Automated Detection of Type of Scoliosis Surgery from Operative Notes Using Natural Language Processing

Elham Sagheb, Taghi Ramazania, Noelle Larson, Sunghwan Sohn, Hilal Maradit Kremers

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Scoliosis is an abnormal lateral curvature of the spine and managed surgically in severe cases. There is growing interest in comparing the effectiveness and safety of different surgical options. Yet, the type of surgical procedure is not readily available in a structured format in large databases but resides in the free text of the operative notes, hindering comparative effectiveness studies. In this study, we implemented a high-performance natural language processing (NLP) algorithm to classify 3 types of scoliosis surgery from the free text of operative notes.

Original languageEnglish (US)
Title of host publicationProceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages497-498
Number of pages2
ISBN (Electronic)9781665468459
DOIs
StatePublished - 2022
Event10th IEEE International Conference on Healthcare Informatics, ICHI 2022 - Rochester, United States
Duration: Jun 11 2022Jun 14 2022

Publication series

NameProceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022

Conference

Conference10th IEEE International Conference on Healthcare Informatics, ICHI 2022
Country/TerritoryUnited States
CityRochester
Period6/11/226/14/22

Keywords

  • fusion
  • growing rod
  • natural language processing
  • non-fusion
  • Scoliosis

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality
  • Health Informatics

Fingerprint

Dive into the research topics of 'Automated Detection of Type of Scoliosis Surgery from Operative Notes Using Natural Language Processing'. Together they form a unique fingerprint.

Cite this