Literature DB >> 29221286

Automatic Lung-RADS™ classification with a natural language processing system.

Sebastian E Beyer1, Brady J McKee1, Shawn M Regis2, Andrea B McKee2, Sebastian Flacke1, Gilan El Saadawi3, Christoph Wald1.   

Abstract

BACKGROUND: Our aim was to train a natural language processing (NLP) algorithm to capture imaging characteristics of lung nodules reported in a structured CT report and suggest the applicable Lung-RADS™ (LR) category.
METHODS: Our study included structured, clinical reports of consecutive CT lung screening (CTLS) exams performed from 08/2014 to 08/2015 at an ACR accredited Lung Cancer Screening Center. All patients screened were at high-risk for lung cancer according to the NCCN Guidelines®. All exams were interpreted by one of three radiologists credentialed to read CTLS exams using LR using a standard reporting template. Training and test sets consisted of consecutive exams. Lung screening exams were divided into two groups: three training sets (500, 120, and 383 reports each) and one final evaluation set (498 reports). NLP algorithm results were compared with the gold standard of LR category assigned by the radiologist.
RESULTS: The sensitivity/specificity of the NLP algorithm to correctly assign LR categories for suspicious nodules (LR 4) and positive nodules (LR 3/4) were 74.1%/98.6% and 75.0%/98.8% respectively. The majority of mismatches occurred in cases where pulmonary findings were present not currently addressed by LR. Misclassifications also resulted from the failure to identify exams as follow-up and the failure to completely characterize part-solid nodules. In a sub-group analysis among structured reports with standardized language, the sensitivity and specificity to detect LR 4 nodules were 87.0% and 99.5%, respectively.
CONCLUSIONS: An NLP system can accurately suggest the appropriate LR category from CTLS exam findings when standardized reporting is used.

Entities:  

Keywords:  CT lung screening (CTLS); Lung-RADS™ (LR); natural language processing (NLP)

Year:  2017        PMID: 29221286      PMCID: PMC5708435          DOI: 10.21037/jtd.2017.08.13

Source DB:  PubMed          Journal:  J Thorac Dis        ISSN: 2072-1439            Impact factor:   2.895


  21 in total

1.  Automated extraction and normalization of findings from cancer-related free-text radiology reports.

Authors:  Burke W Mamlin; Daniel T Heinze; Clement J McDonald
Journal:  AMIA Annu Symp Proc       Date:  2003

2.  Natural Language Processing Techniques for Extracting and Categorizing Finding Measurements in Narrative Radiology Reports.

Authors:  M Sevenster; J Buurman; P Liu; J F Peters; P J Chang
Journal:  Appl Clin Inform       Date:  2015-09-30       Impact factor: 2.342

3.  Standardizing Clinical Document Names Using the HL7/LOINC Document Ontology and LOINC Codes.

Authors:  Elizabeth S Chen; Genevieve B Melton; Mark E Engelstad; Indra Neil Sarkar
Journal:  AMIA Annu Symp Proc       Date:  2010-11-13

4.  Identification of findings suspicious for breast cancer based on natural language processing of mammogram reports.

Authors:  N L Jain; C Friedman
Journal:  Proc AMIA Annu Fall Symp       Date:  1997

5.  Automated identification of patients with pulmonary nodules in an integrated health system using administrative health plan data, radiology reports, and natural language processing.

Authors:  Kim N Danforth; Megan I Early; Sharon Ngan; Anne E Kosco; Chengyi Zheng; Michael K Gould
Journal:  J Thorac Oncol       Date:  2012-08       Impact factor: 15.609

6.  Offering lung cancer screening to high-risk medicare beneficiaries saves lives and is cost-effective: an actuarial analysis.

Authors:  Bruce S Pyenson; Claudia I Henschke; David F Yankelevitz; Rowena Yip; Ellynne Dec
Journal:  Am Health Drug Benefits       Date:  2014-08

Review 7.  Low-dose computed tomography screening for lung cancer in a clinical setting: essential elements of a screening program.

Authors:  Brady J McKee; Andrea B McKee; Andrea Borondy Kitts; Shawn M Regis; Christoph Wald
Journal:  J Thorac Imaging       Date:  2015-03       Impact factor: 3.000

8.  Performance of ACR Lung-RADS in a clinical CT lung screening program.

Authors:  Brady J McKee; Shawn M Regis; Andrea B McKee; Sebastian Flacke; Christoph Wald
Journal:  J Am Coll Radiol       Date:  2014-08-28       Impact factor: 5.532

9.  Information Extraction for Clinical Data Mining: A Mammography Case Study.

Authors:  Houssam Nassif; Ryan Woods; Elizabeth Burnside; Mehmet Ayvaci; Jude Shavlik; David Page
Journal:  Proc IEEE Int Conf Data Min       Date:  2009

Review 10.  Issues with implementing a high-quality lung cancer screening program.

Authors:  James L Mulshine; Thomas A D'Amico
Journal:  CA Cancer J Clin       Date:  2014-06-27       Impact factor: 508.702

View more
  5 in total

Review 1.  Recommendations for lung cancer screening in Southern Africa.

Authors:  Coenraad F N Koegelenberg; Shane Dorfman; Ivan Schewitz; Guy A Richards; Shaun Maasdorp; Clifford Smith; Keertan Dheda
Journal:  J Thorac Dis       Date:  2019-09       Impact factor: 2.895

Review 2.  [Basics and applications of Natural Language Processing (NLP) in radiology].

Authors:  F Jungmann; S Kuhn; B Kämpgen
Journal:  Radiologe       Date:  2018-08       Impact factor: 0.635

3.  A systematic review of natural language processing applied to radiology reports.

Authors:  Arlene Casey; Emma Davidson; Michael Poon; Hang Dong; Daniel Duma; Andreas Grivas; Claire Grover; Víctor Suárez-Paniagua; Richard Tobin; William Whiteley; Honghan Wu; Beatrice Alex
Journal:  BMC Med Inform Decis Mak       Date:  2021-06-03       Impact factor: 2.796

Review 4.  Assessment of Electronic Health Record for Cancer Research and Patient Care Through a Scoping Review of Cancer Natural Language Processing.

Authors:  Liwei Wang; Sunyang Fu; Andrew Wen; Xiaoyang Ruan; Huan He; Sijia Liu; Sungrim Moon; Michelle Mai; Irbaz B Riaz; Nan Wang; Ping Yang; Hua Xu; Jeremy L Warner; Hongfang Liu
Journal:  JCO Clin Cancer Inform       Date:  2022-07

Review 5.  The Role of Artificial Intelligence in Early Cancer Diagnosis.

Authors:  Benjamin Hunter; Sumeet Hindocha; Richard W Lee
Journal:  Cancers (Basel)       Date:  2022-03-16       Impact factor: 6.639

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.