Abstract:
OBJECTIVE:Evaluate the quality of clinical order practice patterns machine-learned from clinician cohorts stratified by patient mortality outcomes. MATERIALS AND METHODS:Inpatient electronic health records from 2010 to 2013 were extracted from a tertiary academic hospital. Clinicians (n = 1822) were stratified into low-mortality (21.8%, n = 397) and high-mortality (6.0%, n = 110) extremes using a two-sided P-value score quantifying deviation of observed vs. expected 30-day patient mortality rates. Three patient cohorts were assembled: patients seen by low-mortality clinicians, high-mortality clinicians, and an unfiltered crowd of all clinicians (n = 1046, 1046, and 5230 post-propensity score matching, respectively). Predicted order lists were automatically generated from recommender system algorithms trained on each patient cohort and evaluated against (i) real-world practice patterns reflected in patient cases with better-than-expected mortality outcomes and (ii) reference standards derived from clinical practice guidelines. RESULTS:Across six common admission diagnoses, order lists learned from the crowd demonstrated the greatest alignment with guideline references (AUROC range = 0.86-0.91), performing on par or better than those learned from low-mortality clinicians (0.79-0.84, P < 10-5) or manually-authored hospital order sets (0.65-0.77, P < 10-3). The same trend was observed in evaluating model predictions against better-than-expected patient cases, with the crowd model (AUROC mean = 0.91) outperforming the low-mortality model (0.87, P < 10-16) and order set benchmarks (0.78, P < 10-35). DISCUSSION:Whether machine-learning models are trained on all clinicians or a subset of experts illustrates a bias-variance tradeoff in data usage. Defining robust metrics to assess quality based on internal (e.g. practice patterns from better-than-expected patient cases) or external reference standards (e.g. clinical practice guidelines) is critical to assess decision support content. CONCLUSION:Learning relevant decision support content from all clinicians is as, if not more, robust than learning from a select subgroup of clinicians favored by patient outcomes.
journal_name
J Biomed Informjournal_title
Journal of biomedical informaticsauthors
Wang JK,Hom J,Balasubramanian S,Schuler A,Shah NH,Goldstein MK,Baiocchi MTM,Chen JHdoi
10.1016/j.jbi.2018.09.005subject
Has Abstractpub_date
2018-10-01 00:00:00pages
109-119eissn
1532-0464issn
1532-0480pii
S1532-0464(18)30179-5journal_volume
86pub_type
杂志文章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:MOTIVATION:A challenge in microarray data analysis is to interpret observed changes in terms of biological properties and relationships. One powerful approach is to make associations of gene expression clusters with biomedical ontologies and/or biological pathways. However, this approach evaluates only one cluster at a...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2007.10.003
更新日期:2008-04-01 00:00:00
abstract:BACKGROUND:Personal health information is a valuable resource to the advancement of research. In order to achieve a comprehensive reform of data infrastructure in Australia, both public engagement and building social trust is vital. In light of this, we conducted a study to explore the opinions, perceived risks and tru...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2019.103222
更新日期:2019-07-01 00:00:00
abstract::Electronic health records (EHR) are a major source of information in biomedical informatics. Yet, missing values are prominent characteristics of EHR. Prediction on dataset with missing values results in inaccurate inferences. Nearest neighbour imputation based on lazy learning approach is a proven technique for missi...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2019.103190
更新日期:2019-06-01 00:00:00
abstract:BACKGROUND:The realization of the potential benefits of health information exchange systems (HIEs) for emergency departments (EDs) depends on the way these systems are actually used. The attributes of volume of information and duration of information processing are important for the study of HIE use patterns in the ED,...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2017.05.007
更新日期:2017-07-01 00:00:00
abstract::Many interventions to improve the success of information technology (IT) implementations are grounded in behavioral science, using theories, and models to identify conditions and determinants of successful use. However, each model in the IT literature has evolved to address specific theoretical problems of particular ...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章,评审
doi:10.1016/j.jbi.2003.09.002
更新日期:2003-06-01 00:00:00
abstract::Patient recruitment is one of the most important barriers to successful completion of clinical trials and thus to obtaining evidence about new methods for prevention, diagnostics and treatment. The reason is that recruitment is effort consuming. It requires the identification of candidate patients for the trial (the p...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2015.05.005
更新日期:2015-08-01 00:00:00
abstract:OBJECTIVES:Major adverse cardiac events (MACE) of acute coronary syndrome (ACS) often occur suddenly resulting in high mortality and morbidity. Recently, the rapid development of electronic medical records (EMR) provides the opportunity to utilize the potential of EMR to improve the performance of MACE prediction. In t...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2017.01.001
更新日期:2017-02-01 00:00:00
abstract::Medical abuse refers to a type of abnormal medical practice which is not in compliance with qualitative or ethical standards, such as excessive prescription or overbilling of medical services. Detection of such medical abuses is crucial, especially for the patients and insurance providers, because they become subject ...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2020.103423
更新日期:2020-07-01 00:00:00
abstract::The physical spaces within which the work of health occurs - the home, the intensive care unit, the emergency room, even the bedroom - influence the manner in which behaviors unfold, and may contribute to efficacy and effectiveness of health interventions. Yet the study of such complex workspaces is difficult. Health ...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2015.07.007
更新日期:2015-10-01 00:00:00
abstract::Building classification models from clinical data using machine learning methods often relies on labeling of patient examples by human experts. Standard machine learning framework assumes the labels are assigned by a homogeneous process. However, in reality the labels may come from multiple experts and it may be diffi...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2013.08.007
更新日期:2013-12-01 00:00:00
abstract::Human musculoskeletal system resources of the human body are valuable for the learning and medical purposes. Internet-based information from conventional search engines such as Google or Yahoo cannot response to the need of useful, accurate, reliable and good-quality human musculoskeletal resources related to medical ...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2012.11.001
更新日期:2013-02-01 00:00:00
abstract::The development of convenient serum bioassays for cancer screening, diagnosis, prognosis, and monitoring of treatment is one of top priorities in cancer research community. Although numerous biomarker candidates have been generated by applying high-throughput technologies such as transcriptomics, proteomics, and metab...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2011.08.010
更新日期:2011-12-01 00:00:00
abstract::To improve the performance of Intensive Care Units (ICUs), the field of bio-statistics has developed scores which try to predict the likelihood of negative outcomes. These help evaluate the effectiveness of treatments and clinical practice, and also help to identify patients with unexpected outcomes. However, they hav...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2019.103269
更新日期:2019-10-01 00:00:00
abstract::In many respects, the critical care workplace resembles a paradigmatic complex system: on account of the dynamic and interactive nature of collaborative clinical work, these settings are characterized by non-linear, inter-dependent and emergent activities. Developing a comprehensive understanding of the work activitie...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2011.02.007
更新日期:2011-06-01 00:00:00
abstract:OBJECTIVE:To classify and characterize the variables commonly used to measure the impact of Information Technology (IT) adoption in health care, as well as settings and IT interventions tested, and to guide future research. MATERIALS AND METHODS:We conducted a descriptive study screening a sample of 236 studies from a...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2016.07.018
更新日期:2016-10-01 00:00:00
abstract::The DDIExtraction Shared Task 2013 is the second edition of the DDIExtraction Shared Task series, a community-wide effort to promote the implementation and comparative assessment of natural language processing (NLP) techniques in the field of the pharmacovigilance domain, in particular, to address the extraction of dr...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2014.05.007
更新日期:2014-10-01 00:00:00
abstract:OBJECTIVE:Targeted drugs dramatically improve the treatment outcomes in cancer patients; however, these innovative drugs are often associated with unexpectedly high cardiovascular toxicity. Currently, cardiovascular safety represents both a challenging issue for drug developers, regulators, researchers, and clinicians ...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2013.10.008
更新日期:2014-02-01 00:00:00
abstract::The 2014 i2b2/UTHealth natural language processing shared task featured a track focused on identifying risk factors for heart disease (specifically, Cardiac Artery Disease) in clinical narratives. For this track, we used a "light" annotation paradigm to annotate a set of 1304 longitudinal medical records describing 29...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2015.05.009
更新日期:2015-12-01 00:00:00
abstract::In the past, algorithms exploiting varying semantics in interactions between biological objects such as genes and diseases have been used in bioinformatics to uncover latent relationships within biological datasets. In this paper, we consider the algorithm Medusa in parallel with binary classification in order to find...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2018.07.005
更新日期:2018-08-01 00:00:00
abstract::Computer-based counseling systems in health care play an important role in the toolset available for medical doctors to inform, motivate and challenge their patients according to a well-defined therapeutic goal. The design, development and implementation of such systems require close collaboration between users, i.e. ...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2008.10.005
更新日期:2009-04-01 00:00:00
abstract:MOTIVATION:PubMed is the most widely used database of biomedical literature. To the detriment of the user though, the ranking of the documents retrieved for a query is not content-based, and important semantic information in the form of assigned Medical Subject Headings (MeSH) terms is not readily presented or producti...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2011.05.009
更新日期:2011-12-01 00:00:00
abstract::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....
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2015.01.008
更新日期:2015-04-01 00:00:00
abstract::Protein name recognition aims to detect each and every protein names appearing in a PubMed abstract. The task is not simple, as the graphic word boundary (space separator) assumed in conventional preprocessing does not necessarily coincide with the protein name boundary. Such boundary disagreement caused by tokenizati...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2004.08.001
更新日期:2004-12-01 00:00:00
abstract::Social media has been identified as a promising potential source of information for pharmacovigilance. The adoption of social media data has been hindered by the massive and noisy nature of the data. Initial attempts to use social media data have relied on exact text matches to drugs of interest, and therefore suffer ...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2019.103307
更新日期:2019-11-01 00:00:00
abstract::The discovery of implicit connections between terms that do not occur together in any scientific document underlies the model of literature-based knowledge discovery first proposed by Swanson. Corpus-derived statistical models of semantic distance such as Latent Semantic Analysis (LSA) have been evaluated previously a...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2009.09.003
更新日期:2010-04-01 00:00:00
abstract::We address the assignment of ICD-10 codes for causes of death by analyzing free-text descriptions in death certificates, together with the associated autopsy reports and clinical bulletins, from the Portuguese Ministry of Health. We leverage a deep neural network that combines word embeddings, recurrent units, and neu...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2018.02.011
更新日期:2018-04-01 00:00:00
abstract::Previous research on standardization of eligibility criteria and its feasibility has traditionally been conducted on clinical trial protocols from ClinicalTrials.gov (CT). The portability and use of such standardization for full-text industry-standard protocols has not been studied in-depth. Towards this end, in this ...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2013.06.001
更新日期:2013-10-01 00:00:00
abstract::Recruiting eligible patients for clinical trials is crucial for reliably answering specific questions about medical interventions and evaluation. However, clinical trial recruitment is a bottleneck in clinical research and drug development. Our goal is to provide an approach towards automating this manual and time-con...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2020.103406
更新日期:2020-05-01 00:00:00
abstract::In this paper we propose a novel approach to the design and implementation of knowledge-based decision support systems for translational research, specifically tailored to the analysis and interpretation of data from high-throughput experiments. Our approach is based on a general epistemological model of the scientifi...
journal_title:Journal of biomedical informatics
pub_type: 杂志文章
doi:10.1016/j.jbi.2009.11.005
更新日期:2010-06-01 00:00:00