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 range of movement and/or frequency of musculoskeletal behavior of the patient while the patient moves 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 a given movement corresponding to the measured range of movement and/or frequency of musculoskeletal behavior of the patient;
computing mechanical and/or hemodynamic characteristics of the patient's vascular system 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, determining one or more features of the musculoskeletal behavior of the patient while the patient performs the given movement, the one or more features being used 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 based on the given movement, 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 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 1 , wherein the musculoskeletal behavior of the patient includes a head rotation.
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. The computer-implemented method of claim 7 , wherein the musculoskeletal behavior of the patient includes a head rotation.
9. A computer system for non-invasively assessing a risk of a clinical event in a patient, the system comprising:
at least one data storage device storing instructions for determining an effect of musculoskeletal activities in diagnosing or treating disease; and
at least one processor configured to execute the instructions to perform operations 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 range of movement and/or frequency of musculoskeletal behavior of the patient while the patient moves 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 a given movement corresponding to the measured range of movement and/or frequency of musculoskeletal behavior of the patient;
computing mechanical and/or hemodynamic characteristics of the patient's vascular system at a 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, determining one or more features of the musculoskeletal behavior of the patient while the patient performs the given movement, the one or more features being used 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.
10. The system of claim 9 , wherein generating the updated three-dimensional vascular model of the patient's anatomy further comprises generating a computational anatomic vascular model of the patient's anatomy.
11. The system of claim 10 , wherein the updated three-dimensional patient-specific vascular model of the patient's anatomy is generated using images of the patient's venous system in various postures taken by a magnetic resonance imaging (MRI) system.
12. The system of claim 10 , wherein the musculoskeletal behavior of the patient a head rotation.
13. The system of claim 9 , 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.
14. The system of claim 13 , wherein executing the one or more learned algorithms comprises a training phase and a prediction phase.
15. The system of claim 14 , wherein the training phase includes creating a feature vector of healthy patients and patients suffering from known clinical events or disease.
16. The system of claim 15 , wherein the musculoskeletal behavior of the patient includes a head rotation.
17. A non-transitory computer readable medium storing 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 range of movement and/or frequency of musculoskeletal behavior of the patient while the patient moves 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 a given movement corresponding to the measured range of movement and/or frequency of musculoskeletal behavior of the patient;
computing mechanical and/or hemodynamic characteristics of the patient's vascular system at the given movement 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, determining one or more features of the musculoskeletal behavior of the patient while the patient performs the given movement, the one or more features being used 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 movement, 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.
18. The non-transitory computer readable medium of claim 17 , wherein generating the updated three-dimensional vascular model of the patient's anatomy further comprises generating a computational anatomic vascular model of the patient's anatomy.
19. The non-transitory computer readable medium of claim 17 , wherein the updated three-dimensional patient-specific vascular model of the patient's anatomy is generated using images of the patient's venous system in various postures taken by a magnetic resonance imaging (MRI) system.
20. The non-transitory computer readable medium of claim 17 , wherein the musculoskeletal behavior of the patient includes a head rotation.