REM Sleep Stage Identification with Raw Single-Channel EEG.

This paper focused on creating an interpretable model for automatic rapid eye movement (REM) and non-REM sleep stage scoring for a single-channel electroencephalogram (EEG). Many methods attempt to extract meaningful information to provide to a learning algorithm. This method attempts to let the model extract the meaningful interpretable information by providing a smaller number of time-invariant signal filters for five frequency ranges using five CNN algorithms. A bi-directional GRU algorithm was applied to the output to incorporate time transition information. Training and tests were run on the well-known sleep-EDF-expanded database. The best results produced 97% accuracy, 93% precision, and 89% recall.

Attention Deficit Hyperactivity Disorder Classification Based on Deep Learning.

Attention Deficit Hyperactivity Disorder (ADHD) is a type of mental health disorder that can be seen from children to adults and affects patients' normal life. Accurate diagnosis of ADHD as early as possible is very important for the treatment of patients in clinical applications. Some traditional classification methods, although having been shown powerful in many other classification tasks, are not as successful in the application of ADHD classification. In this paper, we propose two novel deep learning approaches for ADHD classification based on functional magnetic resonance imaging. The first method incorporates independent component analysis with convolutional neural network. It first extracts independent components from each subject. The independent components are then fed into a convolutional neural network as input features to classify the ADHD patient from typical controls. The second method, called the correlation autoencoder method, uses correlations between regions of interest of the brain as the input of an autoencoder to learn latent features, which are then used in the classification task by a new neural network. These two methods use different ways to extract the inter-voxel information from fMRI, but both use convolutional neural networks to further extract predictive features for the classification task. Empirical experiments show that both methods are able to outperform the classical methods such as logistic regression, support vector machines, and other methods used in previous studies.

Extracting default mode network based on graph neural network for resting state fMRI study.

Functional magnetic resonance imaging (fMRI)-based study of functional connections in the brain has been highlighted by numerous human and animal studies recently, which have provided significant information to explain a wide range of pathological conditions and behavioral characteristics. In this paper, we propose the use of a graph neural network, a deep learning technique called graphSAGE, to investigate resting state fMRI (rs-fMRI) and extract the default mode network (DMN). Comparing typical methods such as seed-based correlation, independent component analysis, and dictionary learning, real data experiment results showed that the graphSAGE is more robust, reliable, and defines a clearer region of interests. In addition, graphSAGE requires fewer and more relaxed assumptions, and considers the single subject analysis and group subjects analysis simultaneously.

Elastic net-based framework for imaging mass spectrometry data biomarker selection and classification.

Imaging mass spectrometry (IMS) shows great potential for the rapid mapping of protein localization and for detecting of sizeable differences in protein expression. However, data processing remains challenging due to the difficulty of analyzing high dimensionality, the fact that the number of predictors is significantly larger than the number of observations, and the need to consider both spectral and spatial information in order to represent the advantage of IMS technology. Ideally one would like to efficiently analyze all acquired data to find trace features based on both spectral and spatial patterns. Therefore, biomarker selection from IMS data is a problem of global optimization. A recently developed regularization and variable selection method,elastic net (EN), produces a sparse model with admirable prediction accuracy and can be an effective tool for IMS data processing. In this paper, we incorporate a spatial penalty term into the EN model and develop anew tool for IMS data biomarker selection and classification. A comprehensive IMS data processing software package, called EN4IMS, is also presented. The results of applying our method to both simulated and real data show that the EN4IMS algorithm works efficiently and effectively for IMS data processing: producing a more precise listing of selected peaks, helping confirmation of new potential biomarkers discovery, and providing more accurate classification results.

Using ICD-10-AM codes to characterise hospital-acquired complications.

This paper describes the limitations of using the International Statistical Classification of Diseases and Related Health Problems, Tenth Revision, Australian Modification (ICD-10-AM) to characterise patient harm in hospitals. Limitations were identified during a project to use diagnoses flagged by Victorian coders as hospital-acquired to devise a classification of 144 categories of hospital acquired diagnoses (the Classification of Hospital Acquired Diagnoses or CHADx). CHADx is a comprehensive data monitoring system designed to allow hospitals to monitor their complication rates month-to-month using a standard method. Difficulties in identifying a single event from linear sequences of codes due to the absence of code linkage were the major obstacles to developing the classification. Obstetric and perinatal episodes also presented challenges in distinguishing condition onset, that is, whether conditions were present on admission or arose after formal admission to hospital. Used in the appropriate way, the CHADx allows hospitals to identify areas for future patient safety and quality initiatives. The value of timing information and code linkage should be recognised in the planning stages of any future electronic systems.

A novel comprehensive wave-form MS data processing method.

MOTIVATION: Mass spectrometry (MS) can generate high-throughput protein profiles for biomedical research to discover biologically related protein patterns/biomarkers. The noisy functional MS data collected by current technologies, however, require consistent, sensitive and robust data-processing techniques for successful biomedical application. Therefore, it is important to detect features precisely for each spectrum, quantify them well and assign a unique label to features from the same protein/peptide across spectra. RESULTS: In this article, we propose a new comprehensive MS data preprocessing package, Wave-spec, which includes several novel algorithms. It can overcome several conventional difficulties. Wave-spec can be applied to multiple types of MS data generated with different MS technologies. Results from this new package were evaluated and compared to several existing approaches based on a MALDI-TOF MS dataset. AVAILABILITY: An example of MATLAB scripts used to implement the methods described in this article, along with Supplementary Figures, can be found at http://www.vicc.org/biostatistics/supp.php. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Lineage development in a patient without goblet, paneth, and enteroendocrine cells: a clue for intestinal epithelial differentiation.

We report a patient who presented with severe enterocolitis and apparent absence of Paneth, goblet, and enteroendocrine lineages from the small bowel and colon. The absorptive enterocyte seemed to be normal morphologically and functionally. Because normal enterocytes were present, we hypothesized that this patient had a developmental block in the differentiation of a common stem cell precursor for Paneth, goblet, and neuroendocrine lineages. By using antibodies to protein markers of each cell line, including some that are expressed early in the differentiation process, we aimed to study lineage development in this patient. From our data, we surmise that there may be a two-step process in lineage commitment. The stem cell may commit to an absorptive cell or a granule-containing cell. The daughter cell that is committed to the granule lineage then further commits to a goblet, enteroendocrine, or Paneth cell lineage.

Surgical treatment of pulmonary aspergillosis / 대한흉부외과학회지

No abstract available.

Surgical treatment of metastatic lung cancer / 대한흉부외과학회지

No abstract available.

The changes of serum and urine potassium after extracorporeal circulation in open heart surgery / 대한흉부외과학회지

No abstract available.

Giant cell tumor arising from the rib: a case report / 대한흉부외과학회지

No abstract available.