No abstract

Growing evidence shows that inflammation has a pivotal role in the pathophysiology of essential hypertension (EH). Although it has been acknowledged that target organ damage involves an inflammatory response, most work has focused on the role of macrophages, but T lymphocytes have recently become the center of interest. The goal of our study was to evaluate the role of T-cell-specific cytokines in the pathogenesis of EH. The study examined 39 patients with EH (57.7±6.8 years, systolic blood pressure (SBP) 157.5 ± 11.8 mm Hg, diastolic blood pressure 92.2 ± 12.9 mm Hg, mean arterial pressure 113.9 ± 12.6 mm Hg) and 30 healthy, normotensive controls (55.2 ± 4.9 years). Blood was drawn from a peripheral vein, and serum levels of interferon-inducible protein (IP)-10 and interleukins (IL)-4, -7 and -13 were measured by a multiplexing assay. Hypertensive patients had significantly higher levels of IP-10, IL-4, IL-7 and IL-13 than control subjects. When the patients were classified into tertiles according to their serum IP-10 levels (T1: 41.2-94.1 pg ml À1 ; T2: 103.4-162.5 pg ml À1 ; T3: 171.7-443.5 pg ml À1 ), the patients classified into the highest tertile also had the highest blood pressure. In a correlation analysis, plasma IP-10 concentration was significantly associated with SBP (r¼0.59, Po0.001). Furthermore, hypertensives with microalbuminuria, an early sign of hypertensive target organ damage, had the highest IP-10 levels. A stepwise multivariate regression analysis revealed IP-10 as the strongest independent predictor of SBP (P¼0.01). In conclusion, our study provides new insights into the pathophysiological mechanisms in EH linking inflammation and IP-10. However, these preliminary results need to be confirmed in larger trials.

No abstract

The number of published PDF documents in both the academic and commercial world has increased exponentially in recent decades. There is a growing need to make their rich content discoverable to information retrieval tools. Achieving high-quality semantic searches demands that a document's structural components such as title, section headers, paragraphs, (nested) lists, tables and figures (including their captions) are properly identified. Unfortunately, the PDF format is known to not conserve such structural information because it simply represents a document as a stream of low-level printing commands, in which one or more characters are placed in a bounding box with a particular styling. In this paper, we present a novel approach to document structure recovery in PDF using recurrent neural networks to process the low-level PDF data representation directly, instead of relying on a visual re-interpretation of the rendered PDF page, as has been proposed in previous literature. We demonstrate how a sequence of PDF printing commands can be used as input into a neural network and how the network can learn to classify each printing command according to its structural function in the page. This approach has three advantages: First, it can distinguish among more fine-grained labels (typically 10-20 labels as opposed to 1-5 with visual methods), which results in a more accurate and detailed document structure resolution. Second, it can take into account the text flow across pages more naturally compared to visual methods because it can concatenate the printing commands of sequential pages. Last, our proposed method needs less memory and it is computationally less expensive than visual methods. This allows us to deploy such models in production environments at a much lower cost. Through extensive architectural search in combination with advanced feature engineering, we were able to implement a model that yields a weighted average F1 score of 97% across 17 distinct structural labels. The best model we achieved is currently served in production environments on our Corpus Conversion Service (CCS), which was presented at KDD18. This model enhances the capabilities of CCS significantly, as it eliminates the need for human annotated label ground-truth for every unseen document layout. This proved particularly useful when applied to a huge corpus of PDF articles related to COVID-19.

Over the past few decades, the amount of scientific articles and technical literature has increased exponentially in size. Consequently, there is a great need for systems that can ingest these documents at scale and make the contained knowledge discoverable. Unfortunately, both the format of these documents (e.g. the PDF format or bitmap images) as well as the presentation of the data (e.g. complex tables) make the extraction of qualitative and quantitive data extremely challenging. In this paper, we present a modular, cloud-based platform to ingest documents at scale. This platform, called the Corpus Conversion Service (CCS), implements a pipeline which allows users to parse and annotate documents (i.e. collect ground-truth), train machine-learning classification algorithms and ultimately convert any type of PDF or bitmap-documents to a structured content representation format. We will show that each of the modules is scalable due to an asynchronous microservice architecture and can therefore handle massive amounts of documents. Furthermore, we will show that our capability to gather ground-truth is accelerated by machine-learning algorithms by at least one order of magnitude. This allows us to both gather large amounts of ground-truth in very little time and obtain very good precision/recall metrics in the range of 99% with regard to content conversion to structured output. The CCS platform is currently deployed on IBM internal infrastructure and serving more than 250 active users for knowledge-engineering project engagements.