Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Jan;23(1):e13477.
doi: 10.1002/acm2.13477. Epub 2021 Nov 29.

Topic modeling of maintenance logs for linac failure modes and trends identification

Hongguang Yun  1 , Marco Carlone  2   3 , Zheng Liu  1
Affiliations

Topic modeling of maintenance logs for linac failure modes and trends identification

Hongguang Yun et al. J Appl Clin Med Phys. 2022 Jan.

Abstract

Purpose: Medical linear accelerators (linacs) can fail in a multitude of different manners due to complex structures. An unclear identification of failure modes occurring constantly is a major obstacle to maintenance arrangements, thereby may increasing downtime. This study aims to use natural language processing techniques to deal with the unformatted maintenance logs to identify the linac failure modes and trends over time.

Materials and methods: The data used in our study are unformatted narrative maintenance logs recording linac conditions and repair actions. The latent Dirichlet allocation-based topic modeling method was used to identify topics and keywords regarding the failure modes. The temporal analysis method was applied to examine the variation of failure modes over 20 years.

Results: Based on the output of the topic modeling, 28 topics and keywords with frequency ranking were generated automatically. The latent failure modes in topics were identified and classified into six main subsystems of linacs. Furthermore, by using the temporal analysis method, the trends of all failure modes over 20 years were illustrated. Half of the topics demonstrated variations with three different patterns, namely periodic, increasing, and decreasing.

Conclusions: The results of our study validated the effectiveness of using the topic modeling method to automatically analyze narrative maintenance logs. With domain knowledge, failure modes of linacs can be identified and categorized quantitatively.

Keywords: failure modes; latent Dirichlet allocation; linac; natural language processing; topic modeling.

PubMed Disclaimer

Conflict of interest statement

The authors declare that there is no conflict of interest that could be perceived as prejudicing the impartiality of the research reported

Figures

FIGURE 1
FIGURE 1
Graphical representation of latent Dirichlet allocation model
FIGURE 2
FIGURE 2
Metrics used to select the optimal number of topic
FIGURE 3
FIGURE 3
Top‐ranked words within topic 3 and corresponding failure mode
FIGURE 4
FIGURE 4
Trends of topics with periodic pattern over years
FIGURE 5
FIGURE 5
Trends of topics with increasing trend over years
FIGURE 6
FIGURE 6
Trends of topics with decreasing trend over years
See this image and copyright information in PMC

References

    1. Wroe LM, Ige TA, Asogwa OC, et al. Comparative analysis of radiotherapy linear accelerator downtime and failure modes in the UK, Nigeria and Botswana. Clin Oncol (R Coll Radiol). 2020;32(4):e111‐e118. - PubMed
    1. Sheehy S, Egerton A‐J, Steinberg A, Wroe L. How Robust are Existing Medical LINACs in Challenging Environments? A Study of Down Time and Failure Causes. JACoW Publishing; 2019.
    1. Kuhn KD. Using structural topic modeling to identify latent topics and trends in aviation incident reports. Transp Res C Emerg Technol. 2018;87:105‐122.
    1. Roque C, Lourenço Cardoso J, Connell T, Schermers G, Weber R. Topic analysis of road safety inspections using latent Dirichlet allocation: a case study of roadside safety in Irish main roads. Accid Anal Prev. 2019;131:336‐349. - PubMed
    1. Shah AM, Yan X, Qayyum A, Naqvi RA, Shah SJ. Mining topic and sentiment dynamics in physician rating websites during the early wave of the COVID‐19 pandemic: machine learning approach. Int J Med Inform. 2021;149(104434):104434. - PMC - PubMed