# Tempus multimodal models

Source: https://onco.cc/technologies/tempus-multimodal/  
OnCo record `tempus-multimodal` (Technology). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Models trained on Tempus's paired genomic, pathology, imaging and outcome data to predict response and prognosis.

## Summary

Tempus trains supervised and self-supervised multimodal models on its proprietary clinico-genomic corpus, which pairs sequencing, pathology slides, imaging and outcomes for the same patients. The company reports models that predict microsatellite instability (MSI), homologous recombination deficiency (HRD) and treatment response from routine H&E slides, ECG-based algorithms, and the Tempus One assistant for clinicians. The intended users are oncologists and pharma partners using Tempus testing and its data platform. Validation is largely internal or in company publications, and the models are proprietary, so external groups cannot benchmark them, which is the main reservation about the evidence. For a newcomer: Tempus uses its large private database to build models that guess genomic features and treatment response from slides and records.

## Fields

- Kind: Technology
- Status: emerging
- Last checked: 2026-09-08
- Tags: foundation-model; multimodal
- Principle: Tempus trains supervised and self-supervised multimodal models on a proprietary clinico-genomic corpus.
- Since: 2023
- Strengths: Paired real-world data
- Limitations: Proprietary; limited external validation

## Sources

- Tempus AI: https://www.tempus.com

## Connected records

- fronts: [AI & Computation](https://onco.cc/fronts/ai-computation/)
- companies: [Tempus AI](https://onco.cc/companies/tempus/)
- roadmaps: [AI in oncology roadmap: pattern readers → foundation models → agents in the workflow](https://onco.cc/roadmaps/ai-oncology-roadmap/), [AI in the oncology clinic: from narrow cleared tools to multimodal decision support](https://onco.cc/roadmaps/ai-oncology-clinic/)

---
JSON: https://onco.cc/api/v1/entities/tempus-multimodal.json