1
|
El-Sofany H, Bouallegue B, El-Latif YMA. A proposed technique for predicting heart disease using machine learning algorithms and an explainable AI method. Sci Rep 2024; 14:23277. [PMID: 39375427 PMCID: PMC11458608 DOI: 10.1038/s41598-024-74656-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2024] [Accepted: 09/27/2024] [Indexed: 10/09/2024] Open
Abstract
One of the critical issues in medical data analysis is accurately predicting a patient's risk of heart disease, which is vital for early intervention and reducing mortality rates. Early detection allows for timely treatment and continuous monitoring by healthcare providers, which is essential but often limited by the inability of medical professionals to provide constant patient supervision. Early detection of cardiac problems and continuous patient monitoring by physicians can help reduce death rates. Doctors cannot constantly have contact with patients, and heart disease detection is not always accurate. By offering a more solid foundation for prediction and decision-making based on data provided by healthcare sectors worldwide, machine learning (ML) could help physicians with the prediction and detection of HD. This study aims to use different feature selection strategies to produce an accurate ML algorithm for early heart disease prediction. We have chosen features using chi-square, ANOVA, and mutual information methods. The three feature groups chosen were SF-1, SF-2, and SF-3. The study employed ten machine learning algorithms to determine the most accurate technique and feature subset fit. The classification algorithms used include support vector machines (SVM), XGBoost, bagging, decision trees (DT), and random forests (RF). We evaluated the proposed heart disease prediction technique using a private dataset, a public dataset, and different cross-validation methods. We used the Synthetic Minority Oversampling Technique (SMOTE) to eliminate inconsistent data and discover the machine learning algorithm that achieves the most accurate heart disease predictions. Healthcare providers might identify early-stage heart disease quickly and cheaply with the proposed method. We have used the most effective ML algorithm to create a mobile app that instantly predicts heart disease based on the input symptoms. The experimental results demonstrated that the XGBoost algorithm performed optimally when applied to the combined datasets and the SF-2 feature subset. It had 97.57% accuracy, 96.61% sensitivity, 90.48% specificity, 95.00% precision, a 92.68% F1 score, and a 98% AUC. We have developed an explainable AI method based on SHAP approaches to understand how the system makes its final predictions.
Collapse
Affiliation(s)
- Hosam El-Sofany
- College of Computer Science, King Khalid University, Abha, Kingdom of Saudi Arabia.
| | - Belgacem Bouallegue
- College of Computer Science, King Khalid University, Abha, Kingdom of Saudi Arabia
- Electronics and Micro-Electronics Laboratory (E. μ. E. L), Faculty of Sciences of Monastir, University of Monastir, Monastir, Tunisia
| | | |
Collapse
|
2
|
Loomba RS, Savorgnan F, Acosta S, Elhoff JJ, Farias JS, Villarreal EG, Flores S. Clinical Interventions and Hemodynamic Monitoring in the Setting of Left Ventricular Systolic Heart Failure in Children: Insights From a Physiologic Simulator. Am J Ther 2024; 31:e531-e540. [PMID: 39292830 DOI: 10.1097/mjt.0000000000001711] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/20/2024]
Abstract
BACKGROUND In pediatric critical care, vasoactive/inotropic support is widely used in patients with heart failure, but it remains controversial because the influence of multiple medications and the interplay between their inotropic and vasoactive effects on a given patient are hard to predict. Robust evidence supporting their use and quantifying their effects in this group of patients is scarce. STUDY QUESTION The aim of this study was to characterize the effect of vasoactive medications on various cardiovascular parameters in pediatric patient with decreased ejection fraction. STUDY DESIGN Clinical-data based physiologic simulator study. MEASURE AND OUTCOMES We used a physics-based computer simulator for quantifying the response of cardiovascular parameters to the administration of various types of vasoactive/inotropic medications in pediatric patients with decreased ejection fraction. The simulator allowed us to study the impact of increasing medication dosage and the simultaneous administration of some vasoactive agents. Correlation and linear regression analyses yielded the quantified effects on the vasoactive/inotropic support. RESULTS Cardiac output and systemic venous saturation significantly increased with the administration of dobutamine and milrinone in isolation, and combination of milrinone with dobutamine, dopamine, or epinephrine. Both parameters decreased with the administration of epinephrine and norepinephrine in isolation. No significant change in these hemodynamic parameters was observed with the administration of dopamine in isolation. CONCLUSIONS Milrinone and dobutamine were the only vasoactive medications that, when used in isolation, improved systemic oxygen delivery. Milrinone in combination with dobutamine, dopamine, or epinephrine also increased systemic oxygen delivery. The induced increment on afterload can negatively affect systemic oxygen delivery.
Collapse
Affiliation(s)
- Rohit S Loomba
- Division of Cardiology, Advocate Children's Hospital, Oak Lawn, IL
- Department of Pediatrics, Chicago Medical School/Rosalind Franklin University of Medicine and Science, North Chicago, IL
| | - Fabio Savorgnan
- Section of Critical Care Medicine and Cardiology, Texas Children's Hospital, Houston, TX
- Department of Pediatrics, Baylor College of Medicine, Houston, TX; and
| | - Sebastian Acosta
- Section of Critical Care Medicine and Cardiology, Texas Children's Hospital, Houston, TX
- Department of Pediatrics, Baylor College of Medicine, Houston, TX; and
| | - Justin J Elhoff
- Section of Critical Care Medicine and Cardiology, Texas Children's Hospital, Houston, TX
- Department of Pediatrics, Baylor College of Medicine, Houston, TX; and
| | - Juan S Farias
- Tecnologico de Monterrey, Escuela de Medicina y Ciencias de la Salud, Monterrey, Nuevo Leon, Mexico
| | - Enrique G Villarreal
- Tecnologico de Monterrey, Escuela de Medicina y Ciencias de la Salud, Monterrey, Nuevo Leon, Mexico
| | - Saul Flores
- Section of Critical Care Medicine and Cardiology, Texas Children's Hospital, Houston, TX
- Department of Pediatrics, Baylor College of Medicine, Houston, TX; and
| |
Collapse
|
3
|
Aramburu J, Ruijsink B, Chabiniok R, Pushparajah K, Alastruey J. Patient-specific closed-loop model of the fontan circulation: Calibration and validation. Heliyon 2024; 10:e30404. [PMID: 38742066 PMCID: PMC11089314 DOI: 10.1016/j.heliyon.2024.e30404] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/08/2024] [Revised: 04/24/2024] [Accepted: 04/25/2024] [Indexed: 05/16/2024] Open
Abstract
The Fontan circulation, designed for managing patients with a single functional ventricle, presents challenges in long-term outcomes. Computational methods offer potential solutions, yet their application in cardiology practice remains largely unexplored. Our aim was to assess the ability of a patient-specific, closed-loop, reduced-order blood flow model to simulate pulsatile blood flow in the Fontan circulation. Using one-dimensional models, we simulated the aorta, superior and inferior venae cavae, and right and left pulmonary arteries, while lumping heart chambers and remaining vessels into zero-dimensional models. The model was calibrated with patient-specific haemodynamic data from combined cardiac catheterisation and magnetic resonance exams, using a novel physics-based stepwise methodology involving simpler open-loop models. Testing on a 10-year-old, anesthetised patient, demonstrated the model's capability to replicate pulsatile pressure and flow in the larger vessels and ventricular pressure. Average relative errors in mean pressure and flow were 2.9 % and 3.6 %, with average relative point-to-point errors (RPPE) in pressure and flow at 5.2 % and 16.0 %. Comparing simulation results to measurements, mean aortic pressure and flow values were 50.7 vs. 50.4 mmHg and 41.6 vs. 41.9 ml/s, respectively, while ventricular pressure values were 28.7 vs. 27.4 mmHg. The model accurately described time-varying ventricular volume with a RPPE of 2.9 %, with mean, minimum, and maximum ventricular volume values for simulation results vs. measurements at 59.2 vs. 58.2 ml, 38.0 vs. 37.6 ml, and 76.0 vs. 74.4 ml, respectively. It provided physiologically realistic predictions of haemodynamic changes from pulmonary vasodilation and atrial fenestration opening. The new model and calibration methodology are freely available, offering a platform to virtually investigate the Fontan circulation's response to clinical interventions and explore potential mechanisms of Fontan failure. Future efforts will concentrate on broadening the model's applicability to a wider range of patient populations and clinical scenarios, as well as testing its effectiveness.
Collapse
Affiliation(s)
- Jorge Aramburu
- Universidad de Navarra, TECNUN Escuela de Ingeniería, P° Manuel Lardizabal 13, 20018, Donostia/San Sebastián, Spain
| | - Bram Ruijsink
- School of Biomedical Engineering and Imaging Sciences, King's College London, St Thomas' Hospital, SE1 7EH, London, UK
| | - Radomir Chabiniok
- School of Biomedical Engineering and Imaging Sciences, King's College London, St Thomas' Hospital, SE1 7EH, London, UK
- Division of Pediatric Cardiology, Department of Pediatrics, UT Southwestern Medical Center, Dallas, TX, USA
| | - Kuberan Pushparajah
- School of Biomedical Engineering and Imaging Sciences, King's College London, St Thomas' Hospital, SE1 7EH, London, UK
- Department of Congenital Heart Disease, Evelina Children's Hospital, SE1 7EH, London, UK
| | - Jordi Alastruey
- School of Biomedical Engineering and Imaging Sciences, King's College London, St Thomas' Hospital, SE1 7EH, London, UK
| |
Collapse
|
4
|
A computational study of aortic reconstruction in single ventricle patients. Biomech Model Mechanobiol 2023; 22:357-377. [PMID: 36335184 PMCID: PMC10174275 DOI: 10.1007/s10237-022-01650-w] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/21/2022] [Accepted: 10/12/2022] [Indexed: 11/06/2022]
Abstract
Patients with hypoplastic left heart syndrome (HLHS) are born with an underdeveloped left heart. They typically receive a sequence of surgeries that result in a single ventricle physiology called the Fontan circulation. While these patients usually survive into early adulthood, they are at risk for medical complications, partially due to their lower than normal cardiac output, which leads to insufficient cerebral and gut perfusion. While clinical imaging data can provide detailed insight into cardiovascular function within the imaged region, it is difficult to use these data for assessing deficiencies in the rest of the body and for deriving blood pressure dynamics. Data from patients used in this paper include three-dimensional, magnetic resonance angiograms (MRA), time-resolved phase contrast cardiac magnetic resonance images (4D-MRI) and sphygmomanometer blood pressure measurements. The 4D-MRI images provide detailed insight into velocity and flow in vessels within the imaged region, but they cannot predict flow in the rest of the body, nor do they provide values of blood pressure. To remedy these limitations, this study combines the MRA, 4D-MRI, and pressure data with 1D fluid dynamics models to predict hemodynamics in the major systemic arteries, including the cerebral and gut vasculature. A specific focus is placed on studying the impact of aortic reconstruction occurring during the first surgery that results in abnormal vessel morphology. To study these effects, we compare simulations for an HLHS patient with simulations for a matched control patient that has double outlet right ventricle (DORV) physiology with a native aorta. Our results show that the HLHS patient has hypertensive pressures in the brain as well as reduced flow to the gut. Wave intensity analysis suggests that the HLHS patient has irregular circulatory function during light upright exercise conditions and that predicted wall shear stresses are lower than normal, suggesting the HLHS patient may have hypertension.
Collapse
|
5
|
Corno AF, Koerner TS, Salazar JD. The pendulum of Fontan fenestration. Transl Pediatr 2023; 12:104-107. [PMID: 36798929 PMCID: PMC9926132 DOI: 10.21037/tp-22-562] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/31/2022] [Accepted: 01/10/2023] [Indexed: 01/15/2023] Open
Affiliation(s)
- Antonio F Corno
- Department of Pediatric and Congenital Heart Surgery, Children's Heart Institute, Memorial Hermann Children's Hospital, University of Texas Health Science Center in Houston, McGovern Medical School, Houston, TX, USA
| | - Taylor S Koerner
- Department of Pediatric and Congenital Heart Surgery, Children's Heart Institute, Memorial Hermann Children's Hospital, University of Texas Health Science Center in Houston, McGovern Medical School, Houston, TX, USA
| | - Jorge D Salazar
- Department of Pediatric and Congenital Heart Surgery, Children's Heart Institute, Memorial Hermann Children's Hospital, University of Texas Health Science Center in Houston, McGovern Medical School, Houston, TX, USA
| |
Collapse
|
6
|
Corno AF, Zhou Z, Uppu SC, Huang S, Marino B, Milewicz DM, Salazar JD. The Secrets of the Frogs Heart. Pediatr Cardiol 2022; 43:1471-1480. [PMID: 35290490 DOI: 10.1007/s00246-022-02870-8] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/11/2022] [Accepted: 03/04/2022] [Indexed: 12/18/2022]
Abstract
The heart of the African clawed frog has a double-inlet and single-outlet ventricle supporting systemic and pulmonary circulations via a truncus, and a lifespan of 25-30 years. We sought to understand the unique cardiac anatomic and physiologic characteristics, with balanced circulation and low metabolic rate, by comparing the basic anatomy structures with focused echocardiography and cardiac magnetic resonance imaging. Twenty-four adult female African clawed frogs were randomly subjected to anatomic dissection (n = 4), echocardiography (n = 10), and cardiac magnetic resonance (n = 10). All anatomical features were confirmed and compared with echocardiography and cardiac magnetic resonance imaging. The main characteristics of the cardiovascular circulation in frogs are the following: Intact interatrial septum, with two separate atrio-ventricular valves, preventing atrial mixing of oxygenated and desaturated blood. Single spongiform ventricular cavity, non-conducive for homogeneous mixing. Single outlet with a valve-like mobile spiral structure, actively streaming into systemic and pulmonary arteries. Intact interatrial septum, spongiform ventricle, and valve-like spiral in the conus arteriosus are likely responsible for balanced systemic and pulmonary circulation in frogs, in spite of double-inlet and single-outlet ventricle.
Collapse
Affiliation(s)
- Antonio F Corno
- Children's Heart Institute, Memorial Hermann Children's Hospital, McGovern Medical School, University of Texas Health, 6431 Fannin Street, MSB 6.274, Houston, TX, 77030, USA.
| | - Zhen Zhou
- Medical Genetics, Department of Internal Medicine, McGovern Medical School, University of Texas Health, Houston, TX, 77030, USA
| | - Santosh C Uppu
- Children's Heart Institute, Memorial Hermann Children's Hospital, McGovern Medical School, University of Texas Health, 6431 Fannin Street, MSB 6.274, Houston, TX, 77030, USA
| | - Shuning Huang
- Department of Diagnostic and Interventional Imaging, McGovern Medical School, University of Texas Health, Houston, TX, 77030, USA
| | - Bruno Marino
- Department of Pediatrics, Obstetrics and Gynecology, University La Sapienza, 00161, Roma, Italy
| | - Dianna M Milewicz
- Medical Genetics, Department of Internal Medicine, McGovern Medical School, University of Texas Health, Houston, TX, 77030, USA
| | - Jorge D Salazar
- Children's Heart Institute, Memorial Hermann Children's Hospital, McGovern Medical School, University of Texas Health, 6431 Fannin Street, MSB 6.274, Houston, TX, 77030, USA
| |
Collapse
|
7
|
Ahmad Z, Jin LH, Penny DJ, Rusin CG, Peskin CS, Puelz C. Optimal Fenestration of the Fontan Circulation. Front Physiol 2022; 13:867995. [PMID: 35846014 PMCID: PMC9280082 DOI: 10.3389/fphys.2022.867995] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2022] [Accepted: 05/13/2022] [Indexed: 11/20/2022] Open
Abstract
In this paper, we develop a pulsatile compartmental model of the Fontan circulation and use it to explore the effects of a fenestration added to this physiology. A fenestration is a shunt between the systemic and pulmonary veins that is added either at the time of Fontan conversion or at a later time for the treatment of complications. This shunt increases cardiac output and decreases systemic venous pressure. However, these hemodynamic benefits are achieved at the expense of a decrease in the arterial oxygen saturation. The model developed in this paper incorporates fenestration size as a parameter and describes both blood flow and oxygen transport. It is calibrated to clinical data from Fontan patients, and we use it to study the impact of a fenestration on several hemodynamic variables, including systemic oxygen availability, effective oxygen availability, and systemic venous pressure. In certain scenarios corresponding to high-risk Fontan physiology, we demonstrate the existence of a range of fenestration sizes in which the systemic oxygen availability remains relatively constant while the systemic venous pressure decreases.
Collapse
Affiliation(s)
- Zan Ahmad
- Courant Institute of Mathematical Sciences, New York University, New York, NY, United States
| | - Lynn H. Jin
- Courant Institute of Mathematical Sciences, New York University, New York, NY, United States
- School of Physics, Georgia Institute of Technology, Atlanta, GA, United States
| | - Daniel J. Penny
- Department of Pediatrics, Section of Cardiology, Baylor College of Medicine and Texas Children’s Hospital, Houston, TX, United States
| | - Craig G. Rusin
- Department of Pediatrics, Section of Cardiology, Baylor College of Medicine and Texas Children’s Hospital, Houston, TX, United States
| | - Charles S. Peskin
- Courant Institute of Mathematical Sciences, New York University, New York, NY, United States
| | - Charles Puelz
- Courant Institute of Mathematical Sciences, New York University, New York, NY, United States
- Department of Pediatrics, Section of Cardiology, Baylor College of Medicine and Texas Children’s Hospital, Houston, TX, United States
| |
Collapse
|
8
|
Engineering Perspective on Cardiovascular Simulations of Fontan Hemodynamics: Where Do We Stand with a Look Towards Clinical Application. Cardiovasc Eng Technol 2021; 12:618-630. [PMID: 34114202 DOI: 10.1007/s13239-021-00541-y] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/20/2020] [Accepted: 04/30/2021] [Indexed: 01/02/2023]
Abstract
BACKGROUND Cardiovascular simulations for patients with single ventricles undergoing the Fontan procedure can assess patient-specific hemodynamics, explore surgical advances, and develop personalized strategies for surgery and patient care. These simulations have not yet been broadly accepted as a routine clinical tool owing to a number of limitations. Numerous approaches have been explored to seek innovative solutions for improving methodologies and eliminating these limitations. PURPOSE This article first reviews the current state of cardiovascular simulations of Fontan hemodynamics. Then, it will discuss the technical progress of Fontan simulations with the emphasis of its clinical impact, noting that substantial improvements have been made in the considerations of patient-specific anatomy, flow, and blood rheology. The article concludes with insights into potential future directions involving clinical validation, uncertainty quantification, and computational efficiency. The advancements in these aspects could promote the clinical usage of Fontan simulations, facilitating its integration into routine clinical practice.
Collapse
|
9
|
Dobutamine stress testing in patients with Fontan circulation augmented by biomechanical modeling. PLoS One 2020; 15:e0229015. [PMID: 32084180 PMCID: PMC7034893 DOI: 10.1371/journal.pone.0229015] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/01/2019] [Accepted: 01/28/2020] [Indexed: 02/02/2023] Open
Abstract
Understanding (patho)physiological phenomena and mechanisms of failure in patients with Fontan circulation-a surgically established circulation for patients born with a functionally single ventricle-remains challenging due to the complex hemodynamics and high inter-patient variations in anatomy and function. In this work, we present a biomechanical model of the heart and circulation to augment the diagnostic evaluation of Fontan patients with early-stage heart failure. The proposed framework employs a reduced-order model of heart coupled with a simplified circulation including venous return, creating a closed-loop system. We deploy this framework to augment the information from data obtained during combined cardiac catheterization and magnetic resonance exams (XMR), performed at rest and during dobutamine stress in 9 children with Fontan circulation and 2 biventricular controls. We demonstrate that our modeling framework enables patient-specific investigation of myocardial stiffness, contractility at rest, contractile reserve during stress and changes in vascular resistance. Hereby, the model allows to identify key factors underlying the pathophysiological response to stress in these patients. In addition, the rapid personalization of the model to patient data and fast simulation of cardiac cycles make our framework directly applicable in a clinical workflow. We conclude that the proposed modeling framework is a valuable addition to the current clinical diagnostic XMR exam that helps to explain patient-specific stress hemodynamics and can identify potential mechanisms of failure in patients with Fontan circulation.
Collapse
|
10
|
Cartoski MJ, Nikolov PP, Prakosa A, Boyle PM, Spevak PJ, Trayanova NA. Computational Identification of Ventricular Arrhythmia Risk in Pediatric Myocarditis. Pediatr Cardiol 2019; 40:857-864. [PMID: 30840104 PMCID: PMC6451890 DOI: 10.1007/s00246-019-02082-7] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/21/2018] [Accepted: 02/27/2019] [Indexed: 12/11/2022]
Abstract
Children with myocarditis have increased risk of ventricular tachycardia (VT) due to myocardial inflammation and remodeling. There is currently no accepted method for VT risk stratification in this population. We hypothesized that personalized models developed from cardiac late gadolinium enhancement magnetic resonance imaging (LGE-MRI) could determine VT risk in patients with myocarditis using a previously-validated protocol. Personalized three-dimensional computational cardiac models were reconstructed from LGE-MRI scans of 12 patients diagnosed with myocarditis. Four patients with clinical VT and eight patients without VT were included in this retrospective analysis. In each model, we incorporated a personalized spatial distribution of fibrosis and myocardial fiber orientations. Then, VT inducibility was assessed in each model by pacing rapidly from 26 sites distributed throughout both ventricles. Sustained reentrant VT was induced from multiple pacing sites in all patients with clinical VT. In the eight patients without clinical VT, we were unable to induce sustained reentry in our simulations using rapid ventricular pacing. Application of our non-invasive approach in children with myocarditis has the potential to correctly identify those at risk for developing VT.
Collapse
Affiliation(s)
- Mark J Cartoski
- Divison of Pediatric Cardiology, Department of Pediatrics, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
| | - Plamen P Nikolov
- Institute for Computational Medicine and Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Adityo Prakosa
- Institute for Computational Medicine and Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Patrick M Boyle
- Institute for Computational Medicine and Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Philip J Spevak
- Divison of Pediatric Cardiology, Department of Pediatrics, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Natalia A Trayanova
- Institute for Computational Medicine and Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA
- Division of Cardiology, Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| |
Collapse
|
11
|
Marquis AD, Arnold A, Dean-Bernhoft C, Carlson BE, Olufsen MS. Practical identifiability and uncertainty quantification of a pulsatile cardiovascular model. Math Biosci 2018; 304:9-24. [PMID: 30017910 DOI: 10.1016/j.mbs.2018.07.001] [Citation(s) in RCA: 29] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2017] [Revised: 05/01/2018] [Accepted: 07/02/2018] [Indexed: 11/17/2022]
Abstract
Mathematical models are essential tools to study how the cardiovascular system maintains homeostasis. The utility of such models is limited by the accuracy of their predictions, which can be determined by uncertainty quantification (UQ). A challenge associated with the use of UQ is that many published methods assume that the underlying model is identifiable (e.g. that a one-to-one mapping exists from the parameter space to the model output). In this study we present a novel workflow to calibrate a lumped-parameter model to left ventricular pressure and volume time series data. Key steps include using (1) literature and available data to determine nominal parameter values; (2) sensitivity analysis and subset selection to determine a set of identifiable parameters; (3) optimization to find a point estimate for identifiable parameters; and (4) frequentist and Bayesian UQ calculations to assess the predictive capability of the model. Our results show that it is possible to determine 5 identifiable model parameters that can be estimated to our experimental data from three rats, and that computed UQ intervals capture the measurement and model error.
Collapse
Affiliation(s)
- Andrew D Marquis
- University of Michigan, Ann Arbor, MI, USA; NC State University, Raleigh, NC, USA
| | - Andrea Arnold
- NC State University, Raleigh, NC, USA; Worcester Polytechnic Institute, Worcester, MA, USA
| | | | | | | |
Collapse
|
12
|
Wang T, Liang F, Zhou Z, Qi X. Global sensitivity analysis of hepatic venous pressure gradient (HVPG) measurement with a stochastic computational model of the hepatic circulation. Comput Biol Med 2018; 97:124-136. [DOI: 10.1016/j.compbiomed.2018.04.017] [Citation(s) in RCA: 22] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2018] [Revised: 04/14/2018] [Accepted: 04/21/2018] [Indexed: 02/07/2023]
|