Objective We sought to predict if patients with type 2 diabetes mellitus (DM2) would develop 10 selected complications. Accurate prediction of complications could help with more targeted measures that would prevent or slow down their development. Materials and Methods Experiments were conducted on the Healthcare Cost and Utilization Project State Inpatient Databases of California for the period of 2003 to 2011. Recurrent neural network (RNN) long short-term memory (LSTM) and RNN gated recurrent unit (GRU) deep learning methods were designed and compared with random forest and multilayer perceptron traditional models. Prediction accuracy of selected complications were compared on 3 settings corresponding to minimum number of hospitalizations between diabetes diagnosis and the diagnosis of complications. Results The diagnosis domain was used for experiments. The best results were achieved with RNN GRU model, followed by RNN LSTM model. The prediction accuracy achieved with RNN GRU model was between 73% (myocardial infarction) and 83% (chronic ischemic heart disease), while accuracy of traditional models was between 66% – 76%. Discussion The number of hospitalizations was an important factor for the prediction accuracy. Experiments with 4 hospitalizations achieved significantly better accuracy than with 2 hospitalizations. To achieve improved accuracy deep learning models required training on at least 1000 patients and accuracy significantly dropped if training datasets contained 500 patients. The prediction accuracy of complications decreases over time period. Considering individual complications, the best accuracy was achieved on depressive disorder and chronic ischemic heart disease. Conclusions The RNN GRU model was the best choice for electronic medical record type of data, based on the achieved results.

Social scientists have shown that up to 50% of the comments posted to a news article have no relation to its journalistic content. In this study we propose a classification algorithm to categorize user comments posted to a news article based on their alignment to its content. The alignment seeks to match user comments to an article based on similarity of content, entities in discussion, and topics. We propose a BERTAC, BERT-based approach that learns jointly article-comment embeddings and infers the relevance class of comments. We introduce an ordinal classification loss that penalizes the difference between the predicted and true labels. We conduct a thorough study to show influence of the proposed loss on the learning process. The results on five representative news outlets show that our approach can learn the comment class with up to 36% average accuracy improvement comparing to the baselines, and up to 25% comparing to the BA-BC. BA-BC is our approach that consists of two models aimed to capture dis-jointly the formal language of news articles and the informal language of comments. We also conduct a user study to evaluate human labeling performance to understand the difficulty of the classification task. The user agreement on comment-article alignment is "moderate" per Krippendorff's alpha score, which suggests that the classification task is difficult. Keywords: Text mining • Text classification • Online news • News comments • Relevancy • Understanding user-generated text J. Alshehri and M. Stanojevic-contributed equally.

No abstract

Takayasu arteritis (TA) is characterized by granulomatous panarteritis, vessel wall fibrosis, and irreversible vascular impairment. The aim of this study is to explore the usefulness of the Enhanced Liver Fibrosis score (ELF), procollagen-III aminoterminal propeptide (PIIINP), tissue inhibitor of matrix metalloproteinase-1 (TIMP-1), and hyaluronic acid (HA) in assessing vascular damage in TA patients. ELF, PIIINP, TIMP-1, and HA were measured in 24 TA patients, and the results were correlated with the clinical damage indexes (VDI and TADS), an imaging damage score (CARDS), and disease activity scores (NIH and ITAS2010). A mean ELF score 8.42 (±1.12) and values higher than 7.7 (cut-off for liver fibrosis) in 21/24 (87.5%) of patients were detected. The VDI and TADS correlated significantly to ELF (p < 0.01). Additionally, a strong association across ELF and CARDS (p < 0.0001), PIIINP and CARDS (p < 0.001), and HA and CARDS (p < 0.001) was observed. No correlations of the tested biomarkers with inflammatory parameters, NIH, and ITAS2010 scores were found. To our knowledge, this is the first study that suggests the association of the serum biomarkers PIIINP, HA, and ELF score with damage but not with disease activity in TA patients. The ELF score and PIIINP may be useful biomarkers reflecting an ongoing fibrotic process and quantifying vascular damage.

HIV/HCV co-infection was found to be more prevalent than HIV/HBV co-infection in a Serbian cohort. Co-infection with HCV was related to more profound immunodeficiency prior to therapy initiation, reflecting a possible unfavorable impact of HCV on the natural history of HIV infection.