+1 Recommend
1 collections
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Identification of Patient Profiles with High Risk of Hospital Re-Admissions for Acute COPD Exacerbations (AECOPD) in France Using a Machine Learning Model

      Read this article at

          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.



          To characterise patients with chronic obstructive pulmonary disease (COPD) who are rehospitalised for an acute exacerbation, to estimate the cost of these hospitalisations, to characterise high risk patient sub groups and to identify factors potentially associated with the risk of rehospitalisation.

          Patients and Methods

          This was a retrospective study using the French National Hospital Discharge Database. All patients aged ≥40 years hospitalised for an acute exacerbation of COPD between 2015 and 2016 were identified and followed for six months. Patients with at least one rehospitalisation for acute exacerbation of COPD constituted the rehospitalisation analysis population. A machine learning model was built to study the factors associated with the risk of rehospitalisation using decision tree analysis. A direct cost analysis was performed from the perspective of national health insurance.


          A total of 143,006 eligible patients were hospitalised for an acute exacerbation of COPD (AECOPD) in 2015–2016 (mean age: 74 years; 62.1% men). 25,090 (18.8%) were rehospitalised for another exacerbation within six months. In this study, 8.5% of patients died during or immediately following the index hospitalisation and 10.5% died during or immediately after rehospitalisation ( p <0.001). The specific cost of these rehospitalisations was € 5304. The overall total cost per patient of all AECOPD-related stays was € 9623, being significantly higher in patients who were rehospitalised (€ 16,275) compared to those who were not (€ 8208). In decision tree analysis, the most important driver of rehospitalisation was hospitalisation in the previous two years (contributing 85% of the information).


          Rehospitalisations for acute exacerbations of COPD carry a high epidemiological and economic burden. Since hospitalisation for an acute exacerbation is the most important determinant of future rehospitalisations, management of COPD needs to focus on interventions aimed at decreasing the rehospitalisation risk of in order to lower the burden of disease.

          Related collections

          Most cited references 27

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

          Chronic obstructive pulmonary disease exacerbations in the COPDGene study: associated radiologic phenotypes.

          To test the hypothesis-given the increasing emphasis on quantitative computed tomographic (CT) phenotypes of chronic obstructive pulmonary disease (COPD)-that a relationship exists between COPD exacerbation frequency and quantitative CT measures of emphysema and airway disease. This research protocol was approved by the institutional review board of each participating institution, and all participants provided written informed consent. One thousand two subjects who were enrolled in the COPDGene Study and met the GOLD (Global Initiative for Chronic Obstructive Lung Disease) criteria for COPD with quantitative CT analysis were included. Total lung emphysema percentage was measured by using the attenuation mask technique with a -950-HU threshold. An automated program measured the mean wall thickness and mean wall area percentage in six segmental bronchi. The frequency of COPD exacerbation in the prior year was determined by using a questionnaire. Statistical analysis was performed to examine the relationship of exacerbation frequency with lung function and quantitative CT measurements. In a multivariate analysis adjusted for lung function, bronchial wall thickness and total lung emphysema percentage were associated with COPD exacerbation frequency. Each 1-mm increase in bronchial wall thickness was associated with a 1.84-fold increase in annual exacerbation rate (P = .004). For patients with 35% or greater total emphysema, each 5% increase in emphysema was associated with a 1.18-fold increase in this rate (P = .047). Greater lung emphysema and airway wall thickness were associated with COPD exacerbations, independent of the severity of airflow obstruction. Quantitative CT can help identify subgroups of patients with COPD who experience exacerbations for targeted research and therapy development for individual phenotypes. © RSNA, 2011.
            • Record: found
            • Abstract: found
            • Article: not found

            Risk factors for rehospitalisation in COPD: role of health status, anxiety and depression.

            The aim of the present study was to analyse the risk of rehospitalisation in patients with chronic obstructive pulmonary disease and associated risk factors. This prospective study included 416 patients from a university hospital in each of the five Nordic countries. Data included demographic information, spirometry, comorbidity and 12 month follow-up for 406 patients. The hospital anxiety and depression scale and St. George's Respiratory Questionnaire (SGRQ) were applied to all patients. The number of patients that had a re-admission within 12 months was 246 (60.6%). Patients that had a re-admission had lower lung function and health status. A low forced expiratory volume in one second (FEV1) and health status were independent predictors for re-admission. Hazard ratio (HR; 95% CI) was 0.82 (0.74-0.90) per 10% increase of the predicted FEV1 and 1.06 (1.02-1.10) per 4 units increase in total SGRQ score. The risk of rehospitalisation was also increased in subjects with anxiety (HR 1.76 (1.16-2.68)) and in subjects with low health status (total SGRQ score >60 units). When comparing the different subscales in the SGRQ, the closest relation between the risk of rehospitalisation was seen with the activity scale (HR 1.07 (1.03-1.11) per 4 unit increase). In patients with low health status, anxiety is an important risk factor for rehospitalisation. This may be important for patient treatment and warrants further studies.
              • Record: found
              • Abstract: found
              • Article: found
              Is Open Access

              Frequency of Exacerbations in COPD: An Analysis of the SPIROMICS Cohort

              Background Current treatment strategies to stratify exacerbation risk rely on history of ≥2 events in the previous year. To understand year-to-year variability and factors associated with consistent exacerbations over time, we present a prospective analysis of the SPIROMICS cohort. Methods We analyzed SPIROMICS participants with COPD and three years of prospective data (n=1,105). We classified participants according to yearly exacerbation frequency. Stepwise logistic regression compared factors associated with individuals experiencing ≥1 AECOPD in every year for three years versus none. Results During three years follow-up, 48·7% of participants experienced at least one AECOPD, while the majority (51·3%) experienced none. Only 2·1% had ≥2 AECOPD in each year. An inconsistent pattern (both years with and years without AECOPD) was common (41·3% of the group), particularly among GOLD stages 3 and 4 subjects (56·1%). In logistic regression, consistent AECOPD (≥1 event per year for three years) as compared to no AECOPD were associated with higher baseline symptom burden assessed with the COPD Assessment Test, previous exacerbations, greater evidence of small airway abnormality by computed tomography, lower Interleukin-15 (IL-15) and elevated Interleukin-8 (IL-8). Conclusions Although AECOPD are common, the exacerbation status of most individuals varies markedly from year to year. Among participants who experienced any AECOPD over three years, very few repeatedly experienced ≥2 events/year. In addition to symptoms and history of exacerbations in the prior year, we identified several novel biomarkers associated with consistent exacerbations, including CT-defined small airway abnormality, IL-15 and IL-8.

                Author and article information

                Int J Chron Obstruct Pulmon Dis
                Int J Chron Obstruct Pulmon Dis
                International Journal of Chronic Obstructive Pulmonary Disease
                30 April 2020
                : 15
                : 949-962
                [1 ]Service de Pneumologie, Institut du Thorax, CHU de Nantes , Nantes, France
                [2 ]Service de Pneumologie, CHU Dupuytren , Limoges, France
                [3 ]HEVA , Lyon, France
                [4 ]HEOR/RWE, Boehringer Ingelheim , Paris, France
                [5 ]Institutional and Hospital Partnership, Boehringer Ingelheim , Paris, France
                [6 ]Medical Affairs, Boehringer Ingelheim , Paris, France
                [7 ]CHRU Tours , Tours, France
                [8 ]Service de Pneumologie, CHRU Bretonneau , Tours, France
                Author notes
                Correspondence: Marie Laurent 186 Avenue Thiers, Lyon69006, FranceTel +33 4 72 74 25 60 Email
                © 2020 Cavailles et al.

                This work is published and licensed by Dove Medical Press Limited. The full terms of this license are available at and incorporate the Creative Commons Attribution – Non Commercial (unported, v3.0) License ( By accessing the work you hereby accept the Terms. Non-commercial uses of the work are permitted without any further permission from Dove Medical Press Limited, provided the work is properly attributed. For permission for commercial use of this work, please see paragraphs 4.2 and 5 of our Terms (

                Page count
                Figures: 5, Tables: 3, References: 50, Pages: 14
                The study was funded by Boehringer Ingelheim SA.
                Original Research

                Respiratory medicine

                decision tree analysis, comorbidity, rehospitalisation, cost


                Comment on this article