Cardiogenic embolism stroke risk prediction system and method based on medical images

Abstract

Provided are a system and method for predicting the risk of cardioembolic stroke based on medical images. Systems and methods for patient-specific ischemic stroke risk prediction based on medical images are disclosed. Extract left atrial (LA) and left atrial appendage (LAA) measurements from medical image data of patients. Based on the LA and LAA measurements extracted from the patient's medical image data, derived measures of LA and LAA for the patient are calculated using a patient-specific computational model of cardiac function. Based on the extracted LA and LAA measurements and the derived metrics calculated for the patient's LA and LAA, a trained machine learning-based classifier is used to calculate a stroke risk score for the patient, which inputs the extracted LA and LAA Measurements and derived measures calculated for the patient's LA and LAA were featured.

Description

[0001] This application claims the benefit of US Provisional Application No. 62 / 301,861, filed March 1, 2016, the disclosure of which is incorporated herein by reference in its entirety. technical field [0002] The present invention relates to patient-specific stroke risk prediction, and more particularly to patient-specific cardioembolic stroke risk prediction based on medical images. Background technique [0003] Stroke is the leading cause of adult disability and the fifth leading cause of death in the United States. There are two types of stroke, hemorrhagic and ischemic, with approximately 13% of strokes occurring being hemorrhagic and 87% ischemic. Ischemic strokes can in turn be of the embolic (~20%) or thrombotic (~80%) type. In an embolic stroke, a blood clot or platelet fragment forms somewhere in the body (usually the heart) and travels to the brain, where it blocks a small blood vessel. In a thrombotic stroke, a blood clot forms inside an artery that supplies ...

AI Technical Summary

Problems solved by technology

However, risk indicators extracted from such assessments are limited to simple statistical indicators with large variance, which are usually based on clinical longitudinal data

This risk prediction method has several disadvantages, including temporal plasticity (i.e., uncertainty) and a large range of these indicators, and weak / reduced patient specificity

Images