Dataset Information

Deep Neural Network to Accurately Predict Left Ventricular Systolic Function Under Mechanical Assistance

ABSTRACT: Characterizing left ventricle (LV) systolic function in the presence of an LV assist device (LVAD) is extremely challenging. We developed a framework comprising a deep neural network (DNN) and a 0D model of the cardiovascular system to predict parameters of LV systolic function. DNN input data were systemic and pulmonary arterial pressure signals, and rotation speeds of the device. Output data were parameters of LV systolic function, including end-systolic maximal elastance (Emax,lv), a variable essential for adequate hemodynamic assessment of the LV. A 0D model of the cardiovascular system, including a wide range of LVAD settings and incorporating the whole spectrum of heart failure, was used to generate data for the training procedure of the DNN. The DNN predicted Emax,lv with a mean relative error of 10.1%, and all other parameters of LV function with a mean relative error of <13%. The framework was then able to retrieve a number of LV physiological variables (i.e., pressures, volumes, and ejection fraction) with a mean relative error of <5%. Our method provides an innovative tool to assess LV hemodynamics under device assistance, which could be helpful for a better understanding of LV-LVAD interactions, and for therapeutic optimization.

SUBMITTER: Bonnemain J

PROVIDER: S-EPMC8576185 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundDespite advancements in pharmacological and device-based treatment, heart failure (HF) continues to impose an enormous burden for health care system worldwide. Decompensation of HF is one of the main causes of hospitalization, therefore the identification of patients with the highest risk of such complication is still of great clinical importance. The prognostic significance and utility of global longitudinal strain (GLS) has been previously studied in patients with the broad spectrum of cardiovascular diseases in various endpoints, however its role in assessing the risk of hospitalization due to HF exacerbation of optimally treated outpatients has not been fully explored. Therefore, the aim of the study was to verify whether the GLS of the left ventricle (LV) derived by 2D speckle tracking echocardiography has, independently of other well-known clinical parameters, an additional impact on the risk of HF decompensation in stable patients with LV systolic dysfunction of ischemic origin.MethodsIn 193 clinically stable HF outpatients with LV ejection fraction (LVEF) ≤ 50%, GLS, additionally to other clinical parameters, was analyzed. During 34 (14-71) months of follow-up, 58 patients were hospitalized due to HF decompensation (EVENT).ResultsEVENT was significantly associated with age, QRS width, NYHA functional class, left atrium diameter, LV systolic and diastolic volume, LVEF, hemoglobin, brain natriuretic peptide, diuretic treatment, absence of beta-blockers, impaired renal function and history of diabetes in univariate Cox analyzes. GLS with pre-specified cut-off value of -9.4% was also significantly associated with the EVENT (HR 15.16; 95% CI 1.81-126.91). After adjusting for above-mentioned parameters GLS was still a significant predictor of hospitalization due to HF decompensation.ConclusionsGLS measurement can provide incremental information on the risk of HF decompensation in stable outpatients with LV systolic dysfunction of ischemic origin.

Dataset Information

Deep Neural Network to Accurately Predict Left Ventricular Systolic Function Under Mechanical Assistance

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets