Metrics of High Cofluctuation and Entropy to Describe Control of Cardiac Function in the Stellate Ganglion

Neural control of the heart involves dynamic adaptation of mechanical and electrical indices to meet blood flow demands. The control system receives centrally-derived inputs to coordinate cardiac function on a beat-by-beat basis, producing 'functional' outputs such as the blood pressure waveform. Bilateral stellate ganglia (SG) are responsible for integration of multiple inputs and efferent cardiopulmonary sympathetic neurotransmission. In this work, we investigate network processing of cardiopulmonary transduction by SG neuronal populations in porcine with chronic pacing-induced heart failure and control subjects. We derive novel metrics to describe control of cardiac function by the SG during baseline and stressed states from in vivo extracellular microelectrode recordings. Network-level spatiotemporal dynamic signatures are found by quantifying state changes in coactive neuronal populations (i.e., cofluctuations). Differences in 'neural specificity' of SG network activity to specific phases of the cardiac cycle are studied using entropy estimation. Fundamental differences in information processing and cardiac control are evident in chronic heart failure where the SG exhibits: i) short-lived, high amplitude cofluctuations in baseline states, ii) greater variation in neural specificity to cardiac cycles, iii) limited sympathetic reserve during stressed states, and iv) neural network activity and cardiac control linkage that depends on disease state and cofluctuation magnitude. These findings indicate that spatiotemporal dynamics of stellate ganglion neuronal populations are altered in heart failure, and lay the groundwork for understanding dysfunction neuronal signaling reflective of cardiac sympathoexcitation.

Estimation of Stroke Volume Variance from Arterial Blood Pressure: Using a 1-D Convolutional Neural Network

Background: We aimed to create a novel model using a deep learning method to estimate stroke volume variation (SVV), a widely used predictor of fluid responsiveness, from arterial blood pressure waveform (ABPW). Methods: In total, 557 patients and 8,512,564 SVV datasets were collected and were divided into three groups: training, validation, and test. Data was composed of 10 s of ABPW and corresponding SVV data recorded every 2 s. We built a convolutional neural network (CNN) model to estimate SVV from the ABPW with pre-existing commercialized model (EV1000) as a reference. We applied pre-processing, multichannel, and dimension reduction to improve the CNN model with diversified inputs. Results: Our CNN model showed an acceptable performance with sample data (r = 0.91, MSE = 6.92). Diversification of inputs, such as normalization, frequency, and slope of ABPW significantly improved the model correlation (r = 0.95), lowered mean squared error (MSE = 2.13), and resulted in a high concordance rate (96.26%) with the SVV from the commercialized model. Conclusions: We developed a new CNN deep-learning model to estimate SVV. Our CNN model seems to be a viable alternative when the necessary medical device is not available, thereby allowing a wider range of application and resulting in optimal patient management.

Classification of patients with Alzheimer’s disease using the arterial pulse spectrum and a multilayer-perceptron analysis

Cerebrovascular atherosclerosis has been identified as a prominent pathological feature of Alzheimer’s disease (AD); the link between vessel pathology and AD risk may also extend to extracranial arteries. This study aimed to determine the effectiveness of using arterial pulse-wave measurements and multilayer perceptron (MLP) analysis in distinguishing between AD and control subjects. Radial blood pressure waveform (BPW) and finger photoplethysmography signals were measured noninvasively for 3 min in 87 AD patients and 74 control subjects. The 5-layer MLP algorithm employed evaluated the following 40 harmonic pulse indices: amplitude proportion and its coefficient of variation, and phase angle and its standard deviation. The BPW indices differed significantly between the AD patients (6247 pulses) and control subjects (6626 pulses). Significant intergroup differences were found between mild, moderate, and severe AD (defined by Mini-Mental-State-Examination scores). The hold-out test results indicated an accuracy of 82.86%, a specificity of 92.31%, and a 0.83 AUC of ROC curve when using the MLP-based classification between AD and Control. The identified differences can be partly attributed to AD-induced changes in vascular elastic properties. The present findings may be meaningful in facilitating the development of a noninvasive, rapid, inexpensive, and objective method for detecting and monitoring the AD status.

An Estimation Method of Continuous Non-Invasive Arterial Blood Pressure Waveform Using Photoplethysmography: A U-Net Architecture-Based Approach

Blood pressure (BP) monitoring has significant importance in the treatment of hypertension and different cardiovascular health diseases. As photoplethysmogram (PPG) signals can be recorded non-invasively, research has been highly conducted to measure BP using PPG recently. In this paper, we propose a U-net deep learning architecture that uses fingertip PPG signal as input to estimate arterial BP (ABP) waveform non-invasively. From this waveform, we have also measured systolic BP (SBP), diastolic BP (DBP), and mean arterial pressure (MAP). The proposed method was evaluated on a subset of 100 subjects from two publicly available databases: MIMIC and MIMIC-III. The predicted ABP waveforms correlated highly with the reference waveforms and we have obtained an average Pearson’s correlation coefficient of 0.993. The mean absolute error is 3.68 ± 4.42 mmHg for SBP, 1.97 ± 2.92 mmHg for DBP, and 2.17 ± 3.06 mmHg for MAP which satisfy the requirements of the Association for the Advancement of Medical Instrumentation (AAMI) standard and obtain grade A according to the British Hypertension Society (BHS) standard. The results show that the proposed method is an efficient process to estimate ABP waveform directly using fingertip PPG.

Abstract P187: Testing Of A Long-term Implantable Blood Pressure Waveform Monitoring System

The long-term Implantable Blood Pressure Waveform Monitoring System consists of a miniature applanation tonometer sensor head connected to a battery powered electronics module via a flexible lead. The BP Sensor continuously monitors the arterial BP waveform with data transmitted to a smart phone for real-time data analysis and display. Key data can be transmitted via the cellular network to a central monitoring station for advanced analysis by a computer and clinician. The BP Sensor has been evaluated for safety, accuracy, stability, and reliability for up to 10 months surrounding the external carotid arteries of large canine. Serial ultrasound studies of the artery-sensor interface shows normal artery shape, diameter, and blood flow velocity. BP Sensor performance remained stable for ~ 60 days between calibrations and correlated with reference BP waveform measurement (± 2.5 mm Hg). The BP Sensor head has a novel design that securely couples the diaphragm to the outside wall of a peripheral artery in optimal alignment with minimal flattening (~ 15 %). The Figure below shows the BP Sensor output signal’s detailed BP waveform four months after implantation. The waveform shows subtle and consistent fluctuations in the peaks and valleys of the BP waveform due to positive pressure mechanical ventilation with a respiratory rate of 14 breaths per minute. This is a significant observation which indicates that the BP Sensor has very good sensitivity (± 1 mm Hg) in the normal hemodynamic range (reference BP ~100/60). The real-time and recorded BP Sensor waveform data will be used to make a diagnosis and adjust medication in a more timely and effective manor, leading to improved clinical outcomes.