high detection performance is feasible. (2) Cows with mastitis that do not need immediate attention. Although these cows have a risk of progressing into severe CM or chronic mastitis, they should get the chance to cure spontaneously under close monitoring. Sensor alerts should have a reasonable sensitivity (>80%) and a high specificity (>99.5%). The time window may be around 7 d. (3) Cows needing attention at drying off. For selective dry cow treatment, the absence or presence of an intramammary infection at dry-off needs to be known. To avoid both false-positive and false-negative alerts, sensitivity and specificity can be equally high (>95%). (4) Herd-level udder health. By combining sensor readings from all cows in the herd, novel herd-level key performance indicators can be developed to monitor udder health status and development over time and raise alerts at significant deviances from predefined thresholds; sensitivity should be reasonably high, >80%, and because of the costs for further analysis of false-positive alerts, the specificity should be >99%. The development and validation of sensor-based algorithms specifically for these 4 mastitis situations will encourage situation-specific farmer interventions and operational udder health management.