An artificial intelligence framework integrating longitudinal electronic health records with real-world data enables continuous pan-cancer prognostication

Publikation: Beitrag in FachzeitschriftForschungsartikelBeigetragenBegutachtung

Beitragende

  • Olivier Morin - , University of California at San Francisco (Autor:in)
  • Martin Vallières - , University of California at San Francisco (Autor:in)
  • Steve Braunstein - , University of California at San Francisco (Autor:in)
  • Jorge Barrios Ginart - , University of California at San Francisco (Autor:in)
  • Taman Upadhaya - , University of California at San Francisco (Autor:in)
  • Henry C Woodruff - , Maastricht University (Autor:in)
  • Alex Zwanenburg - , Universitätsklinikum Carl Gustav Carus Dresden (Autor:in)
  • Avishek Chatterjee - , McGill University (Autor:in)
  • Javier E Villanueva-Meyer - , University of California at San Francisco (Autor:in)
  • Gilmer Valdes - , University of California at San Francisco (Autor:in)
  • William Chen - , University of California at San Francisco (Autor:in)
  • Julian C Hong - , University of California at San Francisco (Autor:in)
  • Sue S Yom - , University of California at San Francisco (Autor:in)
  • Timothy D Solberg - , University of California at San Francisco (Autor:in)
  • Steffen Löck - , OncoRay - Nationales Zentrum für Strahlenforschung in der Onkologie, Universitätsklinikum Carl Gustav Carus Dresden (Autor:in)
  • Jan Seuntjens - , McGill University (Autor:in)
  • Catherine Park - , University of California at San Francisco (Autor:in)
  • Philippe Lambin - , Maastricht University (Autor:in)

Abstract

Despite widespread adoption of electronic health records (EHRs), most hospitals are not ready to implement data science research in the clinical pipelines. Here, we develop MEDomics, a continuously learning infrastructure through which multimodal health data are systematically organized and data quality is assessed with the goal of applying artificial intelligence for individual prognosis. Using this framework, currently composed of thousands of individuals with cancer and millions of data points over a decade of data recording, we demonstrate prognostic utility of this framework in oncology. As proof of concept, we report an analysis using this infrastructure, which identified the Framingham risk score to be robustly associated with mortality among individuals with early-stage and advanced-stage cancer, a potentially actionable finding from a real-world cohort of individuals with cancer. Finally, we show how natural language processing (NLP) of medical notes could be used to continuously update estimates of prognosis as a given individual's disease course unfolds.

Details

OriginalspracheEnglisch
Seiten (von - bis)709-722
Seitenumfang14
FachzeitschriftNature cancer
Jahrgang2
Ausgabenummer7
PublikationsstatusVeröffentlicht - Juli 2021
Peer-Review-StatusJa

Externe IDs

Scopus 85111270103
ORCID /0000-0002-7017-3738/work/142253923

Schlagworte

Ziele für nachhaltige Entwicklung

ASJC Scopus Sachgebiete