Dataset Information

Diagnosis of pulmonary hypertension from magnetic resonance imaging-based computational models and decision tree analysis.

ABSTRACT: Accurately identifying patients with pulmonary hypertension (PH) using noninvasive methods is challenging, and right heart catheterization (RHC) is the gold standard. Magnetic resonance imaging (MRI) has been proposed as an alternative to echocardiography and RHC in the assessment of cardiac function and pulmonary hemodynamics in patients with suspected PH. The aim of this study was to assess whether machine learning using computational modeling techniques and image-based metrics of PH can improve the diagnostic accuracy of MRI in PH. Seventy-two patients with suspected PH attending a referral center underwent RHC and MRI within 48 hours. Fifty-seven patients were diagnosed with PH, and 15 had no PH. A number of functional and structural cardiac and cardiovascular markers derived from 2 mathematical models and also solely from MRI of the main pulmonary artery and heart were integrated into a classification algorithm to investigate the diagnostic utility of the combination of the individual markers. A physiological marker based on the quantification of wave reflection in the pulmonary artery was shown to perform best individually, but optimal diagnostic performance was found by the combination of several image-based markers. Classifier results, validated using leave-one-out cross validation, demonstrated that combining computation-derived metrics reflecting hemodynamic changes in the pulmonary vasculature with measurement of right ventricular morphology and function, in a decision support algorithm, provides a method to noninvasively diagnose PH with high accuracy (92%). The high diagnostic accuracy of these MRI-based model parameters may reduce the need for RHC in patients with suspected PH.

SUBMITTER: Lungu A

PROVIDER: S-EPMC4869922 | biostudies-other | 2016 Jun

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

Project description:Rationale: Pulmonary arterial hypertension (PAH) is a life-shortening condition. The European Society of Cardiology and European Respiratory Society and the REVEAL (North American Registry to Evaluate Early and Long-Term PAH Disease Management) risk score calculator (REVEAL 2.0) identify thresholds to predict 1-year mortality.Objectives: This study evaluates whether cardiac magnetic resonance imaging (MRI) thresholds can be identified and used to aid risk stratification and facilitate decision-making.Methods: Consecutive patients with PAH (n = 438) undergoing cardiac MRI were identified from the ASPIRE (Assessing the Spectrum of Pulmonary Hypertension Identified at a Referral Center) MRI database. Thresholds were identified from a discovery cohort and evaluated in a test cohort.Measurements and Main Results: A percentage-predicted right ventricular end-systolic volume index threshold of 227% or a left ventricular end-diastolic volume index of 58 ml/m2 identified patients at low (<5%) and high (>10%) risk of 1-year mortality. These metrics respectively identified 63% and 34% of patients as low risk. Right ventricular ejection fraction >54%, 37-54%, and <37% identified 21%, 43%, and 36% of patients at low, intermediate, and high risk, respectively, of 1-year mortality. At follow-up cardiac MRI, patients who improved to or were maintained in a low-risk group had a 1-year mortality <5%. Percentage-predicted right ventricular end-systolic volume index independently predicted outcome and, when used in conjunction with the REVEAL 2.0 risk score calculator or a modified French Pulmonary Hypertension Registry approach, improved risk stratification for 1-year mortality.Conclusions: Cardiac MRI can be used to risk stratify patients with PAH using a threshold approach. Percentage-predicted right ventricular end-systolic volume index can identify a high percentage of patients at low-risk of 1-year mortality and, when used in conjunction with current risk stratification approaches, can improve risk stratification. This study supports further evaluation of cardiac MRI in risk stratification in PAH.

Project description:BackgroundBronchopulmonary dysplasia (BPD) associated with pulmonary hypertension (PH) is a significant source of morbidity and mortality in premature infants. Recent advances have allowed the use of cardiovascular magnetic resonance (CMR) in the assessment of respiratory and cardiac disease in infants with BPD. In adults and older pediatric patients, decreased CMR interventricular septal curvature correlates with increased mean pulmonary artery pressure and pulmonary vascular resistance. The current study sought to determine the relationship of CMR derived septal curvature in neonates with BPD and BPD-PH with a need for PH therapy.MethodsForty moderate or severe BPD and 12 mild BPD or control infants were imaged without contrast between 38 and 47 weeks post-menstrual age on a neonatal-sized, neonatal intensive care unit-sited 1.5 T CMR scanner. CMR indices including eccentricity index (CMR-EI) and septal curvature were measured and compared to BPD severity and clinical outcomes including hospital length of stay (LOS), duration of respiratory support, respiratory support level at discharge and PH therapy.ResultsCMR-EI was directly associated and septal curvature was inversely associated with BPD severity. In a univariate analysis, CMR-EI and septal curvature were associated with increased hospital LOS, duration of respiratory support, respiratory support at hospital discharge, and need for PH therapy. In multivariable analysis CMR-EI was associated with hospital LOS and duration of respiratory support and septal curvature was associated with respiratory support at hospital discharge. Septal curvature was the only clinical or CMR variable associated with need for PH therapy (R2 = 0.66, p = 0.0014) in multivariable analysis demonstrating improved discrimination beyond CMR-EI.ConclusionsCMR derived septal curvature correlates significantly with clinical outcomes including hospital LOS, duration of respiratory support, respiratory support level at hospital discharge, and PH therapy in neonates with BPD and BPD-PH. Further, CMR derived septal curvature demonstrated improved discrimination of need for PH therapy and respiratory support at discharge compared to clinical variables and other CMR indices, supporting septal curvature as a non-invasive marker of PH in this population with potential to guide management strategies.

Project description:PurposeThis study aimed to develop machine learning models for the diagnosis of Parkinson's disease (PD) using multiple structural magnetic resonance imaging (MRI) features and validate their performance.MethodsBrain structural MRI scans of 60 patients with PD and 56 normal controls (NCs) were enrolled as development dataset and 69 patients with PD and 71 NCs from Parkinson's Progression Markers Initiative (PPMI) dataset as independent test dataset. First, multiple structural MRI features were extracted from cerebellar, subcortical, and cortical regions of the brain. Then, the Pearson's correlation test and least absolute shrinkage and selection operator (LASSO) regression were used to select the most discriminating features. Finally, using logistic regression (LR) classifier with the 5-fold cross-validation scheme in the development dataset, the cerebellar, subcortical, cortical, and a combined model based on all features were constructed separately. The diagnostic performance and clinical net benefit of each model were evaluated with the receiver operating characteristic (ROC) analysis and the decision curve analysis (DCA) in both datasets.ResultsAfter feature selection, 5 cerebellar (absolute value of left lobule crus II cortical thickness (CT) and right lobule IV volume, relative value of right lobule VIIIA CT and lobule VI/VIIIA gray matter volume), 3 subcortical (asymmetry index of caudate volume, relative value of left caudate volume, and absolute value of right lateral ventricle), and 4 cortical features (local gyrification index of right anterior circular insular sulcus and anterior agranular insula complex, local fractal dimension of right middle insular area, and CT of left supplementary and cingulate eye field) were selected as the most distinguishing features. The area under the curve (AUC) values of the cerebellar, subcortical, cortical, and combined models were 0.679, 0.555, 0.767, and 0.781, respectively, for the development dataset and 0.646, 0.632, 0.690, and 0.756, respectively, for the independent test dataset, respectively. The combined model showed higher performance than the other models (Delong's test, all p-values < 0.05). All models showed good calibration, and the DCA demonstrated that the combined model has a higher net benefit than other models.ConclusionThe combined model showed favorable diagnostic performance and clinical net benefit and had the potential to be used as a non-invasive method for the diagnosis of PD.

Dataset Information

Diagnosis of pulmonary hypertension from magnetic resonance imaging-based computational models and decision tree analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets