Automated thematic analysis of health information technology (HIT) related incident reports
Bibliographic record
Abstract
In this paper, the authors describe a method for exploring the feasibility of using Natural Language Processing (NLP) and Machine Learning (ML) techniques to analyze patient safety incident database reports for themes. We developed a novel thematic analysis strategy to automatically detect keywords and latent themes that describe HIT-related patient safety incidents. The strategy was applied to patient safety reports to test the approach. The efforts by the automated strategy were compared to the efforts by analysts who manually reviewed and identified key words, topics, and themes for the same reports. The computer-based error themes were also compared to the human-determined themes for crosschecking. The manual thematic analysis took about 150 hours to complete on the patient safety reports. The semi-automated approach took only 10% of that time. 95% of the themes extracted from the automated method were aligned with the themes from the manual process. The findings underscore the utility of NLP and ML in identifying thematic patterns embedded in large numbers of unstructured data. The NLP-ML method therefore represents a valuable addition to the tools of detecting and understanding HIT-related errors.
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 | 0.022 | 0.075 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.015 | 0.009 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".