Induction of Heme Oxygenase-1 Is Linked to the Severity of Disease in Human Abdominal Aortic Aneurysm.

Background Rupture of abdominal aortic aneurysm (rAAA) is associated with high case fatality rates, and risk of rupture increases with the AAA diameter. Heme oxygenase-1 (gene HMOX1, protein HO-1) is a stress-induced protein and induction has protective effects in the vessel wall. HMOX1-/- mice are more susceptible to angiotensin II-induced AAA formation, but the regulation in human nonruptured and ruptured AAA is only poorly understood. Our hypothesis proposed that HO-1 is reduced in AAA and lowering is inversely associated with the AAA diameter. Methods and Results AAA walls from patients undergoing elective open repair (eAAA) or surgery because of rupture (rAAA) were analyzed for aortic HMOX1/HO-1 expression by quantitative real-time polymerase chain reaction and Western blot. Aortas from patients with aortic occlusive disease served as controls. HMOX1/HO-1 expression was 1.1- to 7.6-fold upregulated in eAAA and rAAA. HO-1 expression was 3-fold higher in eAAA specimen with a diameter >84.4 mm, whereas HO-1 was not different in rAAA. Other variables that are known for associations with AAA and HO-1 induction were tested. In eAAA, HO-1 expression was negatively correlated with aortic collagen content and oxidative stress parameters H2O2 release, oxidized proteins, and thiobarbituric acid reactive substances. Serum HO-1 concentrations were analyzed in patients with eAAA, and maximum values were found in an aortic diameter of 55 to 70 mm with no further increase >70 mm, compared with <55 mm. Conclusions Aortic HO-1 expression was increased in eAAA and rAAA. HO-1 increased with the severity of disease but was additionally connected to less oxidative stress and vasoprotective mechanisms.

Automating the search for a patent's prior art with a full text similarity search.

More than ever, technical inventions are the symbol of our society's advance. Patents guarantee their creators protection against infringement. For an invention being patentable, its novelty and inventiveness have to be assessed. Therefore, a search for published work that describes similar inventions to a given patent application needs to be performed. Currently, this so-called search for prior art is executed with semi-automatically composed keyword queries, which is not only time consuming, but also prone to errors. In particular, errors may systematically arise by the fact that different keywords for the same technical concepts may exist across disciplines. In this paper, a novel approach is proposed, where the full text of a given patent application is compared to existing patents using machine learning and natural language processing techniques to automatically detect inventions that are similar to the one described in the submitted document. Various state-of-the-art approaches for feature extraction and document comparison are evaluated. In addition to that, the quality of the current search process is assessed based on ratings of a domain expert. The evaluation results show that our automated approach, besides accelerating the search process, also improves the search results for prior art with respect to their quality.

"What is relevant in a text document?": An interpretable machine learning approach.

Text documents can be described by a number of abstract concepts such as semantic category, writing style, or sentiment. Machine learning (ML) models have been trained to automatically map documents to these abstract concepts, allowing to annotate very large text collections, more than could be processed by a human in a lifetime. Besides predicting the text's category very accurately, it is also highly desirable to understand how and why the categorization process takes place. In this paper, we demonstrate that such understanding can be achieved by tracing the classification decision back to individual words using layer-wise relevance propagation (LRP), a recently developed technique for explaining predictions of complex non-linear classifiers. We train two word-based ML models, a convolutional neural network (CNN) and a bag-of-words SVM classifier, on a topic categorization task and adapt the LRP method to decompose the predictions of these models onto words. Resulting scores indicate how much individual words contribute to the overall classification decision. This enables one to distill relevant information from text documents without an explicit semantic information extraction step. We further use the word-wise relevance scores for generating novel vector-based document representations which capture semantic information. Based on these document vectors, we introduce a measure of model explanatory power and show that, although the SVM and CNN models perform similarly in terms of classification accuracy, the latter exhibits a higher level of explainability which makes it more comprehensible for humans and potentially more useful for other applications.

Robust artifactual independent component classification for BCI practitioners.

OBJECTIVE: EEG artifacts of non-neural origin can be separated from neural signals by independent component analysis (ICA). It is unclear (1) how robustly recently proposed artifact classifiers transfer to novel users, novel paradigms or changed electrode setups, and (2) how artifact cleaning by a machine learning classifier impacts the performance of brain-computer interfaces (BCIs). APPROACH: Addressing (1), the robustness of different strategies with respect to the transfer between paradigms and electrode setups of a recently proposed classifier is investigated on offline data from 35 users and 3 EEG paradigms, which contain 6303 expert-labeled components from two ICA and preprocessing variants. Addressing (2), the effect of artifact removal on single-trial BCI classification is estimated on BCI trials from 101 users and 3 paradigms. MAIN RESULTS: We show that (1) the proposed artifact classifier generalizes to completely different EEG paradigms. To obtain similar results under massively reduced electrode setups, a proposed novel strategy improves artifact classification. Addressing (2), ICA artifact cleaning has little influence on average BCI performance when analyzed by state-of-the-art BCI methods. When slow motor-related features are exploited, performance varies strongly between individuals, as artifacts may obstruct relevant neural activity or are inadvertently used for BCI control. SIGNIFICANCE: Robustness of the proposed strategies can be reproduced by EEG practitioners as the method is made available as an EEGLAB plug-in.

Predicting treatment response in social anxiety disorder from functional magnetic resonance imaging.

CONTEXT: Current behavioral measures poorly predict treatment outcome in social anxiety disorder (SAD). To our knowledge, this is the first study to examine neuroimaging-based treatment prediction in SAD. OBJECTIVE: To measure brain activation in patients with SAD as a biomarker to predict subsequent response to cognitive behavioral therapy (CBT). DESIGN: Functional magnetic resonance imaging (fMRI) data were collected prior to CBT intervention. Changes in clinical status were regressed on brain responses and tested for selectivity for social stimuli. SETTING: Patients were treated with protocol-based CBT at anxiety disorder programs at Boston University or Massachusetts General Hospital and underwent neuroimaging data collection at Massachusetts Institute of Technology. PATIENTS: Thirty-nine medication-free patients meeting DSM-IV criteria for the generalized subtype of SAD. INTERVENTIONS: Brain responses to angry vs neutral faces or emotional vs neutral scenes were examined with fMRI prior to initiation of CBT. MAIN OUTCOME MEASURES: Whole-brain regression analyses with differential fMRI responses for angry vs neutral faces and changes in Liebowitz Social Anxiety Scale score as the treatment outcome measure. RESULTS: Pretreatment responses significantly predicted subsequent treatment outcome of patients selectively for social stimuli and particularly in regions of higher-order visual cortex. Combining the brain measures with information on clinical severity accounted for more than 40% of the variance in treatment response and substantially exceeded predictions based on clinical measures at baseline. Prediction success was unaffected by testing for potential confounding factors such as depression severity at baseline. CONCLUSIONS: The results suggest that brain imaging can provide biomarkers that substantially improve predictions for the success of cognitive behavioral interventions and more generally suggest that such biomarkers may offer evidence-based, personalized medicine approaches for optimally selecting among treatment options for a patient.