Machine learning methods are used to discover complex nonlinear relationships in biological and medical data. However, sophisticated learning models are computationally unfeasible for data with millions of features. Here, we introduce the first feature selection method for nonlinear learning problems that can scale up to large, ultra-high dimensional biological data. More specifically, we scale up the novel Hilbert-Schmidt Independence Criterion Lasso (HSIC Lasso) to handle millions of features with tens of thousand samples. The proposed method is guaranteed to find an optimal subset of maximally predictive features with minimal redundancy, yielding higher predictive power and improved interpretability. Its effectiveness is demonstrated through applications to classify phenotypes based on module expression in human prostate cancer patients and to detect enzymes among protein structures. We achieve high accuracy with as few as 20 out of one million features—a dimensionality reduction of 99.998 percent. Our algorithm can be implemented on commodity cloud computing platforms. The dramatic reduction of features may lead to the ubiquitous deployment of sophisticated prediction models in mobile health care applications.

This paper represents the process of an on-going participatory action research project within a city affected by the socio-economic crisis. The focus of the research is to explore the possibilities of transforming idle capacity of skilled professionals into job opportunities through service design and defining strategies for designing a new value creation system between members in a community. The existing complementary currency models serve as an inspiration and foundation for conducting the research in collaborative and creative spaces, using a bottom-up approach in designing this service with the potential users in order to create value for that community. This could be achieved by giving shape to a service with its evidences as a framework to adapt to current conditions in peer-to-peer interactions. If a successful long-term and not only crisis-driven model could be designed, prototyped and globally replicated, based on debt-credit system and knowledge economy with enormous benefits of access to products and services, then it could enhance economic efficiency and distribute social capital while promoting new forms of entrepreneurship.

Introduction. We report a case of a sixty-year-old man diagnosed with gluteal compartment syndrome caused by traumatic rupture of the superior gluteal artery associated with fracture of the inferior pubic ramus and blunt trauma. Case report. A patient was injured falling from a height of four meters. Signs of compartment syndrome and sciatic nerve compression developed three hours after the injury. The patient went through a computerized tomography (CT) scan procedure with contrast, which showed a hematoma in the gluteal region, but without signs of active bleeding. However, after observation and monitoring of the patient, CT angiography was performed which revealed a rupture of the superior gluteal artery. Fasciotomy and debridement were performed and the patient was diagnosed with gluteal compartment syndrome and rupture of the superior gluteal artery. Surgery resulted in a significant improvement of the patient’s condition. Conclusion. Traumatic gluteal compartment syndrome is a rare condition. Gluteal compartment syndrome should be taken into consideration in each patient with pelvic trauma and hematoma in the gluteal region whose neurological status is affected. Prompt diagnosis and fasciotomy are crucial in the treatment and fasciotomy presents the gold standard in the treatment.

Background:Global DNA methylation has been reported to be associated with urothelial cell carcinoma (UCC) by studies using blood samples collected at diagnosis. Using the Illumina HumanMethylation450 assay, we derived genome-wide measures of blood DNA methylation and assessed them for their prospective association with UCC risk.Methods:We used 439 case–control pairs from the Melbourne Collaborative Cohort Study matched on age, sex, country of birth, DNA sample type, and collection period. Conditional logistic regression was used to compute odds ratios (OR) of UCC risk per s.d. of each genome-wide measure of DNA methylation and 95% confidence intervals (CIs), adjusted for potential confounders. We also investigated associations by disease subtype, sex, smoking, and time since blood collection.Results:The risk of superficial UCC was decreased for individuals with higher levels of our genome-wide DNA methylation measure (OR=0.71, 95% CI: 0.54–0.94; P=0.02). This association was particularly strong for current smokers at sample collection (OR=0.47, 95% CI: 0.27–0.83). Intermediate levels of our genome-wide measure were associated with decreased risk of invasive UCC. Some variation was observed between UCC subtypes and the location and regulatory function of the CpGs included in the genome-wide measures of methylation.Conclusions:Higher levels of our genome-wide DNA methylation measure were associated with decreased risk of superficial UCC and intermediate levels were associated with reduced risk of invasive disease. These findings require replication by other prospective studies.

The aim of this study was to clarify the clinical role of CD44 expression in ovarian serous cancer, and its relation to clinicopathologic prognostic factors, disease free survival and overall survival (OS). Immunohistochemical staining for CD44 was performed on 81 formalin-fixed, paraffin-embedded tumor sections. CD44 expression was found in 43% of ovarian carcinoma samples. Correlations between categorical variables were studied using the &khgr;2 and the Mann-Whitney U test. For survival analysis, the Kaplan-Meier method, the log-rank test and the Cox proportional hazard regression model were used. We did not find any statistically significant difference in the distribution of respondents according to clinical stage of the disease, tumor grade or the presence of vascular invasion in relation to the expression of CD44. According to the results of uninominal analysis, early International Federation of Gynecology and Obstetrics (FIGO) stage of the disease (P=0.003) was associated with longer disease free survival, while the expression of CD44 (P<0.001), FIGO stage III and IV (P=0.009) and the finding of vascular invasion (P=0.005) was related to a shorter OS. In conclusion, we proved that positive CD44 immunoexpression is a independent prognostic indicator of shorter OS of patients with ovarian serous cancer.

Mammary analogue secretory carcinoma (MASC) is a recently described low-grade malignant tumor of the salivary glands, biologically and morphologically equivalent to secretory breast carcinoma. We give a brief overview of this new entity, including morphological, immunohistochemical, molecular-genetic, clinical, epidemiologic features, differential diagnosis, and outcome results.