Using CT scans and patient tests to predict who will benefit from PD‑1 immunotherapy
Prospective validation of a radiomics-based multi-modal predictive model for metastatic non-small cell lung cancer patients treated with PD-1 immunotherapy
['FUNDING_SBIR_2'] · ONC.AI, INC. · NIH-11192898
A computer tool combines CT scan features, blood and tumor markers, and clinical data to predict which people with advanced lung or bladder cancer are likely to benefit from PD‑1 immunotherapy.
Quick facts
| Phase | ['FUNDING_SBIR_2'] |
|---|---|
| Study type | Nih_funding |
| Sex | All |
| Sponsor | ONC.AI, INC. (nih funded) |
| Locations | 1 site (SAN CARLOS, UNITED STATES) |
| Trial ID | NIH-11192898 on ClinicalTrials.gov |
What this research studies
This project uses advanced image analysis (radiomics) on routine CT scans together with blood and tumor protein/genomic data and clinical information to build a prediction tool. Machine learning and computer vision methods link imaging features from all tumors in the body with proteomic and genomic markers. The team plans a prospective validation to see how well the multi‑modal biomarker predicts real patient responses to PD‑1/PD‑L1 immunotherapy. The approach aims to avoid limits of single biopsies by using whole‑tumor imaging plus routine labs.
Who could benefit from this research
Good fit: People with advanced (metastatic) non‑small cell lung cancer or bladder cancer who are being considered for or are receiving PD‑1/PD‑L1 immunotherapy are the most likely candidates.
Not a fit: People without lung or bladder cancer, those not receiving PD‑1/PD‑L1 therapy, or patients with very early‑stage disease are unlikely to benefit from this specific tool.
Why it matters
Potential benefit: If successful, the tool could help identify people most likely to benefit from expensive and potentially toxic PD‑1 immunotherapy, reducing unnecessary treatment and side effects.
How similar studies have performed: Other biomarker methods like PD‑L1 staining, tumor mutational burden, and some radiomics approaches have shown promise but have not yet produced a widely reliable clinical predictor, so this multi‑modal approach is relatively novel.
Where this research is happening
SAN CARLOS, UNITED STATES
- ONC.AI, INC. — SAN CARLOS, UNITED STATES (ACTIVE)
Researchers
- Principal investigator: JORDAN, PETR — ONC.AI, INC.
- Study coordinator: JORDAN, PETR
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Conditions: Bladder Cancer