SUPPLEMENT Peterson, Thomas C.; Heim, Richard R.; Hirsch, Robert ...
Bulletin of the American Meteorological Society,
06/2013, Letnik:
94, Številka:
6
Journal Article
Electronic health records (EHR) contain a large variety of information on the clinical history of patients such as vital signs, demographics, diagnostic codes and imaging data. The enormous potential ...for discovery in this rich dataset is hampered by its complexity and heterogeneity. We present the first study to assess unsupervised homogenization pipelines designed for EHR clustering. To identify the optimal pipeline, we tested accuracy on simulated data with varying amounts of redundancy, heterogeneity, and missingness. We identified two optimal pipelines: 1) Multiple Imputation by Chained Equations (MICE) combined with Local Linear Embedding; and 2) MICE, Z-scoring, and Deep Autoencoders.
Predicting future clinical events helps physicians guide appropriate intervention. Machine learning has tremendous promise to assist physicians with predictions based on the discovery of complex ...patterns from historical data, such as large, longitudinal electronic health records (EHR). This study is a first attempt to demonstrate such capabilities using raw echocardiographic videos of the heart. We show that a large dataset of 723,754 clinically-acquired echocardiographic videos (~45 million images) linked to longitudinal follow-up data in 27,028 patients can be used to train a deep neural network to predict 1-year mortality with good accuracy (area under the curve (AUC) in an independent test set = 0.839). Prediction accuracy was further improved by adding EHR data (AUC = 0.858). Finally, we demonstrate that the trained neural network was more accurate in mortality prediction than two expert cardiologists. These results highlight the potential of neural networks to add new power to clinical predictions.
A liquid chromatography/mass spectrometry/mass spectrometry (LC/MS/MS) method has been developed and validated to detect and confirm the marker residue of eprinomectin (B1a component) in bovine liver ...when present at levels ≥2400 ng/g. Sample extracts prepared for assay by the LC/fluorescence determinative method (prior to the derivatization step) and standard solutions were used to validate the confirmatory method. The chromatographic retention time of the eprinomectin B1a component and the relative ion intensities of the parent ion (M + H+ at m/z 914) and three product ions (m/z 896, 468, and 330) generated by fragmentation of the parent ion are compared to those determined from standards. Keywords: Eprinomectin; residue; confirmatory; bovine liver; LC/MS/MS
Chronic administration of sodium azide in rats inhibits cytochrome oxidase and produces learning and memory deficits. The present experiment tested the hypothesis that chronic sodium azide treatment ...might also alter protein kinase C activation. Continuous infusion of sodium azide (400 μg/h, sc) in rats for 2 weeks significantly decreases membrane-bound protein kinase C in hippocampus, but not frontal cortex, temporal cortex, or cerebellum. Since protein kinase C activation is correlated with hippocampus-dependent learning, these results suggest a possible biochemical mechanism for azide-induced impairment of learning.