Systems and methods for cardiovascular blood flow and musculoskeletal modeling for predicting device failure or clinical events
Computer-implemented methods are disclosed for assessing the effect of musculoskeletal activities on disease and/or clinical events, the method comprising: receiving a patient-specific vascular and musculoskeletal model of a patient's anatomy, including at least one vessel of the patient; receiving at least one characteristic of the patient's musculoskeletal activity; generating or updating a computational anatomic vascular and musculoskeletal model of the patient's anatomy based on the received at least one characteristic of musculoskeletal activity; performing at least one of a computational fluid dynamics analysis or a structural mechanics simulation on the computational anatomic vascular and musculoskeletal model; and estimating at least one of the patient's risk of disease or clinical events based on the performed computational fluid dynamics analysis and/or structural mechanics simulation. Systems and computer readable media for executing these methods are also disclosed.
1. A computer-implemented method of non-invasively assessing a risk of a clinical event in a patient, the method comprising:
obtaining, via an imaging device, one or more images of a patient's anatomy;
generating a first three-dimensional patient-specific vascular model of the patient's anatomy based on the one or more images, including at least one vessel of the patient;
measuring a duration and/or frequency of musculoskeletal behavior of the patient while the patient is at a given posture via a device associated with the patient;
generating an updated three-dimensional patient-specific vascular model of the patient's anatomy by simulating or detecting the given posture corresponding to the measured duration and/or frequency of musculoskeletal behavior of the patient;
computing mechanical and/or hemodynamic characteristics of the patient's vascular system at the given posture by performing at least one of a computational fluid dynamics analysis or a structural mechanics simulation using the updated three-dimensional patient-specific vascular model;
using the at least one of the computational fluid dynamics analysis or structural mechanics simulation by creating a feature vector of the musculoskeletal behavior of the patient while the patient is at the given posture to estimate and output an effect of the computed mechanical and/or hemodynamic characteristics on at least one of the patient's risk of disease, a risk of failure of a device, or a performance characteristic of a device;
assessing a risk of a clinical event in the patient at the given posture, using the estimated effect of the mechanical and/or hemodynamic characteristics of the vascular system of the patient on the at least one of the patient's risk of disease, the risk of failure of a device, or the performance characteristic of a device; and
outputting the risk of the clinical event to an electronic storage medium or a display for use by one or more healthcare providers.
2. The computer-implemented method of claim 1 , wherein generating the updated three-dimensional patient-specific vascular model of the patient's anatomy comprises generating a computational anatomic vascular model of the patient's anatomy.
3. The computer-implemented method of claim 2 , wherein the updated three-dimensional patient-specific vascular model of the patient's anatomy is generated using one or more of:
a computational structural mechanics simulation; or
images of the patient's venous system in various postures taken by a magnetic resonance imaging (MRI) system.
4. The computer-implemented method of claim 2 , wherein the musculoskeletal behavior of the patient includes one or more of sitting or lying down.
5. The computer-implemented method of claim 1 , wherein estimating the effect of the mechanical and/or hemodynamic characteristics of the vascular system of the patient on at least one of the patient's risk of disease, the risk of failure of a device, or the performance characteristic of a device includes executing one or more learned algorithms.
6. The computer-implemented method of claim 5 , wherein executing the one or more learned algorithms comprises a training phase and a prediction phase.
7. The computer-implemented method of claim 6 , wherein the training phase includes creating a feature vector of healthy patients and patients suffering from known clinical events or disease.
8. A computer system for non-invasively assessing a risk of a clinical event in a patient, the system comprising:
a data storage device storing instructions for the determining the effect of musculoskeletal activities in diagnosing or treating disease; and
a processor configured to execute the instructions to perform a method including:
obtaining, via an imaging device, one or more images of a patient's anatomy;
generating a first three-dimensional patient-specific vascular model of the patient's anatomy based on the one or more images, including at least one vessel of the patient;
measuring a duration and/or frequency of musculoskeletal behavior of the patient while the patient is at a given posture via a device associated with the patient;
generating an updated three-dimensional patient-specific vascular model of the patient's anatomy by simulating or detecting the given posture corresponding to the measured duration and/or frequency of musculoskeletal behavior of the patient;
computing mechanical and/or hemodynamic characteristics of the patient's vascular system at the given posture by performing at least one of a computational fluid dynamics analysis or a structural mechanics simulation using the updated three-dimensional patient-specific vascular model;
using the at least one of the computational fluid dynamics analysis or structural mechanics simulation by creating a feature vector of the musculoskeletal behavior of the patient while the patient is at the given posture to estimate and output an effect of the computed mechanical and/or hemodynamic characteristics on at least one of the patient's risk of disease, a risk of failure of a device, or a performance characteristic of a device;
assessing a risk of a clinical event in the patient at the given posture, using the estimated effect of the mechanical and/or hemodynamic characteristics of the vascular system of the patient on the at least one of the patient's risk of disease, the risk of failure of a device, or the performance characteristic of a device; and
outputting the risk of the clinical event to an electronic storage medium or a display for use by one or more healthcare providers.
9. The system of claim 8 , wherein the step of generating the updated three-dimensional vascular model of the patient's anatomy comprises generating a computational anatomic vascular model of the patient's anatomy.
10. The system of claim 9 , wherein the updated three-dimensional patient-specific vascular model of the patient's anatomy is generated using one or more of:
a computational structural mechanics simulation; or
images of the patient's venous system in various postures taken by a magnetic resonance imaging (MRI) system.
11. The system of claim 9 , wherein the musculoskeletal behavior of the patient includes one or more of sitting or lying down.
12. The system of claim 8 , wherein estimating the effect of the mechanical and/or hemodynamic characteristics of the vascular system of the patient on at least one of the patient's risk of disease, the risk of failure of a device, or the performance characteristic of a device includes executing one or more learned algorithms.
13. The system of claim 12 , wherein executing the one or more learned algorithms comprises a training phase and a prediction phase.
14. The system of claim 13 , wherein the training phase includes creating a feature vector of healthy patients and patients suffering from known clinical events or disease.
15. A non-transitory computer readable medium for use on a computer system containing computer-executable programming instructions for performing a method of non-invasively assessing a risk of a clinical event in a patient, the method comprising:
obtaining, via an imaging device, one or more images of a patient's anatomy;
generating a first three-dimensional patient-specific vascular model of the patient's anatomy based on the one or more images, including at least one vessel of the patient;
measuring a duration and/or frequency of musculoskeletal behavior of the patient while the patient is at a given posture via a device associated with the patient;
generating an updated three-dimensional patient-specific vascular model of the patient's anatomy by simulating or detecting the given posture corresponding to the measured duration and/or frequency of musculoskeletal behavior of the patient;
computing mechanical and/or hemodynamic characteristics of the patient's vascular system at the given posture by performing at least one of a computational fluid dynamics analysis or a structural mechanics simulation using the updated three-dimensional patient-specific vascular model;
using the at least one of the computational fluid dynamics analysis or structural mechanics simulation by creating a feature vector of the musculoskeletal behavior of the patient while the patient is at the given posture to estimate and output an effect of the computed mechanical and/or hemodynamic characteristics on at least one of the patient's risk of disease, a risk of failure of a device, or a performance characteristic of a device;
assessing a risk of a clinical event in the patient at the given posture, using the estimated effect of the mechanical and/or hemodynamic characteristics of the vascular system of the patient on the at least one of the patient's risk of disease, the risk of failure of a device, or the performance characteristic of a device; and
outputting the risk of the clinical event to an electronic storage medium or a display for use by one or more healthcare providers.
16. The non-transitory computer readable medium of claim 15 , wherein the step of generating the updated three-dimensional vascular model of the patient's anatomy comprises generating a computational anatomic vascular model of the patient's anatomy.
17. The non-transitory computer readable medium of claim 15 , wherein the updated three-dimensional patient-specific vascular model of the patient's anatomy is generated using one or more of:
a computational structural mechanics simulation; or
images of the patient's venous system in various postures taken by a magnetic resonance imaging (MRI) system.
18. The non-transitory computer readable medium of claim 15 , wherein the musculoskeletal behavior of the patient includes one or more of sitting or lying down.