12
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      A machine learning approach to triaging patients with chronic obstructive pulmonary disease

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          COPD patients are burdened with a daily risk of acute exacerbation and loss of control, which could be mitigated by effective, on-demand decision support tools. In this study, we present a machine learning-based strategy for early detection of exacerbations and subsequent triage. Our application uses physician opinion in a statistically and clinically comprehensive set of patient cases to train a supervised prediction algorithm. The accuracy of the model is assessed against a panel of physicians each triaging identical cases in a representative patient validation set. Our results show that algorithm accuracy and safety indicators surpass all individual pulmonologists in both identifying exacerbations and predicting the consensus triage in a 101 case validation set. The algorithm is also the top performer in sensitivity, specificity, and ppv when predicting a patient’s need for emergency care.

          Related collections

          Most cited references36

          • Record: found
          • Abstract: not found
          • Article: not found

          Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease. NHLBI/WHO Global Initiative for Chronic Obstructive Lung Disease (GOLD) Workshop summary.

            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Blood eosinophil count and exacerbations in severe chronic obstructive pulmonary disease after withdrawal of inhaled corticosteroids: a post-hoc analysis of the WISDOM trial

            Blood eosinophil counts might predict response to inhaled corticosteroids (ICS) in patients with chronic obstructive pulmonary disease (COPD) and a history of exacerbations. We used data from the WISDOM trial to assess whether patients with COPD with higher blood eosinophil counts would be more likely to have exacerbations if ICS treatment was withdrawn.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Predictors of mortality in hospitalized adults with acute exacerbation of chronic obstructive pulmonary disease.

              There is a need to identify clinically meaningful predictors of mortality following hospitalized COPD exacerbation. The aim of this study was to systematically review the literature to identify clinically important factors that predict mortality after hospitalization for acute exacerbation of chronic obstructive pulmonary disease (COPD). Eligible studies considered adults admitted to hospital with COPD exacerbation. Two authors independently abstracted data. Odds ratios were then calculated by comparing the prevalence of each predictor in survivors versus nonsurvivors. For continuous variables, mean differences were pooled by the inverse of their variance, using a random effects model. There were 37 studies included (189,772 study subjects) with risk of death ranging from 3.6% for studies considering short-term mortality, 31.0% for long-term mortality (up to 2 yr after hospitalization), and 29.0% for studies that considered solely intensive care unit (ICU)-admitted study subjects. Twelve prognostic factors (age, male sex, low body mass index, cardiac failure, chronic renal failure, confusion, long-term oxygen therapy, lower limb edema, Global Initiative for Chronic Lung Disease criteria stage 4, cor pulmonale, acidemia, and elevated plasma troponin level) were significantly associated with increased short-term mortality. Nine prognostic factors (age, low body mass index, cardiac failure, diabetes mellitus, ischemic heart disease, malignancy, FEV1, long-term oxygen therapy, and PaO2 on admission) were significantly associated with long-term mortality. Three factors (age, low Glasgow Coma Scale score, and pH) were significantly associated with increased risk of mortality in ICU-admitted study subjects. Different factors correlate with mortality from COPD exacerbation in the short term, long term, and after ICU admission. These parameters may be useful to develop tools for prediction of outcome in clinical practice.
                Bookmark

                Author and article information

                Contributors
                Role: ConceptualizationRole: Data curationRole: Formal analysisRole: Funding acquisitionRole: InvestigationRole: MethodologyRole: Project administrationRole: ResourcesRole: SoftwareRole: SupervisionRole: ValidationRole: VisualizationRole: Writing – original draftRole: Writing – review & editing
                Role: Data curationRole: Formal analysisRole: InvestigationRole: MethodologyRole: ValidationRole: VisualizationRole: Writing – review & editing
                Role: InvestigationRole: ResourcesRole: Supervision
                Role: InvestigationRole: MethodologyRole: Validation
                Role: InvestigationRole: MethodologyRole: Validation
                Role: Software
                Role: Software
                Role: ConceptualizationRole: InvestigationRole: MethodologyRole: SupervisionRole: ValidationRole: Writing – review & editing
                Role: Editor
                Journal
                PLoS One
                PLoS ONE
                plos
                plosone
                PLoS ONE
                Public Library of Science (San Francisco, CA USA )
                1932-6203
                2017
                22 November 2017
                : 12
                : 11
                : e0188532
                Affiliations
                [1 ] Revon Systems Inc, Louisville, KY, United States of America, 40014
                [2 ] Department of Mathematics, University of Delaware, Newark, DE, United States of America, 19716
                [3 ] Department of Pulmonology, Kaiser Permanente, Clackamas, OR, United States of America, 97015
                [4 ] Vancouver Clinic Division of Pulmonology & Critical Care, Vancouver, WA, United States of America, 98664
                [5 ] Washington State University School of Medicine, Spokane, WA, United States of America, 99210
                [6 ] Department of Medicine, National Jewish Health, Denver, CO, United States of America, 80206
                Ospedale S. Corona, ITALY
                Author notes

                Competing Interests: We would like to disclose that Anthony N. Gerber is a consultant for Revon Systems Inc and holds stock options. This does not alter our adherence to PLOS ONE policies on sharing data and materials.

                Author information
                http://orcid.org/0000-0002-2931-691X
                Article
                PONE-D-17-29303
                10.1371/journal.pone.0188532
                5699810
                29166411
                34c9285a-ab04-4e5a-a30e-fc7b2f674d8f
                © 2017 Swaminathan et al

                This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

                History
                : 20 August 2017
                : 8 November 2017
                Page count
                Figures: 9, Tables: 4, Pages: 21
                Funding
                The authors received no specific funding for this work.
                Categories
                Research Article
                People and Places
                Population Groupings
                Professions
                Medical Personnel
                Medical Doctors
                Physicians
                Medicine and Health Sciences
                Health Care
                Health Care Providers
                Medical Doctors
                Physicians
                Physical Sciences
                Mathematics
                Applied Mathematics
                Algorithms
                Research and Analysis Methods
                Simulation and Modeling
                Algorithms
                Medicine and Health Sciences
                Pulmonology
                Chronic Obstructive Pulmonary Disease
                People and Places
                Population Groupings
                Professions
                Medical Personnel
                Medical Doctors
                Medicine and Health Sciences
                Health Care
                Health Care Providers
                Medical Doctors
                Medicine and Health Sciences
                Pulmonology
                Medicine and Health Sciences
                Critical Care and Emergency Medicine
                Research and Analysis Methods
                Mathematical and Statistical Techniques
                Statistical Methods
                Forecasting
                Physical Sciences
                Mathematics
                Statistics (Mathematics)
                Statistical Methods
                Forecasting
                Engineering and Technology
                Management Engineering
                Decision Analysis
                Decision Trees
                Research and Analysis Methods
                Decision Analysis
                Decision Trees
                Custom metadata
                The data is available as a Supporting Information file.

                Uncategorized
                Uncategorized

                Comments

                Comment on this article