Abstract A029: Validation of a Deep Learning Serial Computed Tomography Response Biomarker for Predicting Overall Survival in Metastatic Kidney Cancer Treated with Immune Checkpoint Inhibitors
Bibliographic record
Abstract
Abstract Background: Reliable prognostic biomarkers are needed to guide treatment decisions for patients with metastatic kidney cancer receiving immune checkpoint inhibitors (ICIs). Radiomics biomarkers leveraging quantitative imaging features from longitudinal CT scans have demonstrated prognostic utility across multiple tumor types, including advanced non-small cell lung cancer (NSCLC). Evaluating such biomarkers in additional tumor types may further enhance personalized treatment approaches. Objective: Evaluate the performance of a deep learning biomarker for predicting overall survival (OS) in metastatic kidney cancer patients receiving ICIs. Methods: Serial computed tomography response score (Serial CTRS) is a fully automated deep learning radiomics biomarker that predicts OS by analyzing paired baseline and early-treatment thoracic CT scans, typically capturing thoracic and upper abdominal disease. Serial CTRS was previously validated in advanced NSCLC patients receiving programmed death-ligand 1 (PD-L1) ICIs, demonstrating superior OS prediction compared to conventional RECIST and tumor volume metrics in retrospective real-world and clinical trial datasets. This study retrospectively analyzed paired baseline (within 90 days prior to ICI initiation; median: 21 days prior) and follow-up (28–120 days post-ICI initiation; median: 80 days) thoracic CT scans from 117 metastatic kidney cancer patients treated with ICIs within Providence Health System. Of these, 87 patients (median age: 66 years; IQR: 59–72) with available paired scans were included. Predictive performance of Serial CTRS for OS was assessed using Cox proportional hazards models, concordance index (C-index), and area under the receiver operating characteristic curve (ROC-AUC) for OS at 6, 12, and 24 months. Results: Serial CTRS demonstrated significant association with OS, yielding robust risk stratification (C-index: 0.73; 95% CI: 0.65–0.80). ROC-AUC values showed strong predictive accuracy for OS at 6 months (0.87; 95% CI: 0.79–0.94), 12 months (0.78; 95% CI: 0.66–0.90), and 24 months (0.73; 95% CI: 0.60–0.87). Kaplan-Meier analysis using predetermined thresholds from prior NSCLC datasets revealed clear survival stratification among Serial CTRS groups: low- versus high-survival probability (HR=5.01; 95% CI: 2.15–11.68), low- versus intermediate-survival probability (HR=3.25; 95% CI: 1.58–6.69), and intermediate- versus high-survival probability (HR=1.84; 95% CI: 0.82–4.15). Conclusion: Serial CTRS demonstrated robust and significant predictive utility for OS in metastatic kidney cancer patients receiving ICIs, consistent with previous validation in advanced NSCLC. Its fully automated methodology, which requires no manual lesion annotations, may facilitate scalable and objective clinical implementation enhancing prognostication and optimizing treatment stratification in oncology clinical trials and clinical practice. Further prospective validation exploring integration of Serial CTRS into clinical trial designs is warranted. Citation Format: Chiharu Sako, Taly G. Schmidt, Beatriz G. Lourenco, Karishma Sewaramani, Ross McCall, Ryan Beasley, Arpan A. Patel, Dwight H. Owen, Arya Amini, Ronan J. Kelly, Ray D. Page, Jean-Paul Beregi, Stephane Sanchez, Olivier Gevaert, George R. Simon, Ravi B. Parikh, Petr Jordan, Brendan D. Curti. Validation of a Deep Learning Serial Computed Tomography Response Biomarker for Predicting Overall Survival in Metastatic Kidney Cancer Treated with Immune Checkpoint Inhibitors [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Artificial Intelligence and Machine Learning; 2025 Jul 10-12; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(13_Suppl):Abstract nr A029.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| 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".