Literature DB >> 32799005

Thyroid Ultrasound Reports: Will the Thyroid Imaging, Reporting, and Data System Improve Natural Language Processing Capture of Critical Thyroid Nodule Features?

Kallie J Chen1, Priya H Dedhia2, Joseph R Imbus2, David F Schneider2.   

Abstract

BACKGROUND: Critical thyroid nodule features are contained in unstructured ultrasound (US) reports. The Thyroid Imaging, Reporting, and Data System (TI-RADS) uses five key features to risk stratify nodules and recommend appropriate intervention. This study aims to analyze the quality of US reporting and the potential benefit of Natural Language Processing (NLP) systems in efficiently capturing TI-RADS features from text reports. MATERIALS AND
METHOD: This retrospective study used free-text thyroid US reports from an academic center (A) and community hospital (B). Physicians created "gold standard" annotations by manually extracting TI-RADS features and clinical recommendations from reports to determine how often they were included. Similar annotations were created using an automated NLP system and compared with the gold standard.
RESULTS: Two hundred eighty-two reports contained 409 nodules at least 1-cm in maximum diameter. The gold standard identified three nodules (0.7%) which contained enough information to calculate a complete TI-RADS score. Shape was described most often (92.7% of nodules), whereas margins were described least often (11%). A median number of two TI-RADS features are reported per nodule. The NLP system was significantly less accurate than the gold standard in capturing echogenicity (27.5%) and margins (58.9%). One hundred eight nodule reports (26.4%) included clinical management recommendations, which were included more often at site A than B (33.9 versus 17%, P < 0.05).
CONCLUSIONS: These results suggest a gap between current US reporting styles and those needed to implement TI-RADS and achieve NLP accuracy. Synoptic reporting should prompt more complete thyroid US reporting, improved recommendations for intervention, and better NLP performance.
Copyright © 2020 Elsevier Inc. All rights reserved.

Keywords:  Natural language processing; TI-RADS; Thyroid; Ultrasound

Mesh:

Year:  2020        PMID: 32799005      PMCID: PMC8102071          DOI: 10.1016/j.jss.2020.07.015

Source DB:  PubMed          Journal:  J Surg Res        ISSN: 0022-4804            Impact factor:   2.192


  23 in total

1.  Mayo clinical Text Analysis and Knowledge Extraction System (cTAKES): architecture, component evaluation and applications.

Authors:  Guergana K Savova; James J Masanz; Philip V Ogren; Jiaping Zheng; Sunghwan Sohn; Karin C Kipper-Schuler; Christopher G Chute
Journal:  J Am Med Inform Assoc       Date:  2010 Sep-Oct       Impact factor: 4.497

2.  Automating tissue bank annotation from pathology reports - comparison to a gold standard expert annotation set.

Authors:  Kaihong Liu; Kevin J Mitchell; Wendy W Chapman; Rebecca S Crowley
Journal:  AMIA Annu Symp Proc       Date:  2005

3.  Automated extraction of BI-RADS final assessment categories from radiology reports with natural language processing.

Authors:  Dorothy A Sippo; Graham I Warden; Katherine P Andriole; Ronilda Lacson; Ichiro Ikuta; Robyn L Birdwell; Ramin Khorasani
Journal:  J Digit Imaging       Date:  2013-10       Impact factor: 4.056

4.  Overcoming barriers to NLP for clinical text: the role of shared tasks and the need for additional creative solutions.

Authors:  Wendy W Chapman; Prakash M Nadkarni; Lynette Hirschman; Leonard W D'Avolio; Guergana K Savova; Ozlem Uzuner
Journal:  J Am Med Inform Assoc       Date:  2011 Sep-Oct       Impact factor: 4.497

5.  Thyroid Ultrasound Reports: Deficiencies and Recommendations.

Authors:  Laila Qadan; Adel Ahmed; Kusum Kapila
Journal:  Med Princ Pract       Date:  2019-02-10       Impact factor: 1.927

6.  Automated annotation and classification of BI-RADS assessment from radiology reports.

Authors:  Sergio M Castro; Eugene Tseytlin; Olga Medvedeva; Kevin Mitchell; Shyam Visweswaran; Tanja Bekhuis; Rebecca S Jacobson
Journal:  J Biomed Inform       Date:  2017-04-18       Impact factor: 6.317

7.  Thyroid nodule ultrasound reports in routine clinical practice provide insufficient information to estimate risk of malignancy.

Authors:  Christopher John Symonds; Paula Seal; Sana Ghaznavi; Winson Y Cheung; Ralf Paschke
Journal:  Endocrine       Date:  2018-05-25       Impact factor: 3.633

8.  Radiological reports: a comparison between the transmission efficiency of information in free text and in structured reports.

Authors:  Flavio Barbosa; Lea Maria Zanini Maciel; Elizabeth Melmi Vieira; Paulo M de Azevedo Marques; Jorge Elias; Valdair Francisco Muglia
Journal:  Clinics (Sao Paulo)       Date:  2010       Impact factor: 2.365

9.  Facilitating cancer research using natural language processing of pathology reports.

Authors:  Hua Xu; Kristin Anderson; Victor R Grann; Carol Friedman
Journal:  Stud Health Technol Inform       Date:  2004

10.  The utility of thyroid ultrasonography in the management of thyroid nodules.

Authors:  Gary Gamme; Tyler Parrington; Edward Wiebe; Sunita Ghosh; Brendan Litt; David C Williams; Todd P W McMullen
Journal:  Can J Surg       Date:  2017-04       Impact factor: 2.089

View more
  1 in total

Review 1.  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
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.