Topic modeling of maintenance logs for linac failure modes and trends identification
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.005 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".