Detection of early-stage urothelial cancers using methylation patterns in urine cell-free DNA.
Bibliographic record
Abstract
687 Background: Urine cell-free DNA (ucfDNA) has the potential to improve detection and monitoring of early-stage urothelial carcinoma (UC). We previously demonstrated the utility of ucfDNA methylation patterns to detect non-muscle invasive bladder cancer (NMIBC) in patients with suspicious bladder lesions (by cystoscopy or imaging). Based on those results, we trained a biopsy-free urine classifier for cancer detection. Here, we evaluate the performance of the urine classifier in an independent test set of patients with early-stage NMIBC or upper tract UC (UTUC). Methods: The urine classifier was trained using GRAIL’s biobank of plasma and cancer tissue, as well as prospectively collected urine from cancer and non-cancer participants (urine samples, n = 468). The locked classifier was evaluated at 95% and 98% target specificities on an independent test set of biobanked urine from patients with a new diagnosis of NMIBC (n = 49, 24 low grade and 25 high grade) and UTUC (n = 19, 9 low grade and 10 high grade), as well as age- and gender-matched non-cancer controls (n = 66). Results: The observed specificities in the test set at target specificities of 95% and 98% were 93.9% (62/66, 95% CI 85.2-98.3%) and 97.0% (64/66, 95% CI 89.5-99.6%), respectively. Observed sensitivity was the same at both target specificities. Of the 68 patients with a new diagnosis of either NMIBC or UTUC, 57 were classified as cancer, while 11 were classified as non-cancer. The urine classifier had a sensitivity of 100% for high grade NMIBC (25/25; 95% CI 86.3-100%) and 58.3% for low grade NMIBC (14/24; 95% CI 36.6-77.9%). For patients with UTUC, the urine classifier had a sensitivity of 100% for high grade UTUC (10/10; 95% CI 69.2-100%) and 88.9% for low grade UTUC (8/9; 95% CI 51.8-99.7%). Conclusions: A biopsy-free urine classifier based on ucfDNA methylation patterns is able to identify early-stage NMIBC and UTUC with high sensitivity at high specificity, particularly for patients with high grade disease. The classifier performance was validated in urine with an independent test set and did not require matched blood or tissue, highlighting the potential for a non-invasive and cost-effective method for UC screening. Current efforts are focused on evaluating urine classifier performance in prospective cohorts of UC patients undergoing both screening and recurrence monitoring.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".