Automatic Extraction of Major Osteoporotic Fractures from Radiology Reports using Natural Language Processing

Yanshan Wang; Saeed Mehrabi; Sunghwan Sohn; Elizabeth Atkinson; Shreyasee Amin; Hongfang Liu

doi:10.1109/ICHI-W.2018.00021

Automatic Extraction of Major Osteoporotic Fractures from Radiology Reports using Natural Language Processing

Yanshan Wang, Saeed Mehrabi, Sunghwan Sohn, Elizabeth Atkinson, Shreyasee Amin, Hongfang Liu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

In this study, we developed a rule-based natural language processing (NLP) algorithm for automatic extraction of six major osteoporotic fractures from radiology reports. We validated the NLP algorithm using a dataset of radiology reports from Mayo Clinic with the gold standard constructed by medical experts. The micro-Averaged sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score of the proposed NLP algorithm are 0.796, 0.978, 0.972, 0.831, 0.874, respectively. The highest F1-score was achieved at 0.958 for the extraction of proximal femur fracture while the lowest was 0.821 for the hand and finger/wrists fracture. The experimental results verified the effectiveness of the proposed rule-based NLP algorithm in the automatic extraction of major osteoporotic fractures from radiology reports.

Original language	English (US)
Title of host publication	Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	64-65
Number of pages	2
ISBN (Electronic)	9781538667774
DOIs	https://doi.org/10.1109/ICHI-W.2018.00021
State	Published - Jul 16 2018
Event	6th IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018 - New York, United States Duration: Jun 4 2018 → Jun 7 2018

Publication series

Name	Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018

Other

Other	6th IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018
Country/Territory	United States
City	New York
Period	6/4/18 → 6/7/18

Keywords

fracture
natural language processing
osteoporosis
radiology report

ASJC Scopus subject areas

Information Systems and Management
Health Informatics

Access to Document

10.1109/ICHI-W.2018.00021

Cite this

Wang, Y., Mehrabi, S., Sohn, S., Atkinson, E., Amin, S., & Liu, H. (2018). Automatic Extraction of Major Osteoporotic Fractures from Radiology Reports using Natural Language Processing. In Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018 (pp. 64-65). Article 8411807 (Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICHI-W.2018.00021

Automatic Extraction of Major Osteoporotic Fractures from Radiology Reports using Natural Language Processing. / Wang, Yanshan; Mehrabi, Saeed; Sohn, Sunghwan et al.
Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 64-65 8411807 (Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Wang, Y, Mehrabi, S, Sohn, S, Atkinson, E, Amin, S & Liu, H 2018, Automatic Extraction of Major Osteoporotic Fractures from Radiology Reports using Natural Language Processing. in Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018., 8411807, Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018, Institute of Electrical and Electronics Engineers Inc., pp. 64-65, 6th IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018, New York, United States, 6/4/18. https://doi.org/10.1109/ICHI-W.2018.00021

Wang Y, Mehrabi S, Sohn S, Atkinson E, Amin S, Liu H. Automatic Extraction of Major Osteoporotic Fractures from Radiology Reports using Natural Language Processing. In Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 64-65. 8411807. (Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018). doi: 10.1109/ICHI-W.2018.00021

Wang, Yanshan ; Mehrabi, Saeed ; Sohn, Sunghwan et al. / Automatic Extraction of Major Osteoporotic Fractures from Radiology Reports using Natural Language Processing. Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 64-65 (Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018).

@inproceedings{7ef26d9eace34f51afce50c1c3f8f696,

title = "Automatic Extraction of Major Osteoporotic Fractures from Radiology Reports using Natural Language Processing",

abstract = "In this study, we developed a rule-based natural language processing (NLP) algorithm for automatic extraction of six major osteoporotic fractures from radiology reports. We validated the NLP algorithm using a dataset of radiology reports from Mayo Clinic with the gold standard constructed by medical experts. The micro-Averaged sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score of the proposed NLP algorithm are 0.796, 0.978, 0.972, 0.831, 0.874, respectively. The highest F1-score was achieved at 0.958 for the extraction of proximal femur fracture while the lowest was 0.821 for the hand and finger/wrists fracture. The experimental results verified the effectiveness of the proposed rule-based NLP algorithm in the automatic extraction of major osteoporotic fractures from radiology reports.",

keywords = "fracture, natural language processing, osteoporosis, radiology report",

author = "Yanshan Wang and Saeed Mehrabi and Sunghwan Sohn and Elizabeth Atkinson and Shreyasee Amin and Hongfang Liu",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 6th IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018 ; Conference date: 04-06-2018 Through 07-06-2018",

year = "2018",

month = jul,

day = "16",

doi = "10.1109/ICHI-W.2018.00021",

language = "English (US)",

series = "Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "64--65",

booktitle = "Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018",

}

TY - GEN

T1 - Automatic Extraction of Major Osteoporotic Fractures from Radiology Reports using Natural Language Processing

AU - Wang, Yanshan

AU - Mehrabi, Saeed

AU - Sohn, Sunghwan

AU - Atkinson, Elizabeth

AU - Amin, Shreyasee

AU - Liu, Hongfang

PY - 2018/7/16

Y1 - 2018/7/16

N2 - In this study, we developed a rule-based natural language processing (NLP) algorithm for automatic extraction of six major osteoporotic fractures from radiology reports. We validated the NLP algorithm using a dataset of radiology reports from Mayo Clinic with the gold standard constructed by medical experts. The micro-Averaged sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score of the proposed NLP algorithm are 0.796, 0.978, 0.972, 0.831, 0.874, respectively. The highest F1-score was achieved at 0.958 for the extraction of proximal femur fracture while the lowest was 0.821 for the hand and finger/wrists fracture. The experimental results verified the effectiveness of the proposed rule-based NLP algorithm in the automatic extraction of major osteoporotic fractures from radiology reports.

AB - In this study, we developed a rule-based natural language processing (NLP) algorithm for automatic extraction of six major osteoporotic fractures from radiology reports. We validated the NLP algorithm using a dataset of radiology reports from Mayo Clinic with the gold standard constructed by medical experts. The micro-Averaged sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score of the proposed NLP algorithm are 0.796, 0.978, 0.972, 0.831, 0.874, respectively. The highest F1-score was achieved at 0.958 for the extraction of proximal femur fracture while the lowest was 0.821 for the hand and finger/wrists fracture. The experimental results verified the effectiveness of the proposed rule-based NLP algorithm in the automatic extraction of major osteoporotic fractures from radiology reports.

KW - fracture

KW - natural language processing

KW - osteoporosis

KW - radiology report

UR - http://www.scopus.com/inward/record.url?scp=85051022287&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051022287&partnerID=8YFLogxK

U2 - 10.1109/ICHI-W.2018.00021

DO - 10.1109/ICHI-W.2018.00021

M3 - Conference contribution

AN - SCOPUS:85051022287

T3 - Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018

SP - 64

EP - 65

BT - Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 6th IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018

Y2 - 4 June 2018 through 7 June 2018

ER -

Automatic Extraction of Major Osteoporotic Fractures from Radiology Reports using Natural Language Processing

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this