Sarah Jabbour1, David Fouhey1, Ella Kazerooni2, Jenna Wiens1, Michael W Sjoding3. 1. Department of Electrical Engineering and Computer Science, Division of Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, USA. 2. Department of Radiology, University of Michigan Medical School, Ann Arbor, Michigan, USA. 3. Pulmonary and Critical Care Medicine, Department of Internal Medicine, University of Michigan Medical School, Ann Arbor, Michigan, USA.
Abstract
OBJECTIVE: When patients develop acute respiratory failure (ARF), accurately identifying the underlying etiology is essential for determining the best treatment. However, differentiating between common medical diagnoses can be challenging in clinical practice. Machine learning models could improve medical diagnosis by aiding in the diagnostic evaluation of these patients. MATERIALS AND METHODS: Machine learning models were trained to predict the common causes of ARF (pneumonia, heart failure, and/or chronic obstructive pulmonary disease [COPD]). Models were trained using chest radiographs and clinical data from the electronic health record (EHR) and applied to an internal and external cohort. RESULTS: The internal cohort of 1618 patients included 508 (31%) with pneumonia, 363 (22%) with heart failure, and 137 (8%) with COPD based on physician chart review. A model combining chest radiographs and EHR data outperformed models based on each modality alone. Models had similar or better performance compared to a randomly selected physician reviewer. For pneumonia, the combined model area under the receiver operating characteristic curve (AUROC) was 0.79 (0.77-0.79), image model AUROC was 0.74 (0.72-0.75), and EHR model AUROC was 0.74 (0.70-0.76). For heart failure, combined: 0.83 (0.77-0.84), image: 0.80 (0.71-0.81), and EHR: 0.79 (0.75-0.82). For COPD, combined: AUROC = 0.88 (0.83-0.91), image: 0.83 (0.77-0.89), and EHR: 0.80 (0.76-0.84). In the external cohort, performance was consistent for heart failure and increased for COPD, but declined slightly for pneumonia. CONCLUSIONS: Machine learning models combining chest radiographs and EHR data can accurately differentiate between common causes of ARF. Further work is needed to determine how these models could act as a diagnostic aid to clinicians in clinical settings.
OBJECTIVE: When patients develop acute respiratory failure (ARF), accurately identifying the underlying etiology is essential for determining the best treatment. However, differentiating between common medical diagnoses can be challenging in clinical practice. Machine learning models could improve medical diagnosis by aiding in the diagnostic evaluation of these patients. MATERIALS AND METHODS: Machine learning models were trained to predict the common causes of ARF (pneumonia, heart failure, and/or chronic obstructive pulmonary disease [COPD]). Models were trained using chest radiographs and clinical data from the electronic health record (EHR) and applied to an internal and external cohort. RESULTS: The internal cohort of 1618 patients included 508 (31%) with pneumonia, 363 (22%) with heart failure, and 137 (8%) with COPD based on physician chart review. A model combining chest radiographs and EHR data outperformed models based on each modality alone. Models had similar or better performance compared to a randomly selected physician reviewer. For pneumonia, the combined model area under the receiver operating characteristic curve (AUROC) was 0.79 (0.77-0.79), image model AUROC was 0.74 (0.72-0.75), and EHR model AUROC was 0.74 (0.70-0.76). For heart failure, combined: 0.83 (0.77-0.84), image: 0.80 (0.71-0.81), and EHR: 0.79 (0.75-0.82). For COPD, combined: AUROC = 0.88 (0.83-0.91), image: 0.83 (0.77-0.89), and EHR: 0.80 (0.76-0.84). In the external cohort, performance was consistent for heart failure and increased for COPD, but declined slightly for pneumonia. CONCLUSIONS: Machine learning models combining chest radiographs and EHR data can accurately differentiate between common causes of ARF. Further work is needed to determine how these models could act as a diagnostic aid to clinicians in clinical settings.
Authors: A L Goldberger; L A Amaral; L Glass; J M Hausdorff; P C Ivanov; R G Mark; J E Mietus; G B Moody; C K Peng; H E Stanley Journal: Circulation Date: 2000-06-13 Impact factor: 29.690
Authors: Stefano Nardini; Isabella Annesi-Maesano; Marzia Simoni; Adriana Del Ponte; Claudio Maria Sanguinetti; Fernando De Benedetto Journal: Respir Med Date: 2018-08-17 Impact factor: 3.415
Authors: Mihaela S Stefan; Meng-Shiou Shieh; Penelope S Pekow; Michael B Rothberg; Jay S Steingrub; Tara Lagu; Peter K Lindenauer Journal: J Hosp Med Date: 2013-01-18 Impact factor: 2.960
Authors: Patrick Ray; Sophie Birolleau; Yannick Lefort; Marie-Hélène Becquemin; Catherine Beigelman; Richard Isnard; Antonio Teixeira; Martine Arthaud; Bruno Riou; Jacques Boddaert Journal: Crit Care Date: 2006-05-24 Impact factor: 9.097
Authors: Emmert Roberts; Andrew J Ludman; Katharina Dworzynski; Abdallah Al-Mohammad; Martin R Cowie; John J V McMurray; Jonathan Mant Journal: BMJ Date: 2015-03-04