ASCO 2024

Picture Health at ASCO 2024

Picture Health Announces Three Research Abstracts at the 2024 ASCO Annual Meeting

Accurate predictive biomarkers are necessary to optimize treatment selection and clinical trial recruitment. Picture Health’s proprietary AI platform extracts biological tumor features from routinely collected radiology or pathology images to quickly build reliable imaging biomarkers that accurately characterize patient subpopulations. We are presenting three research abstracts demonstrating use of such biomarkers at the ASCO annual meeting, May 31-June 4, in Chicago, IL. 

Interested in learning more? Schedule a meeting with our team at ASCO.

Radiomic signature predictive of progression

An interpretable AI-derived radiology signature to identify patients at risk of progression on the PACIFIC regimen for unresectable non-small cell lung cancer. Abstract 8079, Poster Bd 341June 3, 1:30PM CDT- Poster Session- Hall A

Our novel predictive AI signature identifies stage III NSCLC patients who will fail to benefit from chemo-radio-immunotherapy prior to treatment initiation, and outperforms current IO biomarker, PD-L1. This signature can help identify a subset of unresectable NSCLC patients who may benefit from alternatives to standard of care treatments.

Independent validation of ICI radiomic signature

CheckpointPx: a predictive radiology AI model of immune checkpoint inhibitor (ICI) benefit in NSCLC.
Abstract 8632, Poster Bd 496–  June 3, 1:30PM CDT- Poster Session – Hall A

We are excited to share an independent validation of CheckpointPx, our proprietary AI signature that predicts response to ICI treatment regimensCheckpoint Px identifies NSCLC patients who would benefit from ICI over chemotherapy. The signature’s predictive association with PFS among ICI patients can help address critical gaps in the NSCLC predictive biomarker landscape.

Independent validation of ICI-pneumonitis risk predictor

AI-based radiomics model for predicting immune checkpoint inhibitor- related pneumonitis (CIP) in advanced NSCLC patients: An external validation study.  Abstract Abstract 12136, Poster Bd 265  June 3, 2024; 1:30PM CDT – Poster Session – Hall A

Our AI-powered pneumonitis risk prediction models identified patients at risk of checkpoint inhibitor – related pneumonitis (CIP) prior to treatment in an external independent validation. Our model could improve the identification and management of CIP in NSCLC patients receiving immunotherapy treatments, driving safer and more efficient patient selection for clinical trials.  


© 2023 picturehealth. All Rights Reserved. | Catalyzed by digital catalyst logo