Development of a genomic-clinical classifier for predicting progression after radical cystectomy in patients with muscle invasive bladder cancer.
Bibliographic record
Abstract
4542 Background: The mainstay of muscle-invasive bladder cancer treatment is surgical resection with/without multi-agent chemotherapy. Management decisions are based on a small number of clinical and pathologic parameters with poor prognostic and predictive power. There is an urgent need for enhanced biomarkers to guide therapy of this lethal disease. Here we have developed a genomic signature of bladder cancer progression using whole transcriptome profiling technology. Methods: 251 FFPE bladder cancer specimens were obtained from patients undergoing radical cystectomy at the University of Southern California (1998-2004). All patients had pT2-T4a,N0 urothelial carcinoma in the absence of pre-operative chemotherapy. Median follow-up was 5 years. RNA expression levels were measured with 1.4 million feature oligonucleotide microarrays. Patients were divided into a training set (2/3 of cohort) to develop a genomic classifier for risk of progression (defined as any type of bladder cancer recurrence), and a validation set (1/3 of cohort). In parallel, multivariable analysis was used to develop a clinical classifier using typical clinical and pathologic variables. Finally, a genomic-clinical classifier was built combining the genomic classifier with clinical variables using logistic regression. The receiver-operator characteristic (ROC) area under the curve (AUC) metric was used to evaluate each classifier in the validation set. Results: The genomic classifier consisted of 89 features corresponding to 80 genes that were combined in a k-nearest neighbor model (KNN89). KNN89 showed an AUC of 0.77 in ROC analysis on the validation set. The best clinical classifier showed an AUC of 0.72. The genomic-clinical classifier demonstrated an AUC of 0.81. Multivariable analysis incorporating all clinical parameters and KNN89 further revealed that KNN89 was the only significant predictor of bladder cancer progression (p=0.0077). Conclusions: We have developed a combined genomic-clinical classifier that shows improved performance over clinical models alone for prediction of progression after radical cystectomy. External validation of this classifier is ongoing.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 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".