Bayesian clinical decision model for determining probability of transplant glomerulopathy

US8510245B2 · kind B2 · utility

Assignee

• The United States of America as represented by the Secretary of the Army · US

Inventors

• Alexander Stojadinovic · Bethesda, US
• Eric A. Elster · Kensington, US
• Doug K. Tadaki · Frederick, US
• John S. Eberhardt, III · Jeffersonton, US
• Trevor Brown · Washington, US
• Thomas A. Davis · Centreville, US
• Jonathan Forsberg · Kensington, US
• Jason Hawksworth · Silver Spring, US
• Roslyn Bernstein Mannon · Birmingham, US

Key dates

• Filing date: Apr 8, 2011
• Grant date: Aug 13, 2013
• Expiry date: Jan 23, 2032

Classification

• Technology area (CPC G): Physics
• CPC primary: G16B50/00
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

An embodiment of the invention provides a method for determining a patient-specific probability of transplant glomerulopathy. The method collects clinical parameters from a plurality of patients to create a training database. A fully unsupervised Bayesian Belief Network model is created using data from the training database; and, the fully unsupervised Bayesian Belief Network is validated. Clinical parameters are collected from an individual patient; and, such clinical parameters are input into the fully unsupervised Bayesian Belief Network model via a graphical user interface. The patient-specific probability of transplant glomerulopathy is output from the fully unsupervised Bayesian Belief Network model and sent to the graphical user interface for use by a clinician in pre-operative planning. The fully unsupervised Bayesian Belief Network model is updated using the clinical parameters from the individual patient and the patient-specific probability of transplant glomerulopathy.