杉本 晃一

BACKGROUND: Left ventricular enlargement (LVE) is a common manifestation of cardiac remodeling that is closely associated with cardiac dysfunction, heart failure (HF), and arrhythmias. This study aimed to propose a machine learning (ML)-based strategy to identify LVE in HF patients by means of pulse wave signals. METHOD: We constructed two high-quality pulse wave datasets comprising a non-LVE group and an LVE group based on the 264 HF patients. Fourier series calculations were employed to determine if significant frequency differences existed between the two datasets, thereby ensuring their validity. Then, the ML-based identification was undertaken by means of classification and regression models: a weighted random forest model was employed for binary classification of the datasets, and a densely connected convolutional network was utilized to directly estimate the left ventricular diastolic diameter index (LVDdI) through regression. Finally, the accuracy of the two models was validated by comparing their results with clinical measurements, using accuracy and the area under the receiver operating characteristic curve (AUC-ROC) to assess their capability for identifying LVE patients. RESULTS: The classification model exhibited superior performance with an accuracy of 0.91 and an AUC-ROC of 0.93. The regression model achieved an accuracy of 0.88 and an AUC-ROC of 0.89, indicating that both models can quickly and accurately identify LVE in HF patients. CONCLUSION: The proposed ML methods are verified to achieve effective classification and regression with good performance for identifying LVE in HF patients based on pulse wave signals. This study thus demonstrates the feasibility and potential of the ML-based strategy for clinical practice while offering an effective and robust tool for diagnosing and intervening ventricular remodeling.

Abstract Objective. This study aims to accurately identify the effects of respiration on the hemodynamics of the human cardiovascular system, especially the cerebral circulation. Approach: we have developed a machine learning (ML)-integrated zero–one-dimensional (0–1D) multiscale hemodynamic model combining a lumped-parameter 0D model for the peripheral vascular bed and a one-dimensional (1D) hemodynamic model for the vascular network. In vivo measurement data of 21 patients were retrieved and partitioned into 8000 data samples in which respiratory fluctuation (RF) of intrathoracic pressure (ITP) was fitted by the Fourier series. ML-based classification and regression algorithms were used to examine the influencing factors and variation trends of the key parameters in the ITP equations and the mean arterial pressure. These parameters were employed as the initial conditions of the 0–1D model to calculate the radial artery blood pressure and the vertebral artery blood flow volume (VAFV). Main results: during stable spontaneous respiration, the VAFV can be augmented at the inhalation endpoints by approximately 0.1 ml s⁻¹ for infants and 0.5 ml s⁻¹ for adolescents or adults, compared to those without RF effects. It is verified that deep respiration can further increase the ranges up to 0.25 ml s⁻¹ and 1 ml s⁻¹, respectively. Significance. This study reveals that reasonable adjustment of respiratory patterns, i.e. in deep breathing, enhances the VAFV and promotes cerebral circulation.

Three-dimensional computational fluid dynamics (CFD) simulations were performed in the anastomotic region of the Fontan route between the venae cava and pulmonary arteries to investigate the risk of thrombosis due to blood stasis in the Fontan circulation. The finite volume method based on the time-averaged continuity and Navier–Stokes equations combined with the k-ω SST turbulent model was used in the CFD simulations. Low shear rate (SR) and SR on the wall (WSR) of <10 s−1 were used as markers to assess blood stasis as a cause of blood coagulation. Simulated blood flow velocity and both SR and WSR were reduced in the right atrium (RA) as the cavity of a flow channel in the atriopulmonary connection (APC) Fontan model, whereas the values increased in the total cavopulmonary connection (TCPC) Fontan model, which has no cavity. The volume of SR <10 s−1 and wall surface area of WSR <10 s−1 were, respectively, 4.6–261.8 cm3 and 1.2–38.3 cm2 in the APC Fontan model, and 0.1–0.3 cm3 and 0.1–0.6 cm2 in the TCPC Fontan model. The SR and WSR increased in the APC model with a normal-sized RA and the TCPC model as the flow rate of blood from the inferior vena cava increased with exercise; however, the SR and WSR in the RA decreased in the APC model with a dilated RA owing to the development of a recirculating flow. These findings suggest that the APC Fontan has a higher risk of thrombosis due to blood stasis than the TCPC Fontan and a higher RA dilation is associated with a higher risk of thrombosis from a fluid mechanics perspective.

Abstract Background: Although serum lactate levels are widely accepted markers of haemodynamic instability, an alternative method to evaluate haemodynamic stability/instability continuously and non-invasively may assist in improving the standard of patient care. We hypothesise that blood lactate in paediatric ICU patients can be predicted using machine learning applied to arterial waveforms and perioperative characteristics. Methods: Forty-eight post-operative children, median age 4 months (2.9–11.8 interquartile range), mean baseline heart rate of 131 beats per minute (range 33–197), mean lactate level at admission of 22.3 mg/dL (range 6.3–71.1), were included. Morphological arterial waveform characteristics were acquired and analysed. Predicting lactate levels was accomplished using regression-based supervised learning algorithms, evaluated with hold-out cross-validation, including, basing prediction on the currently acquired physiological measurements along with those acquired at admission, as well as adding the most recent lactate measurement and the time since that measurement as prediction parameters. Algorithms were assessed with mean absolute error, the average of the absolute differences between actual and predicted lactate concentrations. Low values represent superior model performance. Results: The best performing algorithm was the tuned random forest, which yielded a mean absolute error of 3.38 mg/dL when predicting blood lactate with updated ground truth from the most recent blood draw. Conclusions: The random forest is capable of predicting serum lactate levels by analysing perioperative variables, including the arterial pressure waveform. Thus, machine learning can predict patient blood lactate levels, a proxy for haemodynamic instability, non-invasively, continuously and with accuracy that may demonstrate clinical utility.

To explore hemodynamic interaction between the human respiratory system (RS) and cardiovascular system (CVS), here we propose an integrated computational model to predict the CVS hemodynamics with consideration of the respiratory fluctuation (RF). A submodule of the intrathoracic pressure (ITP) adjustment is developed and incorporated in a 0-1D multiscale hemodynamic model of the CVS specified for infant, adolescent, and adult individuals. The model is verified to enable reasonable estimation of the blood pressure waveforms accounting for the RF-induced pressure fluctuations in comparison with clinical data. The results show that the negative ITP caused by respiration increases the blood flow rates in superior and inferior vena cavae; the deep breathing improves the venous return in adolescents but has less influence on infants. It is found that a marked reduction in ITP under pathological conditions can excessively increase the flow rates in cavae independent of the individual ages, which may cause the hemodynamic instability and hence increase the risk of heart failure. Our results indicate that the present 0-1D multiscale CVS model incorporated with the RF effect is capable of providing a useful and effective tool to explore the physiological and pathological mechanisms in association with cardiopulmonary interactions and their clinical applications.