Corcoran Morrison (linkvessel98)

Malignant pleural mesothelioma (MPM) is often associated with a poor prognosis and options for the treatment of this disease are few. To date, the important role of the immune microenvironment in modifying the disease natural history is well established. The programmed cell death pathway (PD-1/PD-L1) limits the T lymphocyte activation in peripheral tissues when an inflammatory response occurs, and controls the tumour immune escape. PD-L1 is broadly expressed in several malignant tumours and associated with poor clinical outcomes. Thus, the aim of our study is to investigate the potential role of PD-L1 expression in MPM prognosis. Biopsy samples from 198 patients diagnosed with MPM were examined by immunohistochemistry (IHC) and reverse transcription-polymerase chain reaction (RT-PCR) to evaluate PD-L1 protein and gene expression. For PD-L1 protein expression we consider at least 5% membranous staining as positive. Gene expression levels were calculated with ΔΔCt method. Positive expression of PD-L1 by IHC was correlated with worse overall survival (OS; p=0.0225) in MPM patients. PD-L1 positive status was correlated with worse OS in the subgroup of patients with ECOG score less then 2 (p=0.0004, n=129) and these data were confirmed by multivariate analysis. No significant correlation was found between PD-L1 gene expression and OS. Our results show that PD-L1 evaluated by IHC assay may be a prognostic biomarker for MPM patients with good performance status. Physiological time series are common data sources in many health applications. Mining data from physiological time series is crucial for promoting healthy living and reducing governmental medical expenditure. Recently, research and applications of deep learning methods on physiological time series have developed rapidly because such data can be continuously recorded by smart wristbands or smartwatches. However, existing deep learning methods suffer from excessive model complexity and a lack of explanation. This paper aims to handle these issues. We propose TEG-net, which is a novel deep learning method for accurately diagnosing and explaining physiological time series. BI9787 TEG-net constructs T-net (a multi-scale bi-directional temporal convolutional neural network) to model physiological time series directly, E-net (personalized linear model) to model expert features extracted from physiological time series, and G-net (gating neural network) to combine T-net and E-net for diagnosis. The combination of T-net and E-net through G-net improves diagnosis accuracy and E-net can be utilized for explanation. Experimental results demonstrate that TEG-net outperforms the second-best baseline by 13.68% in terms of area under the receiver operating characteristic curve and 11.49% in terms of area under the precision-recall curve. Additionally, intuitive justifications can be provided to explain model predictions. This paper develops an ensemble method to combine expert features and deep learning method for modeling physiological time series. Improvements in diagnostic accuracy and explanation make TEG-net applicable to many real-world health applications. This paper develops an ensemble method to combine expert features and deep learning method for modeling physiological time series. Improvements in diagnostic accuracy and explanation make TEG-net applicable to many real-world health applications. The Edinburgh Postnatal Depression Scale (EPDS) and Patient Health Questionnaire-9 (PHQ-9) are widely used depression screening tools, yet perceptions and understandings of their questions and of depression are not well defined in cross-cultural research. 30 postpartum women living with HIV in Malawi were recruited from a cohort study and participated in in-depth cognitive interviews. Transcripts were evaluated following an inductive approach to identify common themes. Participants most frequently described look