Predicting severe clinical events by learning about life-saving actions and outcomes using distant supervision.

Abstract:

:Medical error is a leading cause of patient death in the United States. Among the different types of medical errors, harm to patients caused by doctors missing early signs of deterioration is especially challenging to address due to the heterogeneity of patients' physiological patterns. In this study, we implemented risk prediction models using the gradient boosted tree method to derive risk estimates for acute onset diseases in the near future. The prediction model uses physiological variables as input signals and the time of the administration of outcome-related interventions and discharge diagnoses as labels. We examine four categories of acute onset illness: acute heart failure (AHF), acute lung injury (ALI), acute kidney injury (AKI), and acute liver failure (ALF). To develop and test the model, we consider data from two sources: 23,578 admissions to the Intensive Care Unit (ICU) from the MIMIC-3 dataset (Beth-Israel Hospital) and 16,612 ICU admissions on hospitals affiliated with our institution (University of Washington Medical Center and Harborview Medical Center, the UW-CDR dataset). We systematically identify outcome-related interventions for each acute organ failure, then use them, along with discharge diagnoses, to label proxy events to train gradient boosted trees. The trained models achieve the highest F1 score with a value of 0.6018 when predicting the need for life-saving interventions for ALI within the next 24 h in the MIMIC-3 dataset while showing a median F1 score of 0.3850 from all acute organ failures in both datasets. The approach also achieves the highest F1 score of 0.6301 when classifying a patient's ALI status at the time of discharge from the MIMIC-3 dataset, with a median F1 score of 0.4307 in both datasets. This study shows the potential for using the time of outcome-related intervention administrations and discharge diagnoses as labels to train supervised machine learning models that predict the risk of acute onset illnesses.

journal_name

J Biomed Inform

authors

Lee DH,Yetisgen M,Vanderwende L,Horvitz E

doi

10.1016/j.jbi.2020.103425

subject

Has Abstract

pub_date

2020-07-01 00:00:00

pages

103425

eissn

1532-0464

issn

1532-0480

pii

S1532-0464(20)30053-8

journal_volume

107

pub_type

杂志文章
  • Analysis of microarray leukemia data using an efficient MapReduce-based K-nearest-neighbor classifier.

    abstract::Microarray-based gene expression profiling has emerged as an efficient technique for classification, prognosis, diagnosis, and treatment of cancer. Frequent changes in the behavior of this disease generates an enormous volume of data. Microarray data satisfies both the veracity and velocity properties of big data, as ...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2016.03.002

    authors: Kumar M,Rath NK,Rath SK

    更新日期:2016-04-01 00:00:00

  • Interestingness measures and strategies for mining multi-ontology multi-level association rules from gene ontology annotations for the discovery of new GO relationships.

    abstract::The Gene Ontology (GO), a set of three sub-ontologies, is one of the most popular bio-ontologies used for describing gene product characteristics. GO annotation data containing terms from multiple sub-ontologies and at different levels in the ontologies is an important source of implicit relationships between terms fr...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2013.06.012

    authors: Manda P,McCarthy F,Bridges SM

    更新日期:2013-10-01 00:00:00

  • Decision-making model for early diagnosis of congestive heart failure using rough set and decision tree approaches.

    abstract::The accurate diagnosis of heart failure in emergency room patients is quite important, but can also be quite difficult due to our insufficient understanding of the characteristics of heart failure. The purpose of this study is to design a decision-making model that provides critical factors and knowledge associated wi...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2012.04.013

    authors: Son CS,Kim YN,Kim HS,Park HS,Kim MS

    更新日期:2012-10-01 00:00:00

  • Does the use of structured reporting improve usability? A comparative evaluation of the usability of two approaches for findings reporting in a large-scale telecardiology context.

    abstract::One of the main reasons that leads to a low adoption rate of telemedicine systems is poor usability. An aspect that influences usability during the reporting of findings is the input mode, e.g., if a free-text (FT) or a structured report (SR) interface is employed. The objective of our study is to compare the usabilit...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2014.07.002

    authors: Lacerda TC,von Wangenheim CG,von Wangenheim A,Giuliano I

    更新日期:2014-12-01 00:00:00

  • Vaidurya: a multiple-ontology, concept-based, context-sensitive clinical-guideline search engine.

    abstract::We designed and implemented a generic search engine (Vaidurya), as part of our Digital clinical-Guideline Library (DeGeL) framework. Two search methods were implemented in addition to full-text search: (1) concept-based search, which relies on pre-indexing the guidelines in a clinically meaningful fashion, and (2) con...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2008.07.003

    authors: Moskovitch R,Shahar Y

    更新日期:2009-02-01 00:00:00

  • Comparison of reversible-jump Markov-chain-Monte-Carlo learning approach with other methods for missing enzyme identification.

    abstract::Computational identification of missing enzymes plays a significant role in accurate and complete reconstruction of metabolic network for both newly sequenced and well-studied organisms. For a metabolic reaction, given a set of candidate enzymes identified according to certain biological evidences, a powerful mathemat...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2007.09.002

    authors: Geng B,Zhou X,Zhu J,Hung YS,Wong ST

    更新日期:2008-04-01 00:00:00

  • A controlled greedy supervised approach for co-reference resolution on clinical text.

    abstract::Identification of co-referent entity mentions inside text has significant importance for other natural language processing (NLP) tasks (e.g. event linking). However, this task, known as co-reference resolution, remains a complex problem, partly because of the confusion over different evaluation metrics and partly beca...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2013.03.007

    authors: Chowdhury MF,Zweigenbaum P

    更新日期:2013-06-01 00:00:00

  • Grounding a new information technology implementation framework in behavioral science: a systematic analysis of the literature on IT use.

    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

    authors: Kukafka R,Johnson SB,Linfante A,Allegrante JP

    更新日期:2003-06-01 00:00:00

  • MorphoCol: An ontology-based knowledgebase for the characterisation of clinically significant bacterial colony morphologies.

    abstract:BACKGROUND:One of the major concerns of the biomedical community is the increasing prevalence of antimicrobial resistant microorganisms. Recent findings show that the diversification of colony morphology may be indicative of the expression of virulence factors and increased resistance to antibiotic therapeutics. To tra...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2015.03.007

    authors: Sousa AM,Pereira MO,Lourenço A

    更新日期:2015-06-01 00:00:00

  • The European cross-border health data exchange roadmap: Case study in the Italian setting.

    abstract::Health data exchange is a major challenge due to the sensitive information and the privacy issues entailed. Considering the European context, in which health data must be exchanged between different European Union (EU) Member States, each having a different national regulatory framework as well as different national h...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2019.103183

    authors: Nalin M,Baroni I,Faiella G,Romano M,Matrisciano F,Gelenbe E,Martinez DM,Dumortier J,Natsiavas P,Votis K,Koutkias V,Tzovaras D,Clemente F

    更新日期:2019-06-01 00:00:00

  • Patient empowerment for cancer patients through a novel ICT infrastructure.

    abstract::As a result of recent advances in cancer research and "precision medicine" approaches, i.e. the idea of treating each patient with the right drug at the right time, more and more cancer patients are being cured, or might have to cope with a life with cancer. For many people, cancer survival today means living with a c...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2019.103342

    authors: Kondylakis H,Bucur A,Crico C,Dong F,Graf N,Hoffman S,Koumakis L,Manenti A,Marias K,Mazzocco K,Pravettoni G,Renzi C,Schera F,Triberti S,Tsiknakis M,Kiefer S

    更新日期:2020-01-01 00:00:00

  • A pilot study of a heuristic algorithm for novel template identification from VA electronic medical record text.

    abstract:RATIONALE:Templates in text notes pose challenges for automated information extraction algorithms. We propose a method that identifies novel templates in plain text medical notes. The identification can then be used to either include or exclude templates when processing notes for information extraction. METHODS:The tw...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2016.07.019

    authors: Redd AM,Gundlapalli AV,Divita G,Carter ME,Tran LT,Samore MH

    更新日期:2017-07-01 00:00:00

  • Use of morphological analysis in protein name recognition.

    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

    authors: Yamamoto K,Kudo T,Konagaya A,Matsumoto Y

    更新日期:2004-12-01 00:00:00

  • Computer mediated reality technologies: A conceptual framework and survey of the state of the art in healthcare intervention systems.

    abstract:INTRODUCTION:The trend of an ageing and growing world population, particularly in developed countries, is expected to continue for decades to come causing an increase in demand for healthcare resources and services. Consequently, demand is growing faster than rises in funding. The UK government, in partnership with the...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章,评审

    doi:10.1016/j.jbi.2019.103102

    authors: Ibrahim Z,Money AG

    更新日期:2019-02-01 00:00:00

  • MeSHing molecular sequences and clinical trials: a feasibility study.

    abstract::The centralized and public availability of molecular sequence and clinical trial data presents an opportunity to identify potentially valuable linkages across the bench-to-bedside "T1" translational barrier. In this study, we sought to leverage keyword metadata (Medical Subject Heading [MeSH] descriptors) to infer rel...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2009.10.003

    authors: Chen ES,Sarkar IN

    更新日期:2010-06-01 00:00:00

  • Multi-step ahead meningitis case forecasting based on decomposition and multi-objective optimization methods.

    abstract::Epidemiological time series forecasting plays an important role in health public systems, due to its ability to allow managers to develop strategic planning to avoid possible epidemics. In this paper, a hybrid learning framework is developed to forecast multi-step-ahead (one, two, and three-month-ahead) meningitis cas...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2020.103575

    authors: Ribeiro MHDM,Mariani VC,Coelho LDS

    更新日期:2020-11-01 00:00:00

  • Finding disease similarity based on implicit semantic similarity.

    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

    authors: Mathur S,Dinakarpandian D

    更新日期:2012-04-01 00:00:00

  • MeSHy: Mining unanticipated PubMed information using frequencies of occurrences and concurrences of MeSH terms.

    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

    authors: Theodosiou T,Vizirianakis IS,Angelis L,Tsaftaris A,Darzentas N

    更新日期:2011-12-01 00:00:00

  • Extending the Fellegi-Sunter probabilistic record linkage method for approximate field comparators.

    abstract::Probabilistic record linkage is a method commonly used to determine whether demographic records refer to the same person. The Fellegi-Sunter method is a probabilistic approach that uses field weights based on log likelihood ratios to determine record similarity. This paper introduces an extension of the Fellegi-Sunter...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2009.08.004

    authors: DuVall SL,Kerber RA,Thomas A

    更新日期:2010-02-01 00:00:00

  • 3D interactive surgical visualization system using mobile spatial information acquisition and autostereoscopic display.

    abstract::Three-dimensional (3D) visualization of preoperative and intraoperative medical information becomes more and more important in minimally invasive surgery. We develop a 3D interactive surgical visualization system using mobile spatial information acquisition and autostereoscopic display for surgeons to observe surgical...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2017.05.014

    authors: Fan Z,Weng Y,Chen G,Liao H

    更新日期:2017-07-01 00:00:00

  • Computing with evidence Part II: An evidential approach to predicting metabolic drug-drug interactions.

    abstract::We describe a novel experiment that we conducted with the Drug Interaction Knowledge-base (DIKB) to determine which combinations of evidence enable a rule-based theory of metabolic drug-drug interactions to make the most optimal set of predictions. The focus of the experiment was a group of 16 drugs including six memb...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2009.05.010

    authors: Boyce R,Collins C,Horn J,Kalet I

    更新日期:2009-12-01 00:00:00

  • Classification models for the prediction of clinicians' information needs.

    abstract:OBJECTIVE:Clinicians face numerous information needs during patient care activities and most of these needs are not met. Infobuttons are information retrieval tools that help clinicians to fulfill their information needs by providing links to on-line health information resources from within an electronic medical record...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2008.07.001

    authors: Del Fiol G,Haug PJ

    更新日期:2009-02-01 00:00:00

  • Lessons learnt from the DDIExtraction-2013 Shared Task.

    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

    authors: Segura-Bedmar I,Martínez P,Herrero-Zazo M

    更新日期:2014-10-01 00:00:00

  • Relevance feedback for enhancing content based image retrieval and automatic prediction of semantic image features: Application to bone tumor radiographs.

    abstract:BACKGROUND:The majority of current medical CBIR systems perform retrieval based only on "imaging signatures" generated by extracting pixel-level quantitative features, and only rarely has a feedback mechanism been incorporated to improve retrieval performance. In addition, current medical CBIR approaches do not routine...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2018.07.002

    authors: Banerjee I,Kurtz C,Devorah AE,Do B,Rubin DL,Beaulieu CF

    更新日期:2018-08-01 00:00:00

  • An image score inference system for RNAi genome-wide screening based on fuzzy mixture regression modeling.

    abstract::With recent advances in fluorescence microscopy imaging techniques and methods of gene knock down by RNA interference (RNAi), genome-scale high-content screening (HCS) has emerged as a powerful approach to systematically identify all parts of complex biological processes. However, a critical barrier preventing fulfill...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2008.04.007

    authors: Wang J,Zhou X,Li F,Bradley PL,Chang SF,Perrimon N,Wong ST

    更新日期:2009-02-01 00:00:00

  • Scenario-based design: a method for connecting information system design with public health operations and emergency management.

    abstract:UNLABELLED:Responding to public health emergencies requires rapid and accurate assessment of workforce availability under adverse and changing circumstances. However, public health information systems to support resource management during both routine and emergency operations are currently lacking. We applied scenario-...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2011.07.004

    authors: Reeder B,Turner AM

    更新日期:2011-12-01 00:00:00

  • Clinical decision support models and frameworks: Seeking to address research issues underlying implementation successes and failures.

    abstract::Computer-based clinical decision support (CDS) has been pursued for more than five decades. Despite notable accomplishments and successes, wide adoption and broad use of CDS in clinical practice has not been achieved. Many issues have been identified as being partially responsible for the relatively slow adoption and ...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章,评审

    doi:10.1016/j.jbi.2017.12.005

    authors: Greenes RA,Bates DW,Kawamoto K,Middleton B,Osheroff J,Shahar Y

    更新日期:2018-02-01 00:00:00

  • A term extraction tool for expanding content in the domain of functioning, disability, and health: proof of concept.

    abstract::Among the challenges in developing terminology systems is providing complete content coverage of specialized subject fields. This paper reports on a term extraction tool designed for the development and expansion of terminology systems concerned with functioning, disability, and health. Content relevant to this domain...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2003.09.005

    authors: Harris MR,Savova GK,Johnson TM,Chute CG

    更新日期:2003-08-01 00:00:00

  • Chronic disease modeling and simulation software.

    abstract::Computers allow describing the progress of a disease using computerized models. These models allow aggregating expert and clinical information to allow researchers and decision makers to forecast disease progression. To make this forecast reliable, good models and therefore good modeling tools are required. This paper...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2010.06.003

    authors: Barhak J,Isaman DJ,Ye W,Lee D

    更新日期:2010-10-01 00:00:00

  • Software tools for simultaneous data visualization and T cell epitopes and disorder prediction in proteins.

    abstract::We have developed EpDis and MassPred, extendable open source software tools that support bioinformatic research and enable parallel use of different methods for the prediction of T cell epitopes, disorder and disordered binding regions and hydropathy calculation. These tools offer a semi-automated installation of chos...

    journal_title:Journal of biomedical informatics

    pub_type: 杂志文章

    doi:10.1016/j.jbi.2016.01.016

    authors: Jandrlić DR,Lazić GM,Mitić NS,Pavlović MD

    更新日期:2016-04-01 00:00:00