Clinically-Driven Virtual Patient Cohorts Generation: An Application to Aorta

Pau Romero; Miguel Lozano; Francisco Martínez-Gil; Dolors Serra; Rafael Sebastián; Pablo Lamata; Ignacio García-Fernández

doi:10.3389/fphys.2021.713118

Clinically-Driven Virtual Patient Cohorts Generation: An Application to Aorta

Pau Romero, Miguel Lozano, Francisco Martínez-Gil, Dolors Serra, Rafael Sebastián, Pablo Lamata, Ignacio García-Fernández^*

^*Corresponding author for this work

Biomedical Engineering Department

Research output: Contribution to journal › Article › peer-review

4 Citations (Scopus)

Abstract

The combination of machine learning methods together with computational modeling and simulation of the cardiovascular system brings the possibility of obtaining very valuable information about new therapies or clinical devices through in-silico experiments. However, the application of machine learning methods demands access to large cohorts of patients. As an alternative to medical data acquisition and processing, which often requires some degree of manual intervention, the generation of virtual cohorts made of synthetic patients can be automated. However, the generation of a synthetic sample can still be computationally demanding to guarantee that it is clinically meaningful and that it reflects enough inter-patient variability. This paper addresses the problem of generating virtual patient cohorts of thoracic aorta geometries that can be used for in-silico trials. In particular, we focus on the problem of generating a cohort of patients that meet a particular clinical criterion, regardless the access to a reference sample of that phenotype. We formalize the problem of clinically-driven sampling and assess several sampling strategies with two goals, sampling efficiency, i.e., that the generated individuals actually belong to the target population, and that the statistical properties of the cohort can be controlled. Our results show that generative adversarial networks can produce reliable, clinically-driven cohorts of thoracic aortas with good efficiency. Moreover, non-linear predictors can serve as an efficient alternative to the sometimes expensive evaluation of anatomical or functional parameters of the organ of interest.

Original language	English
Article number	713118
Journal	Frontiers in Physiology
Volume	12
DOIs	https://doi.org/10.3389/fphys.2021.713118
Publication status	Published - 1 Sept 2021

Keywords

clinically-driven sampling
digital twin
generative adversarial network
in-silico trials
support vector machine
synthetic population
thoracic-aorta
virtual cohort

Access to Document

10.3389/fphys.2021.713118

Cite this

@article{9c4d466753c94b7aa90ceea558b59805,

title = "Clinically-Driven Virtual Patient Cohorts Generation: An Application to Aorta",

abstract = "The combination of machine learning methods together with computational modeling and simulation of the cardiovascular system brings the possibility of obtaining very valuable information about new therapies or clinical devices through in-silico experiments. However, the application of machine learning methods demands access to large cohorts of patients. As an alternative to medical data acquisition and processing, which often requires some degree of manual intervention, the generation of virtual cohorts made of synthetic patients can be automated. However, the generation of a synthetic sample can still be computationally demanding to guarantee that it is clinically meaningful and that it reflects enough inter-patient variability. This paper addresses the problem of generating virtual patient cohorts of thoracic aorta geometries that can be used for in-silico trials. In particular, we focus on the problem of generating a cohort of patients that meet a particular clinical criterion, regardless the access to a reference sample of that phenotype. We formalize the problem of clinically-driven sampling and assess several sampling strategies with two goals, sampling efficiency, i.e., that the generated individuals actually belong to the target population, and that the statistical properties of the cohort can be controlled. Our results show that generative adversarial networks can produce reliable, clinically-driven cohorts of thoracic aortas with good efficiency. Moreover, non-linear predictors can serve as an efficient alternative to the sometimes expensive evaluation of anatomical or functional parameters of the organ of interest.",

keywords = "clinically-driven sampling, digital twin, generative adversarial network, in-silico trials, support vector machine, synthetic population, thoracic-aorta, virtual cohort",

author = "Pau Romero and Miguel Lozano and Francisco Mart{\'i}nez-Gil and Dolors Serra and Rafael Sebasti{\'a}n and Pablo Lamata and Ignacio Garc{\'i}a-Fern{\'a}ndez",

note = "Funding Information: This research has been partially funded by VLC-BIOMED Grant Programme, under the project 12-PARAMVALVE-GARCIA-ALBERICH-2017-B. PL holds a Wellcome Trust Senior Research Fellowships (209450/Z/17/Z). Funding Information: Funding. This research has been partially funded by VLC-BIOMED Grant Programme, under the project 12-PARAMVALVE-GARCIA-ALBERICH-2017-B. PL holds a Wellcome Trust Senior Research Fellowships (209450/Z/17/Z). Publisher Copyright: {\textcopyright} Copyright {\textcopyright} 2021 Romero, Lozano, Mart{\'i}nez-Gil, Serra, Sebasti{\'a}n, Lamata and Garc{\'i}a-Fern{\'a}ndez. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.",

year = "2021",

month = sep,

day = "1",

doi = "10.3389/fphys.2021.713118",

language = "English",

volume = "12",

journal = "Frontiers in Physiology",

issn = "1664-042X",

publisher = "Frontiers",

}

TY - JOUR

T1 - Clinically-Driven Virtual Patient Cohorts Generation

T2 - An Application to Aorta

AU - Romero, Pau

AU - Lozano, Miguel

AU - Martínez-Gil, Francisco

AU - Serra, Dolors

AU - Sebastián, Rafael

AU - Lamata, Pablo

AU - García-Fernández, Ignacio

N1 - Funding Information: This research has been partially funded by VLC-BIOMED Grant Programme, under the project 12-PARAMVALVE-GARCIA-ALBERICH-2017-B. PL holds a Wellcome Trust Senior Research Fellowships (209450/Z/17/Z). Funding Information: Funding. This research has been partially funded by VLC-BIOMED Grant Programme, under the project 12-PARAMVALVE-GARCIA-ALBERICH-2017-B. PL holds a Wellcome Trust Senior Research Fellowships (209450/Z/17/Z). Publisher Copyright: © Copyright © 2021 Romero, Lozano, Martínez-Gil, Serra, Sebastián, Lamata and García-Fernández. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.

PY - 2021/9/1

Y1 - 2021/9/1

N2 - The combination of machine learning methods together with computational modeling and simulation of the cardiovascular system brings the possibility of obtaining very valuable information about new therapies or clinical devices through in-silico experiments. However, the application of machine learning methods demands access to large cohorts of patients. As an alternative to medical data acquisition and processing, which often requires some degree of manual intervention, the generation of virtual cohorts made of synthetic patients can be automated. However, the generation of a synthetic sample can still be computationally demanding to guarantee that it is clinically meaningful and that it reflects enough inter-patient variability. This paper addresses the problem of generating virtual patient cohorts of thoracic aorta geometries that can be used for in-silico trials. In particular, we focus on the problem of generating a cohort of patients that meet a particular clinical criterion, regardless the access to a reference sample of that phenotype. We formalize the problem of clinically-driven sampling and assess several sampling strategies with two goals, sampling efficiency, i.e., that the generated individuals actually belong to the target population, and that the statistical properties of the cohort can be controlled. Our results show that generative adversarial networks can produce reliable, clinically-driven cohorts of thoracic aortas with good efficiency. Moreover, non-linear predictors can serve as an efficient alternative to the sometimes expensive evaluation of anatomical or functional parameters of the organ of interest.

AB - The combination of machine learning methods together with computational modeling and simulation of the cardiovascular system brings the possibility of obtaining very valuable information about new therapies or clinical devices through in-silico experiments. However, the application of machine learning methods demands access to large cohorts of patients. As an alternative to medical data acquisition and processing, which often requires some degree of manual intervention, the generation of virtual cohorts made of synthetic patients can be automated. However, the generation of a synthetic sample can still be computationally demanding to guarantee that it is clinically meaningful and that it reflects enough inter-patient variability. This paper addresses the problem of generating virtual patient cohorts of thoracic aorta geometries that can be used for in-silico trials. In particular, we focus on the problem of generating a cohort of patients that meet a particular clinical criterion, regardless the access to a reference sample of that phenotype. We formalize the problem of clinically-driven sampling and assess several sampling strategies with two goals, sampling efficiency, i.e., that the generated individuals actually belong to the target population, and that the statistical properties of the cohort can be controlled. Our results show that generative adversarial networks can produce reliable, clinically-driven cohorts of thoracic aortas with good efficiency. Moreover, non-linear predictors can serve as an efficient alternative to the sometimes expensive evaluation of anatomical or functional parameters of the organ of interest.

KW - clinically-driven sampling

KW - digital twin

KW - generative adversarial network

KW - in-silico trials

KW - support vector machine

KW - synthetic population

KW - thoracic-aorta

KW - virtual cohort

UR - http://www.scopus.com/inward/record.url?scp=85115010255&partnerID=8YFLogxK

U2 - 10.3389/fphys.2021.713118

DO - 10.3389/fphys.2021.713118

M3 - Article

AN - SCOPUS:85115010255

SN - 1664-042X

VL - 12

JO - Frontiers in Physiology

JF - Frontiers in Physiology

M1 - 713118

ER -

Clinically-Driven Virtual Patient Cohorts Generation: An Application to Aorta

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this