🛰️ Daily AI Frontier
‹ back to 2026-08-26

A Multimodal Foundation Model for Longitudinal Patient Representation and Scalable Insight Generation in Oncology

Research Medical/Healthcare AI

Ranking

Overall 80
Content 100
Popularity 34

Observed public metrics from 1 member.

Representative image for A Multimodal Foundation Model for Longitudinal Patient Representation and Scalable Insight Generation in Oncology

Merged summary

TL;DR - oFM is a multimodal foundation model trained on longitudinal records from more than one million oncology patients, integrating clinical history, genomics, transcriptomics, and pathology images. Its frozen patient embeddings substantially improved prognostic and treatment-benefit predictions over expert-curated baseline features.

  • The model encodes daily clinical and molecular episodes, combines them with H&E pathology images, and integrates observations over time into patient-state embeddings.
  • Training used patient-level partitions from a real-world cohort of 1.67 million cancer patients.
  • oFM improved overall-survival AUC from 0.563 to 0.774 and also improved treatment-response and progression-free-survival prediction.
  • Across 11 comparative-treatment cohorts, its embeddings achieved three-fold higher pooled, scale-normalized treatment-benefit AUTOC and improved benefit ranking in 9 cohorts.

Sources (1)

A Multimodal Foundation Model for Longitudinal Patient Representation and Scalable Insight Generation in Oncology

arXiv cs.LG Eugene Vorontsov, Yi Kan Wang, Alican Bozkurt, Adam Casson, Ludmila Tydlitatova, Michal Zelechowski, Ezra E. W. Cohen, Jyoti D. Patel, Max Banaszak, Caitlin McWilliams, Shane Colley, Kate Sasser, Ryan Fukushima, Eric Lefkofsky, Razik Yousfi, Siqi Liu 2026-08-25 arXiv:2608.24688
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-09-02 14:14:15.611011 UTC

TL;DR - oFM is a multimodal foundation model trained on longitudinal records from more than one million oncology patients, integrating clinical history, genomics, transcriptomics, and pathology images. Its frozen patient embeddings substantially improved prognostic and treatment-benefit predictions over expert-curated baseline features.

  • The model encodes daily clinical and molecular episodes, combines them with H&E pathology images, and integrates observations over time into patient-state embeddings.
  • Training used patient-level partitions from a real-world cohort of 1.67 million cancer patients.
  • oFM improved overall-survival AUC from 0.563 to 0.774 and also improved treatment-response and progression-free-survival prediction.
  • Across 11 comparative-treatment cohorts, its embeddings achieved three-fold higher pooled, scale-normalized treatment-benefit AUTOC and improved benefit ranking in 9 cohorts.
item →