On August 4, 2026 Tempus AI, Inc. (NASDAQ: TEM), a technology company leading the adoption of AI to advance precision medicine and patient care, reported study results demonstrating that PRISM2, a multimodal slide-level pathology foundation model developed in collaboration with researchers from Microsoft, can perform clinically important diagnostic tasks using simple prompts and can be leveraged for a variety of downstream applications. The results were published in Nature Medicine.
Schedule your 30 min Free 1stOncology Demo!
Discover why more than 1,500 members use 1stOncology™ to excel in:
Early/Late Stage Pipeline Development - Target Scouting - Clinical Biomarkers - Indication Selection & Expansion - BD&L Contacts - Conference Reports - Combinatorial Drug Settings - Companion Diagnostics - Drug Repositioning - First-in-class Analysis - Competitive Analysis - Deals & Licensing
Schedule Your 30 min Free Demo!
PRISM2 outperformed or matched existing slide-level foundation models across a comprehensive set of diagnostic, biomarker and patient outcome prediction tasks. Additionally, when further tuned to specifically predict long-term outcomes, PRISM2 outperformed standalone models, including achieving high performance predicting colorectal cancer recurrence-free survival.
"PRISM2 represents a true leap forward both in terms of scale and multi-modal AI capabilities," said Razik Yousfi, Senior Vice President and General Manager of AI Products at Tempus. "Our Pathology Foundation Models allow us to have a detailed understanding of tissue, unlocking clinical-grade precision and novel research applications capable of predicting patient outcomes and biomarker status. PRISM2 builds on this by aligning whole-slide pathology images with the language of clinical diagnosis through clinical dialogue training. It can seamlessly handle complex diagnostic and prognostic research tasks without requiring specialized fine-tuning, offering a powerful tool to advance precision oncology."
As part of Tempus’ proprietary Pathology Foundation Models, PRISM2 turns routine hematoxylin and eosin (H&E) slides into deep biological insights. By combining large vision models built from pathology images with large language models, it unlocks diagnostic-grade precision in research involving cancer detection, biomarker identification and prognosis prediction.
PRISM2 was trained on a diverse set of 2.3 million whole-slide images and 14 million diagnostic question−answer pairs derived from nearly 700,000 pathology reports, making it the largest multimodal slide-level pathology datasets to date.
To support ongoing research, open science, and other non-commercial and non-clinical use cases, the full PRISM2 model weights are publicly available through Hugging Face at View Source and View Source-survival.
(Press release, Tempus, AUG 4, 2026, View Source [SID1234669677])