Daniel R Morales1, Rob Flynn2, Jianguo Zhang3, Emmanuel Trucco3, Jennifer K Quint4, Kris Zutis2. 1. Population Health Sciences Division, School of Medicine, University of Dundee, UK; Scottish Centre for Respiratory Research, School of Medicine, University of Dundee, UK. Electronic address: d.r.z.morales@dundee.ac.uk. 2. Medicines Monitoring Unit, School of Medicine, University of Dundee, UK. 3. School of Science and Engineering (Computing), University of Dundee, UK. 4. Department of Respiratory Epidemiology, Occupational Medicine and Public Health, National Heart and Lung Institute, Imperial College London, UK.
Abstract
BACKGROUND: Several models for predicting the risk of death in people with chronic obstructive pulmonary disease (COPD) exist but have not undergone large scale validation in primary care. The objective of this study was to externally validate these models using statistical and machine learning approaches. METHODS: We used a primary care COPD cohort identified using data from the UK Clinical Practice Research Datalink. Age-standardised mortality rates were calculated for the population by gender and discrimination of ADO (age, dyspnoea, airflow obstruction), COTE (COPD-specific comorbidity test), DOSE (dyspnoea, airflow obstruction, smoking, exacerbations) and CODEX (comorbidity, dyspnoea, airflow obstruction, exacerbations) at predicting death over 1-3 years measured using logistic regression and a support vector machine learning (SVM) method of analysis. RESULTS: The age-standardised mortality rate was 32.8 (95%CI 32.5-33.1) and 25.2 (95%CI 25.4-25.7) per 1000 person years for men and women respectively. Complete data were available for 54879 patients to predict 1-year mortality. ADO performed the best (c-statistic of 0.730) compared with DOSE (c-statistic 0.645), COTE (c-statistic 0.655) and CODEX (c-statistic 0.649) at predicting 1-year mortality. Discrimination of ADO and DOSE improved at predicting 1-year mortality when combined with COTE comorbidities (c-statistic 0.780 ADO + COTE; c-statistic 0.727 DOSE + COTE). Discrimination did not change significantly over 1-3 years. Comparable results were observed using SVM. CONCLUSION: In primary care, ADO appears superior at predicting death in COPD. Performance of ADO and DOSE improved when combined with COTE comorbidities suggesting better models may be generated with additional data facilitated using novel approaches.
BACKGROUND: Several models for predicting the risk of death in people with chronic obstructive pulmonary disease (COPD) exist but have not undergone large scale validation in primary care. The objective of this study was to externally validate these models using statistical and machine learning approaches. METHODS: We used a primary care COPD cohort identified using data from the UK Clinical Practice Research Datalink. Age-standardised mortality rates were calculated for the population by gender and discrimination of ADO (age, dyspnoea, airflow obstruction), COTE (COPD-specific comorbidity test), DOSE (dyspnoea, airflow obstruction, smoking, exacerbations) and CODEX (comorbidity, dyspnoea, airflow obstruction, exacerbations) at predicting death over 1-3 years measured using logistic regression and a support vector machine learning (SVM) method of analysis. RESULTS: The age-standardised mortality rate was 32.8 (95%CI 32.5-33.1) and 25.2 (95%CI 25.4-25.7) per 1000 person years for men and women respectively. Complete data were available for 54879 patients to predict 1-year mortality. ADO performed the best (c-statistic of 0.730) compared with DOSE (c-statistic 0.645), COTE (c-statistic 0.655) and CODEX (c-statistic 0.649) at predicting 1-year mortality. Discrimination of ADO and DOSE improved at predicting 1-year mortality when combined with COTE comorbidities (c-statistic 0.780 ADO + COTE; c-statistic 0.727 DOSE + COTE). Discrimination did not change significantly over 1-3 years. Comparable results were observed using SVM. CONCLUSION: In primary care, ADO appears superior at predicting death in COPD. Performance of ADO and DOSE improved when combined with COTE comorbidities suggesting better models may be generated with additional data facilitated using novel approaches.
Authors: Lan Ai Kieu Le; Ane Johannessen; Jon Andrew Hardie; Odd Erik Johansen; Amund Gulsvik; Bjørn Egil Vikse; Per Bakke Journal: Int J Chron Obstruct Pulmon Dis Date: 2019-07-23
Authors: Catherine Owusuaa; Simone A Dijkland; Daan Nieboer; Carin C D van der Rijt; Agnes van der Heide Journal: BMC Pulm Med Date: 2022-04-04 Impact factor: 3.317
Authors: Spencer J Keene; Rachel E Jordan; Frits Me Franssen; Frank de Vries; James Martin; Alice Sitch; Alice Margaret Turner; Andrew P Dickens; David Fitzmaurice; Peymane Adab Journal: Int J Chron Obstruct Pulmon Dis Date: 2019-10-24