Predicting dry matter intake in beef cattle.

Technology that facilitates estimations of individual animal dry matter intake (DMI) rates in group-housed settings will improve production and management efficiencies. Estimating DMI in pasture settings or facilities where feed intake cannot be monitored may benefit from predictive algorithms that use other variables as proxies. This study examined the relationships between DMI, animal performance, and environmental variables. Here we determined whether a machine learning approach can predict DMI from measured water intake variables, age, sex, full body weight, and average daily gain (ADG). Two hundred and five animals were studied in a drylot setting (152 bulls for 88 d and 53 steers for 50 d). Collected data included daily DMI, water intake, daily predicted full body weights, and ADG using In-Pen-Weighing Positions and Feed Intake Nodes. After exclusion of 26 bulls of low-frequency breeds and one severe (>3 standard deviations) outlier, the final number of animals used for modeling was 178 (125 bulls, 53 steers). Climate data were recorded at 30-min intervals throughout the study period. Random Forest Regression (RFR) and Repeated Measures Random Forest (RMRF) were used as machine learning approaches to develop a predictive algorithm. Repeated Measures ANOVA (RMANOVA) was used as the traditional approach. Using the RMRF method, an algorithm was constructed that predicts an animal's DMI within 0.75 kg. Evaluation and refining of algorithms used to predict DMI in drylot by adding more representative data will allow for future extrapolation to controlled small plot grazing and, ultimately, more extensive group field settings.

In animal agriculture, passive monitoring technology has the potential to lead to needed innovations as we look for solutions to make global food production more resilient. Here, we use passive intake systems to measure daily weight, water intake, and climatic variables to accurately predict dry matter intake. Such an approach, if it can be successfully applied for grazing animals would dramatically improve the ability of animal agriculture to reduce the ecological footprints of food production. Two hundred and five animals were studied in a drylot setting (152 bulls for 88 d and 53 steers for 50 d). We used both traditional statistical and modern machine learning approaches to test the ability to predict dry matter intake. Although all approaches had success in predicting dry matter intake, the best prediction came from a machine learning approach which was able to predict the average daily dry matter intake during a test to within 0.75 kg/d. Evaluation and refining of algorithms used to predict dry matter intake in the drylot by adding more representative data will allow for future extrapolation to controlled small plot grazing and, ultimately, more extensive grazing animal intakes at a production scale.

Deep Learning Applied to Raman Spectroscopy for the Detection of Microsatellite Instability/MMR Deficient Colorectal Cancer.

Defective DNA mismatch repair is one pathogenic pathway to colorectal cancer. It is characterised by microsatellite instability which provides a molecular biomarker for its detection. Clinical guidelines for universal testing of this biomarker are not met due to resource limitations; thus, there is interest in developing novel methods for its detection. Raman spectroscopy (RS) is an analytical tool able to interrogate the molecular vibrations of a sample to provide a unique biochemical fingerprint. The resulting datasets are complex and high-dimensional, making them an ideal candidate for deep learning, though this may be limited by small sample sizes. This study investigates the potential of using RS to distinguish between normal, microsatellite stable (MSS) and microsatellite unstable (MSI-H) adenocarcinoma in human colorectal samples and whether deep learning provides any benefit to this end over traditional machine learning models. A 1D convolutional neural network (CNN) was developed to discriminate between healthy, MSI-H and MSS in human tissue and compared to a principal component analysis-linear discriminant analysis (PCA-LDA) and a support vector machine (SVM) model. A nested cross-validation strategy was used to train 30 samples, 10 from each group, with a total of 1490 Raman spectra. The CNN achieved a sensitivity and specificity of 83% and 45% compared to PCA-LDA, which achieved a sensitivity and specificity of 82% and 51%, respectively. These are competitive with existing guidelines, despite the low sample size, speaking to the molecular discriminative power of RS combined with deep learning. A number of biochemical antecedents responsible for this discrimination are also explored, with Raman peaks associated with nucleic acids and collagen being implicated.

Machine Learning of Raman Spectroscopy Data for Classifying Cancers: A Review of the Recent Literature.

Raman Spectroscopy has long been anticipated to augment clinical decision making, such as classifying oncological samples. Unfortunately, the complexity of Raman data has thus far inhibited their routine use in clinical settings. Traditional machine learning models have been used to help exploit this information, but recent advances in deep learning have the potential to improve the field. However, there are a number of potential pitfalls with both traditional and deep learning models. We conduct a literature review to ascertain the recent machine learning methods used to classify cancers using Raman spectral data. We find that while deep learning models are popular, and ostensibly outperform traditional learning models, there are many methodological considerations which may be leading to an over-estimation of performance; primarily, small sample sizes which compound sub-optimal choices regarding sampling and validation strategies. Amongst several recommendations is a call to collate large benchmark Raman datasets, similar to those that have helped transform digital pathology, which researchers can use to develop and refine deep learning models.

Implementation of formal prescription guidelines reduces the economic cost of unused opioids after orthopedic surgery.

BACKGROUND: Prior literature has reported on the concerning emergence of opioid overprescribing, yet there remains a lack of knowledge in understanding the cost of waste of this over-prescription and underconsumption of opioids. As such, further investigating the cost of waste of opioids following orthopedic surgery is of interest to patients, providers, and payors. In one of the largest private orthopedic practices in the United States, opioid prescribing and consumption patterns were tracked prior to, and after the implementation of, formal prescription guidelines. OBJECTIVES: To (1) establish the cost of waste of unused opioids before the implementation of formal prescription guidelines and (2) examine how the cost of unused opioids may be reduced after implementation of formal internal prescription guidelines. METHODS: Two separate phases (Phase I and Phase II) were implemented at different time intervals throughout a two-year period. Implementation of prescription guidelines occurred between Phases I and II, and data from Phase I (pre-implementation) was compared to that from Phase II (postimplementation). Data collection included type, dosage, quantity of opioids prescribed and consumed after elective outpatient procedures in ambulatory surgery centers, in addition to patient interviews/surveys within two weeks after surgery to measure consumption. From these data, the cost of waste was calculated by taking the total cost of prescribed opioids (sum of each prescription × Average Wholesale Price (AWP) minus 60%) per 1,000 patients, and subtracting the total cost of consumed opioids per 1,000 patients, calculated in a similar manner. Further analysis was performed to describe differences in the cost of waste of individual opioids between each of the phases. RESULTS: In Phase I, prior to implementation of formal internal prescription guidelines, there was a sizable cost of waste of unused opioids (per 1,000 patients, AWP minus 60%) of $11,299.51. The cost of waste in Phase II, after implementation of formal internal prescription guidelines, was $6,117.12, which was a significant decrease of 45.9% ($5,182.39) from Phase I (P < 0.001). Furthermore, both the average number of morphine equivalent units prescribed and consumed per patient decreased from Phase I to Phase II (294.6 vs 187.8, P < 0.001; and 144.9 vs 96.0, P < 0.001, respectively). Finally, in describing individual medications, there was a significant decrease in cost of waste (per 1,000 patients, AWP minus 60%) between Phases I and II for- Hydrocodone with APAP 5/525 mg (P< 0.001), Oxycodone CR 10 mg (P< 0.001), Morphine CR 15 mg (P=0.001), and Tramadol 50 mg (P = 0.014). CONCLUSIONS: The results of this study suggest that there is a significant cost of waste associated with differences in prescribed versus consumed opioids following elective orthopedic surgery. This cost of waste was significantly reduced following the introduction and implementation of formal prescription guidelines. DISCLOSURES: This study was funded internally by Revo Health and Twin Cities Orthopedics. Giveans reports consulting fees from Medtrak, Inc., and Superior Medical Experts. The other authors have nothing to disclose.