Application of machine-learning methods to milk mid-infrared spectra for discrimination of cow milk from pasture or total mixed ration diets.

The prevalence of "grass-fed" labeled food products on the market has increased in recent years, often commanding a premium price. To date, the majority of methods used for the authentication of grass-fed source products are driven by auditing and inspection of farm records. As such, the ability to verify grass-fed source claims to ensure consumer confidence will be important in the future. Mid-infrared (MIR) spectroscopy is widely used in the dairy industry as a rapid method for the routine monitoring of individual herd milk composition and quality. Further harnessing the data from individual spectra offers a promising and readily implementable strategy to authenticate the milk source at both farm and processor levels. Herein, a comprehensive comparison of the robustness, specificity, and accuracy of 11 machine-learning statistical analysis methods were tested for the discrimination of grass-fed versus non-grass-fed milks based on the MIR spectra of 4,320 milk samples collected from cows on pasture or indoor total mixed ration-based feeding systems over a 3-yr period. Linear discriminant analysis and partial least squares discriminant analysis (PLS-DA) were demonstrated to offer the greatest level of accuracy for the prediction of cow diet from MIR spectra. Parsimonious strategies for the selection of the most discriminating wavelengths within the spectra are also highlighted.

Predicting cow milk quality traits from routinely available milk spectra using statistical machine learning methods.

Numerous statistical machine learning methods suitable for application to highly correlated features, as those that exist for spectral data, could potentially improve prediction performance over the commonly used partial least squares approach. Milk samples from 622 individual cows with known detailed protein composition and technological trait data accompanied by mid-infrared spectra were available to assess the predictive ability of different regression and classification algorithms. The regression-based approaches were partial least squares regression (PLSR), ridge regression (RR), least absolute shrinkage and selection operator (LASSO), elastic net, principal component regression, projection pursuit regression, spike and slab regression, random forests, boosting decision trees, neural networks (NN), and a post-hoc approach of model averaging (MA). Several classification methods (i.e., partial least squares discriminant analysis (PLSDA), random forests, boosting decision trees, and support vector machines (SVM)) were also used after stratifying the traits of interest into categories. In the regression analyses, MA was the best prediction method for 6 of the 14 traits investigated [curd firmness at 60 min, αS1-casein (CN), αS2-CN, κ-CN, α-lactalbumin, and ß-lactoglobulin B], whereas NN and RR were the best algorithms for 3 traits each (rennet coagulation time, curd-firming time, and heat stability, and curd firmness at 30 min, ß-CN, and ß-lactoglobulin A, respectively), PLSR was best for pH, and LASSO was best for CN micelle size. When traits were divided into 2 classes, SVM had the greatest accuracy for the majority of the traits investigated. Although the well-established PLSR-based method performed competitively, the application of statistical machine learning methods for regression analyses reduced the root mean square error compared with PLSR from between 0.18% (κ-CN) to 3.67% (heat stability). The use of modern statistical machine learning methods for trait prediction from mid-infrared spectroscopy may improve the prediction accuracy for some traits.

Predicting prostate cancer: analysing the clinical efficacy of prostate cancer risk calculators in a referral population.

BACKGROUND: The decision to proceed to biopsy for the diagnosis of prostate cancer in clinical practice is a difficult one. Prostate cancer risk calculators allow for a systematic approach to the use of patient information to predict a patient's likelihood of prostate cancer. AIMS: In this paper, we validate the two leading prostate cancer risk calculators, the prostate cancer prevention trial (PCPT) and the European Randomized Study of Screening for Prostate Cancer (ERSPC) in an Irish population. METHODS: Data were collected for 337 men referred to one tertiary referral center in Ireland. Calibration analysis, ROC analysis and decision curve analysis were undertaken to ascertain the performance of the PCPT and the ERSPC risk calculators in this cohort. RESULTS: Of 337 consecutive biopsies, cancer was subsequently diagnosed in 146 men (43 %), 98 (67 %) of which were high grade. The AUC for the PCPT and ERSPC risk calculators were 0.68 and 0.66, respectively for the prediction of prostate cancer. Each calculator was sufficiently calibrated in this cohort. Decision curve analysis demonstrated a net benefit via the use of the PCPT and ERSPC risk calculators in the diagnosis of prostate cancer. CONCLUSIONS: The PCPT and ERSPC risk calculators achieve a statistically significant prediction of prostate cancer in this Irish population. This study provides external validation for these calculators, and therefore these tools can be used to aid in clinical decision making.

Treating chronic food refusal in young children: home-based parent training.

We evaluated the effects of behavioral parent training program on parent and child feeding-related behaviors in the home. We trained mothers to initiate regular offerings of previously rejected (target) foods and to provide contingent attention (i.e., specific prompts, positive reinforcement) to increase their child's acceptance of nonpreferred foods. For 1 subject, we also directed training at increasing self-eating. Results of a nonconcurrent multiple baseline design across 3 mother-child dyads demonstrated that, with training, all mothers increased offerings of target foods and use of specific prompts, and 2 mothers increased levels of positive attention. In turn, children increased their acceptance of target foods and self-eating, thus demonstrating the functional effects of parent training on in-home meal times. Temporary increases in food refusals occurred when treatment was initiated but declined as treatment continued. We discuss the results in terms of the potential benefits and limitations of a home-based treatment model.

Psychosocial concomitants of children's feeding disorders.

Compared behavior problems, child developmental skills, home environment, and parent emotional distress for 50 families of children aged 11-70 months with differing etiologies of feeding disorders (FD). Results showed that psychosocial functioning differed across FD classifications. Children with nonorganic characteristics to FD had more behavior problems compared to those with only organic FD. Children with primarily or only organic FD displayed lower developmental skills and their parents had higher emotional distress than children with primarily nonorganic FD. High parent distress was associated with older children who had poor feeding skills, less positive disciplinary practices, and higher social status. The findings imply that clinical services to families often are warranted and that service needs vary depending on the nature of FD. Mixed organic and nonorganic FD occurred in the majority of children, which supports the need for more detailed classification than an organic-nonorganic dichotomy used in prior research.

An in vivo evaluation of iron-chelating drugs derived from pyridoxal and its analogs.

Chelating agents related to the newly described iron binding drug, pyridoxal isonicotinoyl hydrazone, were screened for their effects on iron excretion in the rat, employing a new and highly sensitive radioisotopic procedure. Pyridoxal itself induced significant iron excretion when given either parenterally or orally, the excreted iron being derived from the same pool as that tapped by the drug currently used in treating iron overload in man, desferrioxamine B. Schiff base derivatives of pyridoxal produced varying amounts of iron excretion, the hydrazone derivatives being much more effective than pyridoxal alone. These data suggested a number of possible mechanisms for the chelation of endogenous iron by such agents. Pyridoxal benzoyl hydrazone induced approximately 50% more iron excretion than did an equivalent dose of the parent isonicotinoyl analog and bile cannulation studies showed this difference to be associated with a prolonged duration of action of the benzoyl derivative. When give i.v., the benzoyl and isonicotinoyl hydrazones of pyridoxal and the benzoyl hydrazone of salicylaldehyde all produced levels of iron excretion which exceeded that seen with an equivalent dose of desferrioxamine B. It is concluded that the range of active Schiff base derivatives is likely to be large and that some of these, although not necessarily any of the particular compounds described here, may prove to be of clinical use.