Applications
- Classifies clear cell renal cell carcinoma (ccRCC) patients to predict treatment response and prognosis.
- Personalized therapy selection, including immunotherapy and mTOR inhibitors.
Advantages/Benefits
- Faster and cheaper biomarker identification process than traditional methods
- High predictive accuracy for treatment outcomes and prognosis
- Improved patient care through personal treatment
- Broader validation and clinical use
Background
Renal cell carcinoma (RCC) is the most common form of kidney cancer, with the clear cell subtype (ccRCC) accounting for 75% of cases. Despite advancements in therapy, effective biomarkers for patient stratification remain limited. This invention addresses this gap by using artificial intelligence (AI) to develop Cellular Morphometric Biomarkers (CMBs) that predict prognosis and treatment responses, especially to mTOR inhibitors and immunotherapies.
Technology Overview
Researchers at Lawrence Berkeley National Laboratory and UC-Davis Health have developed an AI-based method to improve treatment planning for clear cell renal cell carcinoma (ccRCC). By analyzing tissue samples using 73 key features, called Cellular Morphometric Biomarkers (CMBs), the technology generates a risk score (CMBRS) to classify patients as low or high risk. Low-risk patients are significantly more likely to benefit from mTOR kinase inhibitors, including Everolimus, with data showing a 51% longer treatment duration and a 23% higher survival rate compared to high-risk patients. Tested on over 700 patient samples, the method demonstrated high accuracy, offering a fast, affordable, and reliable way to personalize treatment and improve patient survival.
Development Stage
Proof of Concept, validated in selected public and hospital cohorts
Principal Investigator(s)
- Jian-Hua Mao
- Hang Chang
- Kenneth Iczkowski
- Shuchi Gulati
Status
Patent pending
Opportunities
Available for licensing or collaborative research