What are the novel findings of this work?In patients with low-implantation pregnancy in the first trimester, presence of three or more placental lacunae was strongly associated with placenta accreta spectrum (PAS), with a median of five lacunae present in cases with PAS compared with a median of one lacuna in controls without PAS. Presence of an abnormal uteroplacental interface and lower uterine segment hypervascularity were also strongly associated with PAS. What are the clinical implications of this work?This study contributes valuable evidence demonstrating the feasibility and accuracy of first-trimester ultrasound in diagnosing PAS in at-risk women with low-implantation pregnancy, using well-defined secondand third-trimester ultrasound markers. Introduction of a systematic approach to ultrasound examination in the first trimester would give providers an additional and earlier opportunity to diagnose PAS and would increase the diagnostic value of later scans.

<div id="titleAndAbstract"><p class="0abstract">Breast cancer poses the greatest threat to human life and especially to women's life. Despite the progress made in data mining technology in recent years, the ability to predict and diagnose such fatal diseases based on gene expression data still reveals a limited prediction performance, which may not be surprising since most of the genes in expression data are believed to be irrelevant or redundant. The dimensionality reduction process may be considered as a crucial step to analyze gene expression data, as it can reduce the high dimensionality of the breast cancer datasets, which may result into a better prediction performance of such diseases. The paper suggests a new hybrid approach-based gene selection that combines the filter method and the Ant Colony Optimization algorithm to find the smallest subset of informative genes (genes markers) among 24,481 genes. The proposed approach combines four machine learning algorithms - C5.0 Decision Tree, Support Vector Machines, K-Nearest Neighbors algorithm, and Random Forest Classifier - to classify each of the selected samples (patients) into two classes which have cancer or not.  Compared with existing methods in the literature, experimental results indicate that our proposed gene selection approach achieved globally higher classification accuracies with a relatively smaller number of genes.</p></div>

Introduction The advent of the Gastrograffin® small bowel follow through (G-SBFT) has resulted in a decreased rate of operative intervention of small bowel obstructions (SBO); however, there is no data to suggest when G-SBFT should be performed. Methods We retrospectively reviewed 548 patients, admitted to 1 of 9 hospitals with a diagnosis of SBO. Patients were divided into two categories with regards to timing of G-SBFT: before (early) or after (late) 48 hours from admission. Primary outcomes were length of stay (LOS) and total cost. Secondary outcomes were operative interventions and mortality. Results Of the reviewed patients, 71% had the G-SBFT ordered early. Comparing early versus late, there were no differences in patient characteristics with regards to age, sex, or BMI. There was a significant difference between LOS (4 vs 8 days, P < 0.05) and total cost ($17,056.19 vs $33,292.00, P < 0.05). There was no difference in mortality (1.3% vs 2.6%, P = 0.239) or 30-day readmission rates (15.6% vs 15.9%, P = 0.509). Patients in the early group underwent fewer operations (20.7% vs 31.9%, P = 0.05). Discussion Patients that had a G-SBFT ordered early had a decreased LOS, total cost, and operative intervention. This suggests there is a benefit to ordering G-SBFT earlier in the hospital stay to reduce the overall disease burden, and that it is safe to do so with regards to mortality and readmissions. We therefore recommend ordering a G-SBFT within 48 hours to reduce LOS, cost, and need for an operation

No abstract

Human activity recognition (HAR) is an emerging research topic in pattern recognition, especially in computer vision. The main objective of human activity recognition is to automatically detect and analyze human activities from the information acquired from different sensors. Human activity prediction using big data remains a challengingly open problem. Several approaches have recently been developed in order to find practical ways to solve high dimensionality of data problems. The aim of this study is to attempt, using data mining techniques, to deal with HAR modeling involving a significant number of variables in order to identify relevant parameters from data and thus to maximize the classification accuracy while minimizing the number of features. The proposed framework has 1032 Ismail El Moudden et al. been tested on a publicly HAR available dataset and the results have been interpreted and discussed.

No abstract

Polyomavirus associated nephropathy (PyVAN) continues to be a burden in renal transplantation leading to allograft insufficiency or graft failure. A presumptive diagnosis of PyVAN is made based on the presence of BK polyomavirus in patients' plasma; however, kidney biopsy remains the gold standard to establish a definitive diagnosis. The Banff Working Group on PyVAN proposed a novel classification of definitive PyVAN based on polyomavirus replication/load level and the extent of interstitial fibrosis. The aim of our study was to test the newly defined classes of PyVAN using independent cohorts of 124 kidney transplant patients with PyVAN with respect to the initial presentation and outcome, and to compare our analysis to that previously reported. Detailed analysis of our cohort revealed that the proposed classification of PyVAN did not stratify or identify patients at increased risk of allograft failure. Specifically, while class 3 was associated with the worst prognosis, there was no significant difference between the outcomes in classes 1 and 2. We also found that the timing posttransplantation and inflammation in areas of interstitial fibrosis and tubular atrophy might be additional factors contributing to an unfavorable allograft outcome in patients with PyVAN.

No abstract