Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Formative Research

Date Submitted: Jan 28, 2021
Date Accepted: Sep 18, 2021

The final, peer-reviewed published version of this preprint can be found here:

Toward Data-Driven Radiation Oncology Using Standardized Terminology as a Starting Point: Cross-sectional Study

Cihoric N, Badra EV, Stenger-Weisser A, Aebersold DM, Pavic M

Toward Data-Driven Radiation Oncology Using Standardized Terminology as a Starting Point: Cross-sectional Study

JMIR Form Res 2022;6(1):e27550

DOI: 10.2196/27550

PMID: 35044315

PMCID: 8811690

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

Toward data-driven radiation oncology – standardized terminology as a starting point

  • Nikola Cihoric; 
  • Eugenia Vlaskou Badra; 
  • Anna Stenger-Weisser; 
  • Daniel M. Aebersold; 
  • Matea Pavic

ABSTRACT

Background:

The inability to seamlessly exchange information across radiation therapy ecosystems is a limiting factor in the pursuit of data-driven clinical practice. The implementation of semantic interoperability is a prerequisite for the achievement of full capacity of the latest developments in personalized and precision medicine, such as mathematical modeling, advanced algorithmic information processing as well as artificial intelligence approaches.

Objective:

In this work, we evaluate the current state of terminology resources (TR) dedicated to radiation oncology, as a prerequisite of an oncology semantic ecosystem.

Methods:

Unified Medical Language System™ (UMLS) was searched for the following terms: terms “radio oncology”, “radiation oncology”, “radiation therapy” and “radiotherapy.” We extracted a total of 6509 unique concepts for further analysis. Data processing and lexical analysis was done with Python v3.7 and python library The Natural Language Toolkit (NLTK) version 3.5.

Results:

Concepts were distributed across 35 terminology resources (TRs). The median number of unique concepts per TR was 5 (range 1 – 5479). Five TRs (14% of all TRs) contained 95% (6157) concepts. TRs were created by 29 authors. Authors of the TRs were predominantly legal entities registered in the U.S. (n=25, 71.4%), followed by international organizations (n=6, 17.1%), and legal entities registered in Australia (n=2, 5.7%), the Netherlands and United Kingdom with 1 (2.9%) author each. Out of total 35 TRs, 45.7% (n=16) did not have any restrictions on usage, while as for 54.3% (n=19) of TRs some level of restriction was required. Twenty (57%) of the TRs were updated within the last five years. All concepts found within RT-TRs were labelled with one of 29 semantic types represented within UMLS. After removal of “stop words”, the total number of all words for all TRs together was 56,219 with in median 25 unique words per TR (range 3 - 50682). The total number of unique words in all TRs was 1048 with in median 19 unique words per vocabulary (range 3 - 406). Lexical density for all concepts within all TRs was zero (0.02 rounded to two decimals). Median lexical density per unique TR was 0.7 (range 0.0 -1.0). There was no dedicated radiation therapy TRs.

Conclusions:

We did not identify any dedicated terminology resource for radiation oncology. Current terminologies are not sufficient to cover the need of modern radiation oncology practice and research. To achieve a sufficient level of interoperability, the creation of a new, standardized, universally accepted terminology resource, dedicated to modern radiation therapy, is mandatory. Clinical Trial: Not applicable


 Citation

Please cite as:

Cihoric N, Badra EV, Stenger-Weisser A, Aebersold DM, Pavic M

Toward Data-Driven Radiation Oncology Using Standardized Terminology as a Starting Point: Cross-sectional Study

JMIR Form Res 2022;6(1):e27550

DOI: 10.2196/27550

PMID: 35044315

PMCID: 8811690

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.