Your browser doesn't support javascript.
loading
Performance of a Chest Radiography AI Algorithm for Detection of Missed or Mislabeled Findings: A Multicenter Study.
Kaviani, Parisa; Digumarthy, Subba R; Bizzo, Bernardo C; Reddy, Bhargava; Tadepalli, Manoj; Putha, Preetham; Jagirdar, Ammar; Ebrahimian, Shadi; Kalra, Mannudeep K; Dreyer, Keith J.
Afiliação
  • Kaviani P; Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA.
  • Digumarthy SR; Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA.
  • Bizzo BC; Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA.
  • Reddy B; MGH & BWH Center for Clinical Data Science, Boston, MA 02114, USA.
  • Tadepalli M; Qure.ai, Mumbai 400063, India.
  • Putha P; Qure.ai, Mumbai 400063, India.
  • Jagirdar A; Qure.ai, Mumbai 400063, India.
  • Ebrahimian S; Qure.ai, Mumbai 400063, India.
  • Kalra MK; Internal Medicine, Icahn School of Medicine at Mount Sinai, Elmhurst Hospital Center, Elmhurst, NY 11373, USA.
  • Dreyer KJ; Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA.
Diagnostics (Basel) ; 12(9)2022 Aug 28.
Article em En | MEDLINE | ID: mdl-36140488
Purpose: We assessed whether a CXR AI algorithm was able to detect missed or mislabeled chest radiograph (CXR) findings in radiology reports. Methods: We queried a multi-institutional radiology reports search database of 13 million reports to identify all CXR reports with addendums from 1999-2021. Of the 3469 CXR reports with an addendum, a thoracic radiologist excluded reports where addenda were created for typographic errors, wrong report template, missing sections, or uninterpreted signoffs. The remaining reports contained addenda (279 patients) with errors related to side-discrepancies or missed findings such as pulmonary nodules, consolidation, pleural effusions, pneumothorax, and rib fractures. All CXRs were processed with an AI algorithm. Descriptive statistics were performed to determine the sensitivity, specificity, and accuracy of the AI in detecting missed or mislabeled findings. Results: The AI had high sensitivity (96%), specificity (100%), and accuracy (96%) for detecting all missed and mislabeled CXR findings. The corresponding finding-specific statistics for the AI were nodules (96%, 100%, 96%), pneumothorax (84%, 100%, 85%), pleural effusion (100%, 17%, 67%), consolidation (98%, 100%, 98%), and rib fractures (87%, 100%, 94%). Conclusions: The CXR AI could accurately detect mislabeled and missed findings. Clinical Relevance: The CXR AI can reduce the frequency of errors in detection and side-labeling of radiographic findings.
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Tipo de estudo: Clinical_trials / Diagnostic_studies / Prognostic_studies Idioma: En Revista: Diagnostics (Basel) Ano de publicação: 2022 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Tipo de estudo: Clinical_trials / Diagnostic_studies / Prognostic_studies Idioma: En Revista: Diagnostics (Basel) Ano de publicação: 2022 Tipo de documento: Article