Method and System for Personalized Blood Flow Modeling Based on Wearable Sensor Networks

Patent metadata

Field	Value
Publication number	US-2017293735-A1
Application number	US-201715458106-A
Country	US
Kind code	A1
Filing date	Mar 14, 2017
Priority date	Apr 12, 2016
Publication date	Oct 12, 2017
Grant date	—

Abstract

A method and system for personalized blood flow modeling based on wearable sensor networks is disclosed. A personalized anatomical model of vessels of a patient is generated based on initial patient data. Continuous cardiovascular measurements of the patient are received from a wearable sensor network on the patient. A computational blood flow model for simulating blood flow in the patient-specific anatomical model of the vessels of the patient is personalized based on the continuous cardiovascular measurements from the wearable sensor network. Blood flow and pressure in the patient-specific anatomical model of the vessels of the patient are simulated using the personalized computational blood flow model. Hemodynamic measures of interest for the patient are computed based on the simulated blood flow and pressure.

First claim

1 . A method for simulating blood flow to estimate one or more hemodynamic measures of interest for a patient, comprising:
generating a personalized anatomical model of vessels of a patient based on patient data; receiving one or more continuous cardiovascular measurements of the patient from a wearable sensor network on the patient; personalizing a computational blood flow model for simulating blood flow in the patient-specific anatomical model of the vessels of the patient based on the one or more continuous cardiovascular measurements from the wearable sensor network; simulating blood flow and pressure in the patient-specific anatomical model of the vessels of the patient using the personalized computational blood flow model; and computing one or more hemodynamic measures of interest for the patient based on the simulated blood flow and pressure.

2 . The method of claim 1 , wherein generating a personalized anatomical model of vessels of a patient based on patient data comprises:
receiving medical image data of the patient; and extracting centerlines and cross-sectional measurements for each of a plurality of arteries in a full-body systemic arterial model from the medical image data of the patient;

3 . The method of claim 1 , wherein generating a personalized anatomical model of vessels of a patient based on patient data comprises:
initializing a full-body systemic arterial model using a population-averages full-body systemic arterial model; and personalizing lengths and radii of a plurality of arteries in the full-body systemic arterial model based on the patient data.

4 . The method of claim 3 , wherein personalizing lengths and radii of a plurality of arteries in the full-body systemic arterial model based on the patient data comprises:
personalizing the lengths and radii of the plurality of arteries in the systemic arterial model based on height, weight, body mass index, gender, length of arms, length of legs, length of neck, and length of head of the patient.

5 . The method of claim 1 , further comprising repeating the receiving, personalizing, simulating, and computing steps each time a specified time period has passed, wherein receiving one or more continuous cardiovascular measurements of the patient from a wearable sensor network on the patient comprises:
receiving the one or more continuous cardiovascular measurements of the patient acquired by the wearable sensor network on the patient during the specified time period.

6 . The method of claim 1 , wherein receiving one or more continuous cardiovascular measurements of the patient from a wearable sensor network on the patient comprises:
receiving continuous heart rate measurements, continuous ECG signals, and one or more of continuous pulse oximetry measurements or continuous blood pressure measurements from the wearable sensor network.

7 . The method of claim 6 , wherein the patient-specific anatomical model of the vessels of the patient is a patient-specific anatomical model of full-body system arterial geometry, the computational blood flow model is represents arteries in the patient-specific anatomical model using one-dimensional models, and personalizing a computational blood flow model for simulating blood flow in the patient-specific anatomical model of the vessels of the patient based on the one or more continuous cardiovascular measurements from the wearable sensor network comprises:
personalizing arterial wall properties, an inlet boundary condition, and outlet boundary conditions of the computational blood flow model based on the one or more continuous cardiovascular measurements from the wearable sensor network.

8 . The method of claim 7 , wherein personalizing arterial wall properties, an inlet boundary condition, and outlet boundary conditions of the computational blood flow model based on the one or more continuous cardiovascular measurements from the wearable sensor network comprises:
personalizing wall properties based on the continuous pulse oximetry measurements or the continuous blood pressure measurements and the continuous ECG signals.

9 . The method of claim 7 , wherein personalizing arterial wall properties, an inlet boundary condition, and outlet boundary conditions of the computational blood flow model based on the one or more continuous cardiovascular measurements from the wearable sensor network comprises:
personalizing the inlet boundary condition by estimating a continuous cardiac output based on the continuous pulse oximetry measurements and the continuous ECG signals, and scaling a population-averaged aortic inlet profile using the estimated cardiac output and the continuous heart rate measurements to generate a personalized time-varying flow rate profile at the aortic inlet.

10 . The method of claim 7 , wherein personalizing arterial wall properties, an inlet boundary condition, and outlet boundary conditions of the computational blood flow model based on the one or more continuous cardiovascular measurements from the wearable sensor network comprises:
estimating three-element Windkessel parameters at outlets of the patient-specific anatomical model of full-body system arterial geometry based on the one or more continuous cardiovascular measurements from the wearable sensor network.

11 . The method of claim 1 , wherein computing one or more hemodynamic measures of interest for the patient based on the simulated blood flow and pressure comprises:
computing one or more of a central aortic blood pressure measure, a severity of peripheral artery disease (PAD) measure, a severity of aortic coarctation measure, an onset of hypertension measure, a CVD risk prediction measure, and a severity of coronary artery disease measure based on the simulated blood flow and pressure.

12 . The method of claim 1 , further comprising:
comparing at least one of the one or more hemodynamic measures of interest to a corresponding hemodynamic measure of interest acquired for a population of other patients to detect deviations from population-averaged values.

13 . An apparatus for simulating blood flow to estimate one or more hemodynamic measures of interest for a patient, comprising:
means for generating a personalized anatomical model of vessels of a patient based on patient data; means for receiving one or more continuous cardiovascular measurements of the patient from a wearable sensor network on the patient; means for personalizing a computational blood flow model for simulating blood flow in the patient-specific anatomical model of the vessels of the patient based on the one or more continuous cardiovascular measurements from the wearable sensor network; means for simulating blood flow and pressure in the patient-specific anatomical model of the vessels of the patient using the personalized computational blood flow model; and means for computing one or more hemodynamic measures of interest for the patient based on the simulated blood flow and pressure.

14 . The apparatus of claim 13 , wherein the means for generating a personalized anatomical model of vessels of a patient based on patient data comprises:
means for extracting centerlines and cross-sectional measurements for each of a plurality of arteries in a full-body systemic arterial model from medical image data of the patient;

15 . The apparatus of claim 13 , wherein the means for generating a personalized anatomical model of vessels of a patient based on patient data comprises:
means for initializing a full-body systemic arterial model using a population-averages full-body systemic arterial model; and means for personalizing lengths and ra

Assignees

• Siemens Healthcare Gmbh

Inventors

• Itu Lucian Mihai
• Passerini Tiziano
• Sharma Puneet

Classifications

• G06N99/005

  Physics · mapped topic

• G06F19/3437 Primary

  Physics · mapped topic

• G06F1/163

  Wearable computers, e.g. on a belt · CPC title

• G16H50/50 Primary

  for simulation or modelling of medical disorders · CPC title

• G06N20/00

  Machine learning · CPC title