prnewswire.com web signal

nference, Cedars-Sinai Build AI Platform on 5M+ Patient Records

TL;DR

  • nference and Cedars-Sinai will pool over a decade of de-identified records from more than 5 million patients into a federated AI research platform.
  • In-scope modalities include clinical notes, labs, radiology and pathology imaging, genomics, waveforms, vitals and consented biospecimens.
  • Stated research uses span drug discovery, clinical trial design and future diagnostics; neither party disclosed contract length or financial terms.

nference has signed a long-term agreement with Cedars-Sinai to build a federated AI research platform drawing on more than a decade of de-identified records from over 5 million patients, the two organizations announced on November 20.

The intended data span is unusually wide: clinical notes, laboratory results, medications, diagnostic reports, radiology and pathology imaging, genomic information, patient-consented biospecimen, electrophysiology waveforms, vitals, and flowsheets, refreshed continuously as routine care progresses. nference provides the federated software architecture, multimodal data harmonization and physician-adjudicated curation; Cedars-Sinai contributes the de-identified clinical records.

"Understanding health and disease requires connecting what is happening across organs, across clinical modalities, and across decades of each patient's medical journey," said Venky Soundararajan, Ph.D., nference's founder and co-CEO. Sumeet Chugh, MD, Cedars-Sinai's vice dean and chief artificial intelligence health research officer, said the collaboration is expected to give clinicians and scientists "new ways to learn from the collective experience of patient care," with stated uses spanning drug discovery, clinical trial design and future diagnostics.

Neither party disclosed contract duration or financial terms. As unite.ai noted, the platform remains under development with capabilities still described as "intended" rather than delivered.