Melton, Genevieve B.Ryan, James O.Wang, YanPakhomov, Serguei...
9页
查看更多>>摘要：Background: Full syntactic parsing of clinical text as a part of clinical natural language processing (NLP) is critical for a wide range of applications. Several robust syntactic parsers are publicly available to produce linguistic representations for sentences. However, these existing parsers are mostly trained on general English text and may require adaptation for optimal performance on clinical text. Our objective was to adapt an existing general English parser for the clinical text of operative reports via lexicon augmentation, statistics adjusting, and grammar rules modification based on operative reports.
Romano, Joseph D.Tharp, William G.Sarkar, Indra Neil
29页
查看更多>>摘要：The characterization of complex diseases remains a great challenge for biomedical researchers due to the myriad interactions of genetic and environmental factors. Network medicine approaches strive to accommodate these factors holistically. Phylogenomic techniques that can leverage available genomic data may provide an evolutionary perspective that may elucidate knowledge for gene networks of complex diseases and provide another source of information for network medicine approaches. Here, an automated method is presented that leverages publicly available genomic data and phylogenomic techniques, resulting in a gene network. The potential of approach is demonstrated based on a case study of nine genes associated with Alzheimer Disease, a complex neurodegenerative syndrome.
查看更多>>摘要：Real integration of Virtual Microscopy with the pathologist service workflow requires the design of adaptable strategies for any hospital service to interact with a set of Whole Slide Images. Nowadays, mobile devices have the actual potential of supporting an online pervasive network of specialists working together. However, such devices are still very limited. This article introduces a novel highly adaptable strategy for streaming and visualizing WSI from mobile devices. The presented approach effectively exploits and extends the granularity of the JPEG2000 standard and integrates it with different strategies to achieve a lossless, loosely-coupled, decoder and platform independent implementation, adaptable to any interaction model. The performance was evaluated by two expert pathologists interacting with a set of 20 virtual slides. The method efficiently uses the available device resources: the memory usage did not exceed a 7% of the device capacity while the decoding times were smaller than the 200 ms per Region of Interest, i.e., a window of 256 x 256 pixels. This model is easily adaptable to other medical imaging scenarios. (C) 2015 Elsevier Inc. All rights reserved.
查看更多>>摘要：Introduction: While mammography notably contributes to earlier detection of breast cancer, it has its limitations, including a large number of false positive exams. Improved radiology education could potentially contribute to alleviating this issue. Toward this goal, in this paper we propose an algorithm for modeling of false positive error making among radiology trainees. Identifying troublesome locations for the trainees could focus their training and in turn improve their performance.
Sleator, Roy D.O'Driscoll, AislingBelogrudov, VladislavCarroll, John...
7页
查看更多>>摘要：The recent exponential growth of genomic databases has resulted in the common task of sequence alignment becoming one of the major bottlenecks in the field of computational biology. It is typical for these large datasets and complex computations to require cost prohibitive High Performance Computing (HPC) to function. As such, parallelised solutions have been proposed but many exhibit scalability limitations and are incapable of effectively processing "Big Data" - the name attributed to datasets that are extremely large, complex and require rapid processing. The Hadoop framework, comprised of distributed storage and a parallelised programming framework known as MapReduce, is specifically designed to work with such datasets but it is not trivial to efficiently redesign and implement bioinformatics algorithms according to this paradigm. The parallelisation strategy of "divide and conquer" for alignment algorithms can be applied to both data sets and input query sequences. However, scalability is still an issue due to memory constraints or large databases, with very large database segmentation leading to additional performance decline. Herein, we present Hadoop Blast (HBlast), a parallelised BLAST algorithm that proposes a flexible method to partition both databases and input query sequences using "virtual partitioning". HBlast presents improved scalability over existing solutions and well balanced computational work load while keeping database segmentation and recompilation to a minimum. Enhanced BLAST search performance on cheap memory constrained hardware has significant implications for in field clinical diagnostic testing; enabling faster and more accurate identification of pathogenic DNA in human blood or tissue samples. (C) 2015 Elsevier Inc. All rights reserved.
查看更多>>摘要：Use of clinical simulation in the design and evaluation of eHealth systems and applications has increased during the last decade. This paper describes a methodological approach for using clinical simulations in the design and evaluation of clinical information systems. The method is based on experiences from more than 20 clinical simulation studies conducted at the ITX-lab in the Capital Region of Denmark during the last 5 years. A ten-step approach to conducting simulations is presented in this paper. To illustrate the approach, a clinical simulation study concerning implementation of Digital Clinical Practice Guidelines in a prototype planning and coordination module is presented. In the case study potential benefits were assessed in a full-scale simulation test including 18 health care professionals. The results showed that health care professionals can benefit from such a module. Unintended consequences concerning terminology and changes in the division of responsibility amongst healthcare professionals were also identified, and questions were raised concerning future workflow across sector borders. Furthermore unexpected new possible benefits concerning improved communication, content of information in discharge letters and quality management emerged during the testing. In addition new potential groups of users were identified. The case study is used to demonstrate the potential of using the clinical simulation approach described in the paper. (C) 2015 Elsevier Inc. All rights reserved.
Buist, Diana S. M.Gao, HongyuanBowles, Erin J. AielloCarrell, David...
8页
查看更多>>摘要：Objective: Structured data on mammographic findings are difficult to obtain without manual review. We developed and evaluated a rule-based natural language processing (NLP) system to extract mammographic findings from free-text mammography reports.
Tanaka, Erica AkemiNozawa, Sergio RicardoMacedo, Alessandra AlanizBaranauskas, Jose Augusto...
11页
查看更多>>摘要：Many classification problems, especially in the field of bioinformatics, are associated with more than one class, known as multi-label classification problems. In this study, we propose a new adaptation for the Binary Relevance algorithm taking into account possible relations among labels, focusing on the interpretability of the model, not only on its performance. Experiments were conducted to compare the performance of our approach against others commonly found in the literature and applied to functional genomic datasets. The experimental results show that our proposal has a performance comparable to that of other methods and that, at the same time, it provides an interpretable model from the multi-label problem. (C) 2014 Elsevier Inc. All rights reserved.
查看更多>>摘要：Electronic medical record (EMR) offers promises for novel analytics. However, manual feature engineering from EMR is labor intensive because EMR is complex - it contains temporal, mixed-type and multimodal data packed in irregular episodes. We present a computational framework to harness EMR with minimal human supervision via restricted Boltzmann machine (RBM). The framework derives a new representation of medical objects by embedding them in a low-dimensional vector space. This new representation facilitates algebraic and statistical manipulations such as projection onto 2D plane (thereby offering intuitive visualization), object grouping (hence enabling automated phenotyping), and risk stratification. To enhance model interpretability, we introduced two constraints into model parameters: (a) nonnegative coefficients, and (b) structural smoothness. These result in a novel model called eNRBM (EMR-driven nonnegative RBM). We demonstrate the capability of the eNRBM on a cohort of 7578 mental health patients under suicide risk assessment. The derived representation not only shows clinically meaningful feature grouping but also facilitates short-term risk stratification. The F-scores, 0.21 for moderate-risk and 0.36 for high-risk, are significantly higher than those obtained by clinicians and competitive with the results obtained by support vector machines. (C) 2015 Elsevier Inc. All rights reserved.
Goodman, Corey W.Major, Heather J.Walls, William D.Sheffield, Val C....
8页
查看更多>>摘要：Chromosomal microarrays (CMAs) are routinely used in both research and clinical laboratories; yet, little attention has been given to the estimation of genome-wide true and false negatives during the assessment of these assays and how such information could be used to calibrate various algorithmic metrics to improve performance. Low-throughput, locus-specific methods such as fluorescence in situ hybridization (FISH), quantitative PCR (qPCR), or multiplex ligation-dependent probe amplification (MLPA) preclude rigorous calibration of various metrics used by copy number variant (CNV) detection algorithms. To aid this task, we have established a comparative methodology, CNV-ROC, which is capable of performing a high throughput, low cost, analysis of CMAs that takes into consideration genome-wide true and false negatives. CNV-ROC uses a higher resolution microarray to confirm calls from a lower resolution microarray and provides for a true measure of genome-wide performance metrics at the resolution offered by microarray testing. CNV-ROC also provides for a very precise comparison of CNV calls between two microarray platforms without the need to establish an arbitrary degree of overlap. Comparison of CNVs across microarrays is done on a per-probe basis and receiver operator characteristic (ROC) analysis is used to calibrate algorithmic metrics, such as log(2) ratio threshold, to enhance CNV calling performance. CNV-ROC addresses a critical and consistently overlooked aspect of analytical assessments of genome-wide techniques like CMAs which is the measurement and use of genome-wide true and false negative data for the calculation of performance metrics and comparison of CNV profiles between different microarray experiments. (C) 2015 Elsevier Inc. All rights reserved.
NSTL
Elsevier