Foundation Models

Tempus is your end-to-end partner to accelerate your AI strategy

Leverage our multimodal data and foundation models, deployed at scale.

One of the largest multimodal datasets in the world

~50 million unique cases across therapeutic areas, many with sequencing, imaging, and clinical histories

State-of-the-art foundation models and AI technology

Scientifically proven, multimodal foundation models and off-the-shelf tools accelerate and de-risk your AI development

Proven expertise developing clinical-grade AI

Bring AI models from initial proof-of-concept to robust, validated, and documented products suitable for the clinic

Regulatory excellence and track record

Multiple FDA authorizations across software (SaMD) and traditional diagnostics; dedicated regulatory team with extensive FDA and international expertise

Extensive deployment network and patient footprint

We operate at scale, reaching ~50% of US oncologists, with global infrastructure in place for broad AI deployment

Our models

State of the Art Foundation Models
We pioneered the Virchow and PRISM models, combining pathology images and clinical notes, setting the benchmark for foundation models in computational pathology.

Multimodal Foundation Model Expansion
We are building a unified foundation model that combines our data across modalities to develop a comprehensive understanding of the complexity of disease, beginning with oncology.

Future Vision for Foundation Models
As our dataset continues to scale, and we incorporate new data modalities, these modalities will be integrated into our foundation models, broadening capabilities and expanding to new disease areas.

Regulatory expertise

Navigate the regulatory landscape with our expertise across software and diagnostics

From AI-powered pathology to companion diagnostics, we provide end-to-end guidance to navigate submission and launch. Tempus has extensive regulatory experience inducing FDA approval for our xT CDx assay and 510(k) clearance for our xR IVD assay.

Article

Headline: Paige Prostate's IVDR approval and FDA authorization as the first AI.

The landmark journey of Paige Prostate: IVDR approval and building on a legacy of regulatory excellence as the first FDA-authorized AI

Software clearances

Secured the first and only FDA de novo clearance for an AI-enabled pathology product, Paige Prostate Detect
Gained multiple 510(k) clearances for AI-enabled algorithms, including ECG-AF and ECG-Low EF
Earned two additional FDA Breakthrough Device Designations for Paige Breast Lymph Node and Paige PanCancer Detect
Holds nine FDA clearances for its Pixel cloud-hosted viewer and applications
Received 510(k) clearance for the FullFocus viewer, compatible with three major whole slide image scanners
Obtained IVDR approval and 12 CE-IVD/UKCA marks covering 18 algorithms.

Traditional diagnostics

Received FDA approval for its xT CDx assay and 510(k) clearance for its xR IVD assay.
Regulatory affairs team of 10+ professionals with extensive FDA experience.

Our scale

Once AI-enabled diagnostics are developed, Tempus enables their deployment at scale

~1M

tests run annually on our labs

~65%

of academic medical systems in the US are connected to Tempus

~5K+

connected healthcare institutions

~50%

of oncologists in the U.S

Partnership model

We offer flexible frameworks to align our AI capabilities with your needs

Access our technology off-the-shelf to enable your internal AI development

License our pathology and multimodal foundation models to accelerate your development
Access off-the-shelf AI tools, such as Paige Predict for biomarker prediction across 505 genes

Partner with us, from POC through commercialization on a customized project tailored to your unique needs

Work together to build an new AI application or novel biomarker for your therapy
Validate, deploy, and navigate complex regulatory submissions with our expertise
Scale and drive clinical adoption through our extensive deployment network

Featured

Hear from our experts

Article

Q&A: From proof of concept to clinical deployment: How foundation models are accelerating drug development

Tempus leaders discuss the practical application of multimodal foundation models, from de-risking programs and uncovering novel biomarkers to deploying AI-driven insights at the point of care.

Webinar

Three diverse people in circular headshots on a dark background, with a play button.

Unlocking foundation models: Our experience from proof of concept to deployment at scale

An executive discussion on leveraging multi-modal foundation models to accelerate your drug development journey

Article

From image to insight: How Tempus is leveraging AI to advance biomarker screening at scale

By leveraging Paige Predict to screen for genomic and phenotypic biomarkers, clinicians and researchers have rapid access to valuable information to prioritize testing and pre-screen patients at scale.

Article

Solving cancer’s tissue scarcity problem: How Tempus uses AI models in pathology to transform tissue analysis

Tempus AI research demonstrates how AI can analyze digitized pathology images to predict tissue sample viability for genomic testing, a task that pathologists struggle to perform consistently.

News

Press Release

A light gray and white blurred background with soft gradients.

Tempus Announces the Acquisition of Paige

Paige’s strong foundation in pathology and AI is rooted in its proprietary dataset of almost 7 million digitized pathology slides that are clinically annotated.

Press Release

Tempus Announces the Launch of Paige Predict

Research

Abstract

H&E-Based Deep Learning Model Predicts Immune Phenotypes in NSCLC

A deep learning model accurately identifies tumor-infiltrating lymphocytes (TILs) in non-small cell lung cancer from H&E slides, matching pathologist performance in distinguishing inflamed from non-inflamed immune phenotypes.

Abstract

Hands in a lab coat interacting with a glowing holographic display of biological cells.

Deep Learning Identifies FGFR Alterations from H&E Whole Slide Images in Bladder Cancer

A deep learning model trained on H&E slides predicts FGFR alterations in bladder cancer, potentially streamlining patient selection for targeted therapy NGS screening.

Abstract

Scientist in lab coat and black gloves working with advanced laboratory equipment.

Imaging-based histological features are predictive of MET alterations in Non-Small Cell Lung Cancer

MET is a proto-oncogene whose somatic activation in non-small cell lung cancer leads to increased cell growth and tumor progression

Abstract

Automated multi-channel pipette accurately dispenses red liquid into a laboratory plate.

Medical Image Computing and Computer Assisted Intervention – MICCAI 2021

Deep Orthogonal Fusion: Multimodal Prognostic Biomarker Discovery Integrating Radiology, Pathology, Genomic, and Clinical Data

This is AI-enabled precision medicine

This is the future of healthcare.