System and method for personalization of cardiac hemodynamic digital twin using echocardiogram-based approach

Patent metadata

Field	Value
Publication number	US-2025259752-A1
Application number	US-202519045306-A
Country	US
Kind code	A1
Filing date	Feb 4, 2025
Priority date	Feb 9, 2024
Publication date	Aug 14, 2025
Grant date	—

Abstract

Existing techniques fail to propose a method for improving model parameters optimization and seamless integration of clinical data with computational model required for personalized cardiac hemodynamic model development. This disclosure relates to a system and method, which receives one or more model parameters comprising height, active pressure components and passive pressure components specific to left ventricle from cardiac hemodynamic model. The first set of values corresponding to one or more input parameters comprising end systolic diameter and end diastole diameter are received from subject specific Echo data. The second set of values corresponding to one or more model parameters are estimated using one or more input parameters. The estimated second set of values are optimized using a Particle swarm optimization to obtain one or more optimized values. Select at least a subset of optimized one or more values corresponding to one or more model parameters for personalization.

First claim

What is claimed is:

1 . A processor implemented method, comprising:
receiving, via one or more hardware processors, (i) one or more model parameters specific to a left ventricle from a cardiac hemodynamic model, wherein the one or more model parameters specific to the left ventricle comprises height of the left ventricle (h lv ), one or more active pressure components (a lv ), one or more passive pressure components (b lv ) and one or more compliance parameters C lv , and wherein the cardiac hemodynamic model is driven using an echocardiogram (ECG) data specific to a subject, and (ii) a first set of values corresponding to one or more input parameters from an echo data specific to the subject, wherein the one or more input parameters comprises an end systolic diameter, an end diastole diameter, an end systolic volume and an end diastolic volume specific to the left ventricle; estimating, via the one or more hardware processors, a second set of values corresponding to (i) the height of the left ventricle (h lv ) using the first set of values corresponding to the one or more input parameters, which is represented by an equation—

d
lv

=

6
⁢

V
i

4
⁢
π
⁢

K
lv

⁢

h
lv

wherein, K lv is a scale factor which is dependent on geometry of the left ventricle, V i refers to a volume at any instance in a cardiac cycle, and wherein the height of the left ventricle h lv is dependent on the volume of the left ventricle V lv at any instance in a cardiac cycle which is represented by

V
lv

=

K
lv

⁢

4
3

⁢
π
⁢

h
lv

⁢

d
lv
2

2

,

and ii) the one or more active pressure components (a lv ) and the one or more passive pressure components (b lv ) using the first set of values corresponding to the one or more input parameters, wherein a cardiac chamber pressure of the left ventricle P lv comprising an active filling pressure phase (a) and a passive pressure phase (p) is expressed as P lv =P lv a+P lv p, and wherein the passive pressure phase (p) for the one or more active pressure components (a lv ) and the one or more passive pressure components (b lv ) is represented by an equation—

P
lv

⁢
a

=

E
lv

(

K
lv

⁢

4
3

⁢
π
⁢

h
lv

⁢

d
lv
2

4

)

P
lv

⁢
p

=

a
lv

⁢
e
⁢

(

K
lv

⁢

b
lv

⁢

2
3

⁢
π
⁢

h
lv

⁢

d
lv
2

2

)

-
1

wherein E is an elastance, which is a reciprocal of a compliance function pertaining to the cardiac chamber pressure of the left ventricle;
optimizing, via the one or more hardware processors, the estimated second set of values corresponding to the one or more model parameters using a particle swarm optimization (PSO) technique to obtain one or more optimized values, wherein the optimization is performed by comparing the estimated second set of values corresponding to the one or more model parameters with the first set of values corresponding to the one or more input parameters; and
selecting, via the one or more hardware processors, at least a subset of the one or more optimized values corresponding to the one or more model parameters for personalization.

2 . A system, comprising:
a memory storing instructions; one or more communication interfaces; and one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to:
receive (i) one or more model parameters specific to a left ventricle from a cardiac hemodynamic model, wherein the one or more model parameters specific to the left ventricle comprises height of the left ventricle (h lv ), one or more active pressure components (a lv ), one or more passive pressure components (b lv ) and one or more compliance parameters C lv , and wherein the cardiac hemodynamic model is driven using an echocardiogram (ECG) data specific to a subject, and (ii) a first set of values corresponding to one or more input parameters from an echo data specific to the subject, wherein the one or more input parameters comprises an end systolic diameter, an end diastole diameter, an end systolic volume and an end diastolic volume specific to the

Assignees

• Tata Consultancy Services Ltd

Inventors

• Mazumder Oishee
• Mukherjee Ayan
• Sinha Aniruddha
• Khandelwal Sundeep
• Banerjee Shilajit

Classifications

• G06T2207/30048

  Heart; Cardiac · CPC title

• G06T7/0012

  Biomedical image inspection · CPC title

• G16H30/40

  for processing medical images, e.g. editing · CPC title

• A61B8/0883

  for diagnosis of the heart · CPC title

• A61B5/02028

  Determining haemodynamic parameters not otherwise provided for, e.g. cardiac contractility or left ventricular ejection fraction · CPC title