Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Genomic analysis of oesophageal carcinoma (EC) identifies recurrent mutations in histone methyltransferases as a distinctive subset.

Oncogene·2026

Same author

Identification of a Novel <i>GOLGB1-RET</i> Fusion in Papillary Thyroid Cancer With a Durable Response to Selpercatinib.

JCO precision oncology·2026

Same author

Long Road Home: The Continuing Journey of Metastatic Disease.

JCO oncology practice·2026

Same author

Integrated Molecular and Clinical Analysis of Thymic Epithelial Tumors.

JCO precision oncology·2026

Same author

Multi-Omic Landscape of Gastrointestinal Stromal Tumors in a Real-World Patient Cohort of 1,427 Cases.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026

Same author

Cellular neighborhoods govern antitumor T-cell infiltration following anti-CTLA-4 in melanoma with primary resistance to anti-PD-1.

Cancer discovery·2026

Search research articles

Related Experiment Video

Updated: Sep 13, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

GPSai: A Clinically Validated AI Tool for Tissue of Origin Prediction during Routine Tumor Profiling.

Hassan Ghani¹, Anthony Helmstetter¹, Jennifer R Ribeiro¹

¹Caris Life Sciences, Irving, Texas.

Cancer Research Communications

|July 31, 2025

Summary

An artificial intelligence (AI) tool, Genomic Probability Score AI (GPSai™), accurately identifies cancer tissue of origin, aiding in diagnosing cancers of unknown primary (CUP) and improving treatment decisions.

More Related Videos

Digital Spatial Profiling for Characterization of the Microenvironment in Adult-Type Diffusely Infiltrating Glioma

Digital Spatial Profiling for Characterization of the Microenvironment in Adult-Type Diffusely Infiltrating Glioma

Published on: September 13, 2022

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

Related Experiment Videos

Last Updated: Sep 13, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

Digital Spatial Profiling for Characterization of the Microenvironment in Adult-Type Diffusely Infiltrating Glioma

Digital Spatial Profiling for Characterization of the Microenvironment in Adult-Type Diffusely Infiltrating Glioma

Published on: September 13, 2022

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

Area of Science:

Oncology
Bioinformatics
Artificial Intelligence in Medicine

Background:

A subset of cancers present with unclear or incorrect primary histopathologic diagnoses, posing challenges in diagnosis and treatment.
Cancers of Unknown Primary (CUP) represent a significant diagnostic dilemma, impacting patient management and therapeutic strategies.

Purpose of the Study:

To develop and validate an AI tool, Genomic Probability Score AI (GPSai™), for predicting tumor tissue of origin in CUP and identifying potential misdiagnoses.
To assess the clinical impact of integrating GPSai into routine molecular testing for improving diagnostic accuracy and guiding therapy.

Main Methods:

The GPSai model was trained on whole exome and transcriptome data from over 200,000 cases.
Retrospective and prospective validations were performed on over 97,000 cases.
Clinical utility was evaluated through 8 months of live testing and physician surveys.

Main Results:

GPSai demonstrated 95.0% accuracy in non-CUP cases and identified tumor origin in 84.0% of CUP cases.
The tool led to diagnosis changes in 0.88% of profiled cases, with changes supported by orthogonal evidence.
Diagnosis alterations prompted changes in targeted therapy eligibility in 86.1% of affected patients.

Conclusions:

GPSai accurately identifies tumor tissue of origin, aiding in the diagnosis of CUP and ambiguous tumors.
The AI tool has the potential for clinical impact by improving diagnostic accuracy and guiding subsequent therapeutic decisions.
Integration of GPSai into routine molecular testing can enhance diagnostic precision and optimize patient treatment strategies.