Cancer stage documentation and accuracy: Single-center retrospective study on oropharyngeal cancers
Bibliographic record
Abstract
• Oropharyngeal squamous cell carcinoma (OPSCC) is associated with HPV disease. • Cancer staging determines prognosis and surgical vs non-invasive treatment in OPSCC. • Accurate staging in electronic health records is poor with low documentation rates. • Improved staging accuracy needed to improve treatment outcomes. • Artificial intelligence can be used to improve staging documentation/accuracy. The objectives were to (1) conduct an electronic health records (EHRs) review of oropharyngeal cancer patients, (2) determine EHR stage documentation rates, and (3) compare staging accuracy within EHRs and by Cancer Center Coders. Retrospective analysis of oropharyngeal cancer patients seen between January 1, 2010, and August 1, 2020, at a tertiary care center. Two experts reviewed EHRs to determine tumour (T), nodal (N), metastatic (M) and overall cancer stages. EHR staging documentation was abstracted and accuracy was reported in comparison to expert staging. Cancer Center Coders independently captured cancer staging, and accuracy was reported in comparison to expert staging. 803 patients were included. EHR stage documentation rates were 80 %, 78 %, 16 %, and 16 % for T, N, M, and overall stage, respectively. Average annual concordance (SD) between expert review and Cancer Center Coders were 65.6 %(5.0), 67.0 %(5.4), 90.7 %(4.9), 65.8 %(11.9) for T, N, M and overall stage, respectively. Concordance (SD) between expert review and EHR stage were 65.6%(8.6), 58.5 %(7.8), 9.3 %(3.8) and 13.6 %(7.5) for T, N, M and overall stage, respectively. In a sub-cohort of patients with only chart-documented staging, concordance (SD) rates were 80.9 %(5.4), 74.1 %(5.6), 58.0 %(16.3) and 78.2 %(15.0) for T, N, M and overall cancer stages. EHR stage documentation rates were good for T and N stages, however poor for M and overall cancer stages. Staging accuracy was moderate-to-good when comparing staging from expert reviews to staging by Cancer Center Coders and clinicians. Quality improvement interventions may improve accuracy and frequency of HNC staging, thus improving patient outcomes.
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 | 0.012 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".