Computer-implemented machine learning for detection and statistical analysis of errors by healthcare providers

US11423538B2 · kind B2 · utility

Assignee

• Covera Health · US

Inventors

• Ron Vianu · New York, US
• Tarmo Henrik Aijo · New York, US
• James Browning · Glasgow, GB
• Xiaojin Dong · Bellerose Terrace, US
• Bryce Eron Eakin · New York, US
• Daniel R. Elgort · Cleveland Heights, US
• Richard Herzog · New York, US
• Benjamin L. Odry · West New York, US
• JinHyeong Park · Princeton, US
• Benjamin Sellman Suutari · New York, US
• Gregory Allen Dubbin · New York, US

Key dates

• Filing date: Apr 15, 2020
• Grant date: Aug 23, 2022
• Expiry date: Mar 4, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G16H30/20
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

For training data pairs comprising training text (a radiological report) and training images (radiological images associated with the radiological report), a first encoder network determines word embeddings for the training text. A concept is generated from the operation of layers of the first encoder network, which is regularized by a first loss between the generated concept and a labeled concept for the training text. A second encoder network determines features for the training image. A heatmap is generated from the operation of layers of the second encoder network, which is regularized by a second loss between the generated heatmap and a labeled heatmap for the training image. A categorical cross entropy loss is calculated between a diagnostic quality category (classified by an error encoder) and a labeled diagnostic quality category for the training data pair. A total loss function comprising the first, second, and categorical cross entropy losses is minimized.