Study
PLCO
(Learn more about this study)
Project ID
PLCOI-1637
Initial CDAS Request Approval
Aug 15, 2024
Title
Identification of histologic signatures associated with adjuvant chemotherapy benefit in non-small cell lung cancer using an artificial intelligence-based assay
Summary
Valar Labs is a start-up company, founded by a team of Stanford researchers at the intersection of artificial intelligence (AI) and medicine. The company aims to construct clinically relevant biomarker signatures of morphologic features extracted from histologic slides using AI that can be useful for treatment decisions. Rather than taking a primarily deep learning or "black box" approach employed by other AI groups that does not allow for correlation of outcomes to specific, identifiable histologic features, the Valar Labs Computation Histology AI (CHAI) platform involves AI-powered segmentation of cell nuclei on a diagnostic H&E slide and then AI-powered extraction of more than 1000 quantitative features describing qualities of the identified tumor and tumor microenvironment (such as geometric descriptors of tumor cell nucleus size/shape and quantification of spatial relationships between immune, stromal, and tumor cells) that can then be associated with outcomes of interest, with machine learning used to train a signature consisting of composite, identifiable features capable of serving as a biomarker. Our initial work has focused on identifying such biomarkers in pancreatic cancer (PMID: 37044094) and bladder cancer (manuscript under review at Journal of Urology). Work in bladder cancer has been the basis for a CLIA-approved test to predict benefit from treatment from BCG in non-muscle invasive bladder cancer.
We aim to utilize the Valar Labs CHAI platform to identify a histologic signature associated with survival benefit from use of cisplatin-based chemotherapy in adjuvant NSCLC. To do so, we propose to use PLCO data study to construct and validate a histologic signature that stratifies survival outcomes among patients receiving cisplatin-based chemotherapy. Use of PLCO data would be combined with data from other sources to develop and validate an AI-histologic biomarker associated with chemotherapy benefit that can be implemented in clinical practice for the benefit of patients.
Aims
1) The primary objective of this study is to test the hypothesis that a pre-defined continuous AI-based predictive histologic biomarker is significantly associated with treatment benefit from adjuvant cisplatin-based chemotherapy in NSCLC.
2) The secondary objective of this study is to test the hypothesis that a pre-defined continuous AI-based prognostic histologic biomarker is significantly associated with prognosis among patients with resected NSCLC.
Collaborators
Andrew Nixon, PhD, MBA (Professor of Medicine, Duke Cancer Institute)
Richard M Goldberg, MD (Professor Emeritus, West Virginia University Cancer Institute)
Qian Shi, PhD (Professor of Oncology and Biostatistics, Mayo Clinic)
Anirudh Joshi, MS (CEO, Valar Labs)
Waleed M. Abuzeid, MD (Medical Director, Valar Labs)
