Classification of malignant pediatric renal tumors by gene expression
Bibliographic record
Abstract
BACKGROUND: The most common malignant renal tumors of childhood are Wilms tumor (WT), clear cell sarcoma of the kidney (CCSK), cellular mesoblastic nephroma (CMN), and rhabdoid tumor of the kidney (RTK). Because these tumors present significant diagnostic difficulties, the goal was to define diagnostically useful signatures based on gene expression. PROCEDURES: Gene expression analysis using oligonucleotide arrays was performed on a training set of 47 tumors (10 CCSKs, 9 CMNs, 8 RTKs, and 20 WTs). Classifiers were developed for each tumor type using variations of compound covariate class predictor. The classifiers were applied to an independent test set of 72 tumors (3 CMN, 7 CCSK, 4 RTK, and 58 WT). Central review diagnosis was utilized as the gold standard. Correlation with the institutional diagnosis and qualitative estimation of confidence levels at the time of central review were noted. RESULTS: Within the training set, classifiers resulted in no errors when >10 genes were utilized. Top genes in each classifier were verified using quantitative reverse transcription-polymerase chain reaction (RT-PCR). Applying the classifiers to the test set, 71 of 72 tumors were correctly classified with a confidence level of >99%. The exception was incorrectly classified by the gold standard. In comparison, by histopathology 31% of the non-WT were not accurately classified by the local institution, and 29% were classified with <95% confidence on central review. CONCLUSIONS: Classifiers based on gene expression provide diagnostic confidence and accuracy greater than that of pathologic analysis alone. Tumors that show ambiguous gene expression profiles are those that are also pathologically and molecularly ambiguous and merit further analysis.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 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) | 0.000 | 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 teacher head, 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".