Machine learning extraction of clinical variable values for subjects from clinical record data

US11915807B1 · kind B1 · utility

Assignee

• Flatiron Health, Inc. · US

Inventors

• Jeremy Canfield · Bowling Green, US
• Nisha Singh · Felton, GB
• Marc Knight · Pembroke Pines, US
• Kimberly Wiederkehr · Brooklyn, US
• Sarina Dass · New York, US
• John Ritten · Brooklyn, US
• Ashley Allen · Union, US
• Andrea Ratzlaff · Virginia Beach, US
• Stacie Sienicki · Goshen, US
• Katherine Anne Harrison · Brooklyn, US
• Will Shapiro · New York, US
• Brett Wittmershaus · Brooklyn, US

Key dates

• Filing date: Oct 11, 2022
• Grant date: Feb 27, 2024
• Expiry date: Oct 11, 2042

Classification

• Technology area (CPC G): Physics
• CPC primary: G16H50/70
• WIPO field: Medical technology
• WIPO sector: Instruments

Abstract

Described herein are techniques of using machine learning to automatically extract clinical variable values for subjects from clinical record data. The techniques designate certain clinical variables as hybrid variables that can be assigned values by machine learning model prediction. The techniques process, using a machine learning model trained to predict a value of a hybrid variable, clinical record data associated with a subject to obtain a predicted hybrid variable value and an associated confidence score. The techniques set the value of the hybrid variable for the subject to the predicted hybrid variable value when the model prediction is of sufficiently high confidence.