Abstract:
:We studied how lagged linear regression can be used to detect the physiologic effects of drugs from data in the electronic health record (EHR). We systematically examined the effect of methodological variations ((i) time series construction, (ii) temporal parameterization, (iii) intra-subject normalization, (iv) differencing (lagged rates of change achieved by taking differences between consecutive measurements), (v) explanatory variables, and (vi) regression models) on performance of lagged linear methods in this context. We generated two gold standards (one knowledge-base derived, one expert-curated) for expected pairwise relationships between 7 drugs and 4 labs, and evaluated how the 64 unique combinations of methodological perturbations reproduce the gold standards. Our 28 cohorts included patients in the Columbia University Medical Center/NewYork-Presbyterian Hospital clinical database, and ranged from 2820 to 79,514 patients with between 8 and 209 average time points per patient. The most accurate methods achieved AUROC of 0.794 for knowledge-base derived gold standard (95%CI [0.741, 0.847]) and 0.705 for expert-curated gold standard (95% CI [0.629, 0.781]). We observed a mean AUROC of 0.633 (95%CI [0.610, 0.657], expert-curated gold standard) across all methods that re-parameterize time according to sequence and use either a joint autoregressive model with time-series differencing or an independent lag model without differencing. The complement of this set of methods achieved a mean AUROC close to 0.5, indicating the importance of these choices. We conclude that time-series analysis of EHR data will likely rely on some of the beneficial pre-processing and modeling methodologies identified, and will certainly benefit from continued careful analysis of methodological perturbations. This study found that methodological variations, such as pre-processing and representations, have a large effect on results, exposing the importance of thoroughly evaluating these components when comparing machine-learning methods.
journal_name
J Biomed Informjournal_title
Journal of biomedical informaticsauthors
Levine ME,Albers DJ,Hripcsak Gdoi
10.1016/j.jbi.2018.08.014subject
Has Abstractpub_date
2018-10-01 00:00:00pages
149-159eissn
1532-0464issn
1532-0480pii
S1532-0464(18)30173-4journal_volume
86pub_type
杂志文章abstract::Cloud computing is emerging as the next-generation IT architecture. However, cloud computing also raises security and privacy concerns since the users have no physical control over the outsourced data. This paper focuses on fairly retrieving encrypted private medical records outsourced to remote untrusted cloud server...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2014.02.008
更新日期:2014-08-01 00:00:00
abstract::Large-scale mapping efforts have been done in attempts to migrate systems that use proprietary concepts to ones that use terminological standards such as SNOMED CT. As efforts move towards implementation, the target maps should retain a predictable structure including those targets requiring post-coordination of SNOME...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2009.03.004
更新日期:2009-06-01 00:00:00
abstract::With the rise in chronic, behavior-related disease, computerized behavioral protocols (CBPs) that help individuals improve behaviors have the potential to play an increasing role in the future health of society. To be effective and widely used CBPs should be based on accepted behavioral theory. However, designing CBPs...
journal_title:Journal of biomedical informatics
pub_type: 临床试验,杂志文章
doi:10.1016/j.jbi.2004.12.001
更新日期:2005-08-01 00:00:00
abstract::Text categorization has been used extensively in recent years to classify plain-text clinical reports. This study employs text categorization techniques for the classification of open narrative forensic autopsy reports. One of the key steps in text classification is document representation. In document representation,...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2018.04.013
更新日期:2018-06-01 00:00:00
abstract::We analyze the discriminatory power of k-nearest neighbors, logistic regression, artificial neural networks (ANNs), decision tress, and support vector machines (SVMs) on the task of classifying pigmented skin lesions as common nevi, dysplastic nevi, or melanoma. Three different classification tasks were used as benchm...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1006/jbin.2001.1004
更新日期:2001-02-01 00:00:00
abstract::Gene selection is important for cancer classification based on gene expression data, because of high dimensionality and small sample size. In this paper, we present a new gene selection method based on clustering, in which dissimilarity measures are obtained through kernel functions. It searches for best weights of ge...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2016.05.007
更新日期:2016-08-01 00:00:00
abstract::With the increasing availability of genomic sequence data, numerous methods have been proposed for finding DNA motifs. The discovery of DNA motifs serves a critical step in many biological applications. However, the privacy implication of DNA analysis is normally neglected in the existing methods. In this work, we pro...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2013.12.016
更新日期:2014-08-01 00:00:00
abstract::Federal funds have supported Nurse Practitioner (NP) education and the establishment of nurse-managed centers. Yet, important questions are raised about the quality and appropriate scope of NP care. Few NP-patient encounters are documented in the largest national surveys of ambulatory care, sponsored by the National C...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2003.09.016
更新日期:2003-08-01 00:00:00
abstract:BACKGROUND:Allowing patients to access their own electronic health record (EHR) notes through online patient portals has the potential to improve patient-centered care. However, EHR notes contain abundant medical jargon that can be difficult for patients to comprehend. One way to help patients is to reduce information ...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2017.02.016
更新日期:2017-04-01 00:00:00
abstract::The Breast Imaging Reporting and Data System (BI-RADS) was developed to reduce variation in the descriptions of findings. Manual analysis of breast radiology report data is challenging but is necessary for clinical and healthcare quality assurance activities. The objective of this study is to develop a natural languag...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2017.04.011
更新日期:2017-05-01 00:00:00
abstract::We propose a model-driven methodology aimed to shed light on complex disorders. Our approach enables exploring shared etiologies of comorbid diseases at the molecular pathway level. The method, Comparative Comorbidities Simulation (CCS), uses stochastic Petri net simulation for examining the phenotypic effects of pert...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2016.08.008
更新日期:2016-10-01 00:00:00
abstract::Intensive care monitoring systems are typically developed from population data, but do not take into account the variability among individual patients' characteristics. This study develops patient-specific alarm algorithms in real time. Classification tree and neural network learning were carried out in batch mode on ...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2008.03.011
更新日期:2008-06-01 00:00:00
abstract:OBJECTIVE:Clinical care guidelines recommend that newly diagnosed prostate cancer patients at high risk for metastatic spread receive a bone scan prior to treatment and that low risk patients not receive it. The objective was to develop an automated pipeline to interrogate heterogeneous data to evaluate the use of bone...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2019.103184
更新日期:2019-06-01 00:00:00
abstract:OBJECTIVE:We have developed an automated knowledge base peer feedback system as part of an effort to facilitate the creation and refinement of sound clinical knowledge content within an enterprise-wide knowledge base. The program collects clinical data stored in our Clinical Data Repository during usage of a physician ...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2007.05.006
更新日期:2008-02-01 00:00:00
abstract:BACKGROUND:The determination of risk factors and their temporal relations in natural language patient records is a complex task which has been addressed in the i2b2/UTHealth 2014 shared task. In this context, in most systems it was broadly decomposed into two sub-tasks implemented by two components: entity detection, a...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2015.06.014
更新日期:2015-12-01 00:00:00
abstract::Sensitive biomedical data is often collected from distributed sources, involving different information systems and different organizational units. Local autonomy and legal reasons lead to the need of privacy preserving integration concepts. In this article, we focus on anonymization, which plays an important role for ...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2013.12.002
更新日期:2014-08-01 00:00:00
abstract::Deep learning models (aka Deep Neural Networks) have revolutionized many fields including computer vision, natural language processing, speech recognition, and is being increasingly used in clinical healthcare applications. However, few works exist which have benchmarked the performance of the deep learning models wit...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2018.04.007
更新日期:2018-07-01 00:00:00
abstract::Data analytics is routinely used to support biomedical research in all areas, with particular focus on the most relevant clinical conditions, such as cancer. Bioinformatics approaches, in particular, have been used to characterize the molecular aspects of diseases. In recent years, numerous studies have been performed...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章,评审
doi:10.1016/j.jbi.2020.103466
更新日期:2020-07-01 00:00:00
abstract::In this case study, we describe a method that has potential to provide systematic support for public health information management. Public health agencies depend on specialized information that travels throughout an organization via communication networks among employees. Interactions that occur within these networks ...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2006.09.004
更新日期:2007-08-01 00:00:00
abstract::The Foundational Model of Anatomy (FMA), initially developed as an enhancement of the anatomical content of UMLS, is a domain ontology of the concepts and relationships that pertain to the structural organization of the human body. It encompasses the material objects from the molecular to the macroscopic levels that c...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2003.11.007
更新日期:2003-12-01 00:00:00
abstract:OBJECTIVE:To develop a cost-efficient method for identifying adverse drug events (ADEs) and medication errors (MEs) identified using outpatient electronic medical records within ambulatory settings. DESIGN:Comparison of sensitivity and cost of "traditional" pharmacist based approach to identifying ADEs and MEs during ...
journal_title:Journal of biomedical informatics
pub_type: 临床试验,杂志文章,多中心研究
doi:10.1016/s1532-0464(03)00059-5
更新日期:2003-02-01 00:00:00
abstract::Genomics has contributed to a growing collection of gene-function and gene-disease annotations that can be exploited by informatics to study similarity between diseases. This can yield insight into disease etiology, reveal common pathophysiology and/or suggest treatment that can be appropriated from one disease to ano...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2011.11.017
更新日期:2012-04-01 00:00:00
abstract::The National Drug File - Reference Terminology (NDF-RT) is a large and complex drug terminology consisting of several classification hierarchies on top of an extensive collection of drug concepts. These hierarchies provide important information about clinical drugs, e.g., their chemical ingredients, mechanisms of acti...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2017.07.013
更新日期:2017-09-01 00:00:00
abstract::Stomach cancer is one of the leading causes of cancer-related deaths worldwide. More than 80% diagnosis of this cancer occur at later stages leading to low 5-year survival rate. This emphasizes the need to have better prognostic techniques for stomach cancer. In this regard, the Next-Generation Sequencing of whole gen...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2019.103254
更新日期:2019-09-01 00:00:00
abstract::In absence of periodic systematic comparisons, biologists/bioinformaticians may be forced to make a subjective selection among the many protein-protein interaction (PPI) databases and tools. We conducted a comprehensive compilation and comparison of such resources. We compiled 375 PPI resources, short-listed 125 impor...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2020.103380
更新日期:2020-03-01 00:00:00
abstract::Phylogeography is a field that focuses on the geographical lineages of species such as vertebrates or viruses. Here, geographical data, such as location of a species or viral host is as important as the sequence information extracted from the species. Together, this information can help illustrate the migration of the...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2011.06.005
更新日期:2011-12-01 00:00:00
abstract::Simulators for honing procedural skills (such as surgical skills and central venous catheter placement) have proven to be valuable tools for medical educators and students. While such simulations represent an effective paradigm in surgical education, there is an opportunity to add a layer of cognitive exercises to the...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2009.02.008
更新日期:2009-08-01 00:00:00
abstract::A 1998 paper that delineated desirable characteristics, or desiderata for controlled medical terminologies attempted to summarize emerging consensus regarding structural issues of such terminologies. Among the Desiderata was a call for terminologies to be "concept oriented." Since then, research has trended toward the...
journal_title:Journal of biomedical informatics
pub_type: 评论,杂志文章
doi:10.1016/j.jbi.2005.11.008
更新日期:2006-06-01 00:00:00
abstract:OBJECTIVE:To develop a method for profiling the collective populations targeted for recruitment by multiple clinical studies addressing the same medical condition using one eligibility feature each time. METHODS:Using a previously published database COMPACT as the backend, we designed a scalable method for visual aggr...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2015.01.005
更新日期:2015-04-01 00:00:00
abstract::Identifying the symptom clusters (two or more related symptoms) with shared underlying molecular mechanisms has been a vital analysis task to promote the symptom science and precision health. Related studies have applied the clustering algorithms (e.g. k-means, latent class model) to detect the symptom clusters mostly...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2020.103482
更新日期:2020-07-01 00:00:00