Table of contentsP001 - Sepsis impairs the capillary response within hypoxic capillaries and decreases erythrocyte oxygen-dependent ATP effluxR. M. Bateman, M. D. Sharpe, J. E. Jagger, C. G. EllisP002 - Lower serum immunoglobulin G2 level does not predispose to severe flu.J. Solé-Violán, M. López-Rodríguez, E. Herrera-Ramos, J. Ruíz-Hernández, L. Borderías, J. Horcajada, N. González-Quevedo, O. Rajas, M. Briones, F. Rodríguez de Castro, C. Rodríguez GallegoP003 - Brain protective effects of intravenous immunoglobulin through inhibition of complement activation and apoptosis in a rat model of sepsisF. Esen, G. Orhun, P. Ergin Ozcan, E. Senturk, C. Ugur Yilmaz, N. Orhan, N. Arican, M. Kaya, M. Kucukerden, M. Giris, U. Akcan, S. Bilgic Gazioglu, E. TuzunP004 - Adenosine a1 receptor dysfunction is associated with leukopenia: A possible mechanism for sepsis-induced leukopeniaR. Riff, O. Naamani, A. DouvdevaniP005 - Analysis of neutrophil by hyper spectral imaging - A preliminary reportR. Takegawa, H. Yoshida, T. Hirose, N. Yamamoto, H. Hagiya, M. Ojima, Y. Akeda, O. Tasaki, K. Tomono, T. ShimazuP006 - Chemiluminescent intensity assessed by eaa predicts the incidence of postoperative infectious complications following gastrointestinal surgeryS. Ono, T. Kubo, S. Suda, T. Ueno, T. IkedaP007 - Serial change of c1 inhibitor in patients with sepsis – A prospective observational studyT. Hirose, H. Ogura, H. Takahashi, M. Ojima, J. Kang, Y. Nakamura, T. Kojima, T. ShimazuP008 - Comparison of bacteremia and sepsis on sepsis related biomarkersT. Ikeda, S. Suda, Y. Izutani, T. Ueno, S. OnoP009 - The changes of procalcitonin levels in critical patients with abdominal septic shock during blood purificationT. Taniguchi, M. OP010 - Validation of a new sensitive point of care device for rapid measurement of procalcitoninC. Dinter, J. Lotz, B. Eilers, C. Wissmann, R. LottP011 - Infection biomarkers in primary care patients with acute respiratory tract infections – Comparison of procalcitonin and C-reactive proteinM. M. Meili, P. S. SchuetzP012 - Do we need a lower procalcitonin cut off?H. Hawa, M. Sharshir, M. Aburageila, N. SalahuddinP013 - The predictive role of C-reactive protein and procalcitonin biomarkers in central nervous system infections with extensively drug resistant bacteriaV. Chantziara, S. Georgiou, A. Tsimogianni, P. Alexandropoulos, A. Vassi, F. Lagiou, M. Valta, G. Micha, E. Chinou, G. MichaloudisP014 - Changes in endotoxin activity assay and procalcitonin levels after direct hemoperfusion with polymyxin-b immobilized fiberA. Kodaira, T. Ikeda, S. Ono, T. Ueno, S. Suda, Y. Izutani, H. ImaizumiP015 - Diagnostic usefullness of combination biomarkers on ICU admissionM. V. De la Torre-Prados, A. Garcia-De la Torre, A. Enguix-Armada, A. Puerto-Morlan, V. Perez-Valero, A. Garcia-AlcantaraP016 - Platelet function analysis utilising the PFA-100 does not predict infection, bacteraemia, sepsis or outcome in critically ill patientsN. Bolton, J. Dudziak, S. Bonney, A. Tridente, P. NeeP017 - Extracellular histone H3 levels are in...

Use of online social networks (OSNs) undoubtedly brings the world closer. OSNs like Twitter provide a space for expressing one’s opinions in a public platform. This great potential is misused by the creation of bot accounts, which spread fake news and manipulate opinions. Hence, distinguishing genuine human accounts from bot accounts has become a pressing issue for researchers. In this paper, we propose a framework based on deep learning to classify Twitter accounts as either ‘human’ or ‘bot.’ We use the information from user profile metadata of the Twitter account like description, follower count and tweet count. We name the framework ‘DeeProBot,’ which stands for Deep Profile-based Bot detection framework. The raw text from the description field of the Twitter account is also considered a feature for training the model by embedding the raw text using pre-trained Global Vectors (GLoVe) for word representation. Using only the user profile-based features considerably reduces the feature engineering overhead compared with that of user timeline-based features like user tweets and retweets. DeeProBot handles mixed types of features including numerical, binary, and text data, making the model hybrid. The network is designed with long short-term memory (LSTM) units and dense layers to accept and process the mixed input types. The proposed model is evaluated on a collection of publicly available labeled datasets. We have designed the model to make it generalizable across different datasets. The model is evaluated using two ways: testing on a hold-out set of the same dataset; and training with one dataset and testing with a different dataset. With these experiments, the proposed model achieved AUC as high as 0.97 with a selected set of features.

No abstract

Background: Preterm deliveries have many negative health implications on both mother and child. Identifying the population level factors that increase the risk of preterm deliveries is an important step in the direction of mitigating the impact and reducing the frequency of occurrence of preterm deliveries. The purpose of this work is to identify preterm delivery risk factors and their progression throughout the pregnancy from a large collection of Electronic Health Records (EHR). Results: The study cohort includes more than 60,000 deliveries in the USA with the complete medical history from EHR for diagnoses, medications, procedures and demographics. We propose a temporal analysis of risk factors by estimating and comparing risk ratios at different time points prior to the delivery event. We selected the following time points before delivery: 9, 6, 3 and 1 month(s). We did so by conducting a retrospective cohort study of patient history for a selected set of mothers who delivered preterm and a control group of mothers that delivered full-term. We analyzed the extracted data using a logistic regression model. The results of our analyses showed that the highest risk ratio corresponds to history of previous preterm delivery. Other risk factors were identified, some of which are consistent with those that are reported in the literature, others need further investigation. Conclusions: The comparative analysis of the risk factors at different time points showed that risk factors in the early pregnancy related to patient history and chronic condition, while the risk factors in late pregnancy are specific to the current pregnancy. Our analysis unifies several previously reported studies on preterm risk factors. It also gives important insights on the changes of risk factors in the course of pregnancy.

In this paper we are interested in the prediction of preterm birth based on diagnosis codes from longitudinal EHR. We formulate the prediction problem as a supervised classification with noisy labels. Our base classifier is a Recurrent Neural Network with an attention mechanism. We assume the availability of a data subset with both noisy and clean labels. For the cohort definition, most of the diagnosis codes on mothers' records related to pregnancy are ambiguous for the definition of full-term and preterm classes. On the other hand, diagnosis codes on babies' records provide fine-grained information on prematurity. Due to data de-identification, the links between mothers and babies are not available. We developed a heuristic based on admission and discharge times to match babies to their mothers and hence enrich mothers' records with additional information on delivery status. The obtained additional dataset from the matching heuristic has noisy labels and was used to leverage the training of the deep learning model. We propose an Alternating Loss Correction (ALC) method to train deep models with both clean and noisy labels. First, the label corruption matrix is estimated using the data subset with both noisy and clean labels. Then it is used in the model as a dense output layer to correct for the label noise. The network is alternately trained on epochs with the clean dataset with a simple cross-entropy loss and on next epoch with the noisy dataset and a loss corrected with the estimated corruption matrix. The experiments for the prediction of preterm birth at 90 days before delivery showed an improvement in performance compared with baseline and state of-the-art methods.