Prediction of key milk biomarkers in dairy cows through milk mid-infrared spectra and international collaborations

At the individual cow level, suboptimum fertility, mastitis, negative energy balance, and ketosis are major issues in dairy farming. These problems are widespread on dairy farms and have an important economic impact. The objectives of this study were (1) to assess the potential of milk mid-infrared (MIR) spectra to predict key biomarkers of energy deficit (citrate, isocitrate, glucose-6 phosphate [glucose-6P], free glucose), ketosis (β-hydroxybutyrate [BHB] and acetone), mastitis (N-acetyl-β-d-glucosaminidase activity [NAGase] and lactate dehydrogenase), and fertility (progesterone); (2) to test alternative methodologies to partial least squares (PLS) regression to better account for the specific asymmetric distribution of the biomarkers; and (3) to create robust models by merging large datasets from 5 international or national projects. Benefiting from this international collaboration, the dataset comprised a total of 9,143 milk samples from 3,758 cows located in 589 herds across 10 countries and represented 7 breeds. The samples were analyzed by reference chemistry for biomarker contents, whereas the MIR analyses were performed on 30 instruments from different models and brands, with spectra harmonized into a common format. Four quantitative methodologies were evaluated to address the strongly skewed distribution of some biomarkers. Partial least squares regression was used as the reference basis, and compared with a random modification of distribution associated with PLS (random-downsampling-PLS), an optimized modification of distribution associated with PLS (KennardStone-downsampling-PLS), and support vector machine (SVM). When the ability of MIR to predict biomarkers was too low for quantification, different qualitative methodologies were tested to discriminate low versus high values of biomarkers. For each biomarker, 20% of the herds were randomly removed within all countries to be used as the validation dataset. The remaining 80% of herds were used as the calibration dataset. In calibration, the 3 alternative methodologies outperform the PLS performances for the majority of biomarkers. However, in the external herd validation, PLS provided the best results for isocitrate, glucose-6P, free glucose, and lactate dehydrogenase (coefficient of determination in external herd validation [R2v] = 0.48, 0.58, 0.28, and 0.24, respectively). For other molecules, PLS-random-downsampling and PLS-KennardStone-downsampling outperformed PLS in the majority of cases, but the best results were provided by SVM for citrate, BHB, acetone, NAGase, and progesterone (R2v = 0.94, 0.58, 0.76, 0.68, and 0.15, respectively). Hence, PLS and SVM based on the entire dataset provided the best results for normal and skewed distributions, respectively. Complementary to the quantitative methods, the qualitative discriminant models enabled the discrimination of high and low values for BHB, acetone, and NAGase with a global accuracy around 90%, and glucose-6P with an accuracy of 83%. In conclusion, MIR spectra of milk can enable quantitative screening of citrate as a biomarker of energy deficit and discrimination of low and high values of BHB, acetone, and NAGase, as biomarkers of ketosis and mastitis. Finally, progesterone could not be predicted with sufficient accuracy from milk MIR spectra to be further considered. Consequently, MIR spectrometry can bring valuable information regarding the occurrence of energy deficit, ketosis, and mastitis in dairy cows, which in turn have major influences on their fertility and survival.

Local excision after neoadjuvant chemoradiotherapy versus total mesorectal excision: a case-matched study in 110 selected high-risk patients with rectal cancer

AIM

The aim of this comparative study was to report a 10-year experience of an organ preservation strategy by local excision (LE) in selected high-risk patients (aged patients and/or patients with severe comorbidity and/or indication for abdominoperineal excision) versus total mesorectal excision (TME) after neoadjuvant radiochemotherapy (RCT) for patients with locally advanced (T3-T4 and/or N+) low and mid rectal cancer with suspicion of complete tumour response (CTR) or near-CTR.

METHOD

Thirty-nine patients with rectal cancer who underwent LE after RCT for suspicion of CTR were matched to 71 patients who underwent TME according to body mass index, gender, tumour location and ypTNM stage. Operative, oncological and functional results were compared between groups.

RESULTS

In the LE group, ypT0, ypTis or ypT1N0R0 were noted in 28/39 (72%). Overall morbidity was observed in 10/39 (26%) in LE vs 46/71 in the TME group (65%) (P = 0.001). Severe morbidity (Clavien-Dindo ≥ 3) was noted in 1/39 patients from the LE group (3%) vs 3/71 (4%) from the TME group (P = 1.000). After a mean follow-up of 63 ± 4 months (range 56-70 months), local recurrence was noted in 2/39 (5%) from the LE group vs 2/71 (3%) from the TME group (P = 0.601). Definitive stoma was noted in 2/39 (6%) from the LE group vs 8/71 (12%) from the TME group (P = 0.489). Major low anterior resection syndrome was noted in 5/23 (22%) from LE group vs 11/33 (33%) from the TME group (P = 0.042).

CONCLUSION

The accuracy of response prediction after RCT was 72% after LE. In high-risk patients, LE represents a safe alternative to TME with better functional results and the same long-term oncological outcome.

A comparison of 4 different machine learning algorithms to predict lactoferrin content in bovine milk from mid-infrared spectra

Lactoferrin (LF) is a glycoprotein naturally present in milk. Its content varies throughout lactation, but also with mastitis; therefore it is a potential additional indicator of udder health beyond somatic cell count. Condequently, there is an interest in quantifying this biomolecule routinely. First prediction equations proposed in the literature to predict the content in milk using milk mid-infrared spectrometry were built using partial least square regression (PLSR) due to the limited size of the data set. Thanks to a large data set, the current study aimed to test 4 different machine learning algorithms using a large data set comprising 6,619 records collected across different herds, breeds, and countries. The first algorithm was a PLSR, as used in past investigations. The second and third algorithms used partial least square (PLS) factors combined with a linear and polynomial support vector regression (PLS + SVR). The fourth algorithm also used PLS factors, but included in an artificial neural network with 1 hidden layer (PLS + ANN). The training and validation sets comprised 5,541 and 836 records, respectively. Even if the calibration prediction performances were the best for PLS + polynomial SVR, their validation prediction performances were the worst. The 3 other algorithms had similar validation performances. Indeed, the validation root mean squared error (RMSE) ranged between 162.17 and 166.75 mg/L of milk. However, the lower standard deviation of cross-validation RMSE and the better normality of the residual distribution observed for PLS + ANN suggest that this modeling was more suitable to predict the LF content in milk from milk mid-infrared spectra (R²v = 0.60 and validation RMSE = 162.17 mg/L of milk). This PLS +ANN model was then applied to almost 6 million spectral records. The predicted LF showed the expected relationships with milk yield, somatic cell score, somatic cell count, and stage of lactation. The model tended to underestimate high LF values (higher than 600 mg/L of milk). However, if the prediction threshold was set to 500 mg/L, 82% of samples from the validation having a content of LF higher than 600 mg/L were detected. Future research should aim to increase the number of those extremely high LF records in the calibration set.

Can we refine the management of blunt liver trauma?

AIM

To describe the management of blunt liver injury and to study the potential relation between delayed complications, type of trauma mechanisms and liver lesions.

PATIENTS AND METHODS

This is a retrospective single center study including 116 consecutive patients admitted with blunt liver injury between 2007 and 2015.

RESULTS

Initial CT-scan identified an active bleeding in 33 (28%) patients. AAST (American Association for the Surgery of Trauma) grade was 1 to 3 in 82 (71%) patients and equal to 5 in 15 (13%) patients. Eighty (69%) patients had NOM, with a success rate of 96%. Other abdominal organ lesions were associated to invasive initial management. A follow-up CT-scan was useful to detect hepatic and extra-hepatic complications (46 complications in 80 patients), even without clinical or biological abnormalities. Subsequent hepatic complications such as bleeding, pseudo aneurysms, biloma and biliary peritonitis developed in 15 patients and were associated with the severity of blunt liver injury according to AAST classification (3.7±1.0 vs. 3.0±1.1, P=0.010). Total biliary complications occurred in 13 patients and were significantly more frequently observed in patients with injury of central segments 1, 4 and 9 (69% vs. 36%, P=0.033).

CONCLUSIONS

Non-operative management is possible in most blunt liver injury with a success rate of 96%. A systematic CT-scan should be advocated during follow-up, especially when AAST grade is equal or superior to 3. Biliary complications should be suspected when lesions involve segments 1, 4 and 9.