This peer-reviewed publication based on retrospective data, led by Kaiser Permanente Northwest (KPNW), appeared in Digestive Diseases and Sciences. The publication, “Early Colorectal Cancer Detected by Machine Learning Model Using Gender, Age, and Complete Blood Count Data,” validates of one of Medial EarlySign’s algorithms* on a U.S. adult population.
The study confirms the efficacy of Medial EarlySign’s ColonFlagTM machine learning-based solutions in identifying patients with a 10 times greater risk of harboring undiagnosed colorectal cancer (CRC) while at curable stages. In many patients, our algorithm was further able to identify risk for colorectal tumors up to 360 days earlier than its actual diagnosis using convenional practices.
This peer-reviewed publication gives healthcare systems, physicians, CMIOs, Chief Quality Officers, population health managers, and payors valuable insights from a respected U.S.-based HMO’s data study involving one of our models on a U.S. adult population
Readers will come away with a better understanding of how machine learning-based healthcare models can use ordinary, routine EHR data to identify patients who were non-compliant for screenings, but were likely to have a high-burden disease like CRC.
Highlights of the KPNW study include:
Early Colorectal Cancer Detected by Machine Learning Model Using Gender, Age, and Complete Blood Count Data, Mark C. Hornbrook, et al., Dig Dis Sci (2017) 62:2719–2727, DOI: 10.1007/s10620-017-4722-8
*Note In the U.S. Medial EarlySign commercializes LGI Flag, which identifies individuals at high risk of having lower GI disorders. The algorithm analyzed in this study, ColonFlag, bears CE mark and is commercialized for use in the EU, UK, Israel.