A Novel Classification Technique of Arteriovenous Fistula Stenosis Evaluation Using Bilateral PPG Analysis

Classification and regression of stenosis using an in-vitro pulse wave data set: Dependence on heart rate, waveform and location

BACKGROUND

Data-based approaches promise to use the information in cardiovascular signals to diagnose cardiovascular diseases. Considerable effort has been undertaken in the field of pulse-wave analysis to harness this information. However, the inverse problem, inferring arterial properties from waveform measurements, is not well understood today. Consequently, uncertainties within the estimation hinder the diagnostic application of such methods.

METHOD

This work contributes a publicly available data set measured at an in-vitro cardiovascular simulator, focusing on a set of input conditions (heart rate, waveform) and stenosis locations. Furthermore, a first attempt is undertaken to perform classification and regression on this data set using standard machine learning methods on features extracted from four peripheral pressure signals.

RESULTS

The locations of six different stenoses could be distinguished at high accuracy of 93%, where transfer function-based features outperformed features based solely on signal shape in almost all cases. Furthermore, regression on the stenosis position could be performed with a root mean square error of 2.4 cm along a 20 cm section of the arterial system using a shallow neural network. However, the performance difference between shape and transfer function features was not clear for this task.

CONCLUSION

The data set contains 800 measurements and allows investigating the influence of different heart boundary conditions, such as heart rate and waveform shape, on classification and regression tasks. Extracting features that minimise this influence is a promising way of improving the performance of these tasks.

Measurement of Tremor on Arteriovenous Fistulas with a Flexible Capacitive Sensor

Arteriovenous fistula (AVF) is a widely used vascular access for hemodialysis in clinical. It is a great challenge to monitoring the status of AVF in daily life due to acute AVF stenosis may occur on unnoticeable occasions, such as sleeping. Inspiring tremor is almost always accompanied by a healthy AVF, which can be adopted as an essential physiological sign for AVF monitoring. Hence, a fistula tremor measurement system based on a flexible capacitive pressure sensor is designed in this study. The sensor consists of polydimethylsiloxane(PDMS) dielectric layers, electrode layers, ground layers, and shielding layers. The PDMS layers are fabricated as cross superposition transverse microstructure film to enhance dielectric constant and sensitivity of the sensor. The isolation shielding layers and ground layers guarantee the sensing chain is noise-free. A microcontroller embedded AD7746 measurement circuit is designed for signal acquisition. We test our prototype on the wrists of healthy volunteers and AVF on dialysis patients separately. The pulse signals and AVF tremor signals are clear and distinguishable. The sensor and measurement system have excellent potential in wearable AVF monitoring.

MicroRNA-375-3p is implicated in carotid artery stenosis by promoting the cell proliferation and migration of vascular smooth muscle cells

Background

Atherosclerosis is the main cause of carotid artery stenosis (CAS) which mostly occurs in the elderly. In this paper, the expression level of miR-375-3p in asymptomatic CAS patients and its diagnostic value for asymptomatic CAS were investigated, and the effects of miR-375-3p on the cell proliferation and migration of vascular smooth muscle cells (VSMCs) was further explored.

Methods

98 healthy subjects and 101 asymptomatic CAS patients were participated in this study. qRT-PCR was used to measure the expression level of serum miR-375-3p, and the ROC curve was established to evaluate the predictive value of miR-375-3p for asymptomatic CAS. After transfection with miR-375-3p mimic or inhibitor in vitro, cell proliferation and migration were detected by CCK-8 assay, colony formation assay, and Transwell assay, respectively. The levels of TNF-α, IL-1β, IL-6 were detected by ELISA. Western blot was used to detect the protein expression of XIAP. Finally, luciferase reporter gene assay was applied to assess the interaction of miR-375-3p with target genes.

Results

The expression level of serum miR-375-3p in asymptomatic CAS patients was significantly higher than that in healthy controls, and the AUC value of ROC curve was 0.888. The sensitivity and specificity were 80.2 and 86.7%, respectively, indicating that miR-375-3p had high diagnostic value for asymptomatic CAS. In vitro cell experiments showed that up-regulation of miR-375-3p significantly promoted the proliferation and migration of VSMCs, and also promoted the generation of inflammatory factors and phenotypic transformation of VSMCs. Luciferase reporter gene assay confirmed that XIAP was a target gene of miR-375-3p and was negatively regulated by miR-375-3p.

Conclusions

In this study, miR-375-3p may have a clinical diagnostic value for asymptomatic CAS patients which need further validation. Increased miR-375-3p levels in CAS may be associated with increased proliferation and migration of VSMCs via downregulation of the apoptosis inducing gene XIAP.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12872-021-02326-6.

Arteriovenous Fistula Flow Dysfunction Surveillance: Early Detection Using Pulse Radar Sensor and Machine Learning Classification

Vascular Access (VA) is often referred to as the “Achilles heel” for a Hemodialysis (HD)-dependent patient. Both the patent and sufficient VA provide adequacy for performing dialysis and reducing dialysis-related complications, while on the contrary, insufficient VA is the main reason for recurrent hospitalizations, high morbidity, and high mortality in HD patients. A non-invasive Vascular Wall Motion (VWM) monitoring system, made up of a pulse radar sensor and Support Vector Machine (SVM) classification algorithm, has been developed to detect access flow dysfunction in Arteriovenous Fistula (AVF). The harmonic ratios derived from the Fast Fourier Transform (FFT) spectrum-based signal processing technique were employed as the input features for the SVM classifier. The result of a pilot clinical trial showed that a more accurate prediction of AVF flow dysfunction could be achieved by the VWM monitor as compared with the Ultrasound Dilution (UD) flow monitor. Receiver Operating Characteristic (ROC) curve analysis showed that the SVM classification algorithm achieved a detection specificity of 100% at detection thresholds in the range from 500 to 750 mL/min and a maximum sensitivity of 95.2% at a detection threshold of 750 mL/min.

The prototype device for non-invasive diagnosis of arteriovenous fistula condition using machine learning methods

Pattern recognition and automatic decision support methods provide significant advantages in the area of health protection. The aim of this work is to develop a low-cost tool for monitoring arteriovenous fistula (AVF) with the use of phono-angiography method. This article presents a developed and diagnostic device that implements classification algorithms to identify 38 patients with end stage renal disease, chronically hemodialysed using an AVF, at risk of vascular access stenosis. We report on the design, fabrication, and preliminary testing of a prototype device for non-invasive diagnosis which is very important for hemodialysed patients. The system includes three sub-modules: AVF signal acquisition, information processing and classification and a unit for presenting results. This is a non-invasive and inexpensive procedure for evaluating the sound pattern of bruit produced by AVF. With a special kind of head which has a greater sensitivity than conventional stethoscope, a sound signal from fistula was recorded. The proces of signal acquisition was performed by a dedicated software, written specifically for the purpose of our study. From the obtained phono-angiogram, 23 features were isolated for vectors used in a decision-making algorithm, including 6 features based on the waveform of time domain, and 17 features based on the frequency spectrum. Final definition of the feature vector composition was obtained by using several selection methods: the feature-class correlation, forward search, Principal Component Analysis and Joined-Pairs method. The supervised machine learning technique was then applied to develop the best classification model.

Machine learning-based operation skills assessment with vascular difficulty index for vascular intervention surgery

An accurate assessment of surgical operation skills is essential for improving the vascular intervention surgical outcome and the performance of endovascular surgery robots. In existing studies, subjective and objective assessments of surgical operation skills use a variety of indicators, such as the operation speed and operation smoothness. However, the vascular conditions of particular patients have not been considered in the assessment, leading to deviations in the evaluation. Therefore, in this paper, an operation skills assessment method including the vascular difficulty level index for catheter insertion at the aortic arch in endovascular surgery is proposed. First, the model describing the difficulty of the vascular anatomical structure is established with characteristics of different aortic arch branches based on machine learning. Afterwards, the vascular difficulty level is set as an objective index combined with operating characteristics extracted from the operations performed by surgeons to evaluate the surgical operation skills at the aortic arch using machine learning. The accuracy of the assessment improves from 86.67 to 96.67% after inclusion of the vascular difficulty as an evaluation indicator to more objectively and accurately evaluate skills. The method described in this paper can be adopted to train novice surgeons in endovascular surgery, and for studies of vascular interventional surgery robots. Graphical abstract Operation skill assessment with vascular difficulty for vascular interventional surgery.

Machine Learning Classification for Assessing the Degree of Stenosis and Blood Flow Volume at Arteriovenous Fistulas of Hemodialysis Patients Using a New Photoplethysmography Sensor Device

The classifier of support vector machine (SVM) learning for assessing the quality of arteriovenous fistulae (AVFs) in hemodialysis (HD) patients using a new photoplethysmography (PPG) sensor device is presented in this work. In clinical practice, there are two important indices for assessing the quality of AVF: the blood flow volume (BFV) and the degree of stenosis (DOS). In hospitals, the BFV and DOS of AVFs are nowadays assessed using an ultrasound Doppler machine, which is bulky, expensive, hard to use, and time consuming. In this study, a newly-developed PPG sensor device was utilized to provide patients and doctors with an inexpensive and small-sized solution for ubiquitous AVF assessment. The readout in this sensor was custom-designed to increase the signal-to-noise ratio (SNR) and reduce the environment interference via maximizing successfully the full dynamic range of measured PPG entering an analog-digital converter (ADC) and effective filtering techniques. With quality PPG measurements obtained, machine learning classifiers including SVM were adopted to assess AVF quality, where the input features are determined based on optical Beer-Lambert's law and hemodynamic model, to ensure all the necessary features are considered. Finally, the clinical experiment results showed that the proposed PPG sensor device successfully achieved an accuracy of 87.84% based on SVM analysis in assessing DOS at AVF, while an accuracy of 88.61% was achieved for assessing BFV at AVF.

Levenberg-Marquardt Neural Network Algorithm for Degree of Arteriovenous Fistula Stenosis Classification Using a Dual Optical Photoplethysmography Sensor

This paper proposes a noninvasive dual optical photoplethysmography (PPG) sensor to classify the degree of arteriovenous fistula (AVF) stenosis in hemodialysis (HD) patients. Dual PPG measurement node (DPMN) becomes the primary tool in this work for detecting abnormal narrowing vessel simultaneously in multi-beds monitoring patients. The mean and variance of Rising Slope (RS) and Falling Slope (FS) values between before and after HD treatment was used as the major features to classify AVF stenosis. Multilayer perceptron neural networks (MLPN) training algorithms are implemented for this analysis, which are the Levenberg-Marquardt, Scaled Conjugate Gradient, and Resilient Back-propagation, to identify the degree of HD patient stenosis. Eleven patients were recruited with mean age of 77 ± 10.8 years for analysis. The experimental results indicated that the variance of RS in the HD hand between before and after treatment was significant difference statistically to stenosis (p < 0.05). Levenberg-Marquardt algorithm (LMA) was significantly outperforms the other training algorithm. The classification accuracy and precision reached 94.82% and 92.22% respectively, thus this technique has a potential contribution to the early identification of stenosis for a medical diagnostic support system.

Identification of Cerebral Artery Stenosis Using Bilateral Photoplethysmography

Cerebral artery stenosis is currently diagnosed by transcranial Doppler (TCD), computed tomographic angiography (CTA), or magnetic resonance angiography (MRA). CTA exposes a patient to radiation, while CTA and MRA are invasive and side effects were related to contrast medium use. This study aims to provide a technique that can simply discriminate between people with normal blood vessels and those with cerebral artery stenosis using photoplethysmography (PPG), which is noninvasive and inexpensive. Moreover, the measurement takes only 120 seconds and is conducted on the fingers. The technique projects the light of a specific wavelength and analyzes the pulse waves which are generated when the blood passes through the blood vessels according to one's heartbeat using the transmitted light. Normalization was performed after dividing the extracted pulse waveform into windows, and maximum positive and negative amplitudes (MPA, MNA) were extracted from the detected pulse waves as features. The extracted features were used to identify normal subjects and those with cerebral artery stenosis using a linear discriminant analysis. The study results showed that the recognition rate using MPA was 92.2%, MNA was 90.6%, and combined MPA + MNA was 90.6%. The technique proposed is expected to detect early stage asymptomatic cerebral artery stenosis and help prevent ischemic stroke.

Development of an AVF Stenosis Assessment Tool for Hemodialysis Patients Using Robotic Ultrasound System

With the aging population and lifestyle changes, the number of hemodialysis (HD) patients increases year by year. The arteriovenous fistula (AVF) is the gold standard vascular access used to access the blood for HD treatment. Since the status of stenosis affects HD efficiency, current clinical practices usually use a Doppler ultrasound imaging system to assess the parameters of the stenosis, such as the degree of stenosis (DOS). Unfortunately, this is a very time-consuming task. Furthermore, it is difficult to stably maintain the ultrasound probe for a prolonged period to give doctors clearer or reproducible images. In this study, a robotic ultrasound system (RUS) with ultrasound sequential imaging analysis was designed to evaluate the DOS of the AVF. The sequential imaging analysis was capable of image smoothing and vessel boundary detection. It enabled clinicians to mark the thickness of the plaque for further processing. Finally, the system was used to reconstruct 3D models of fistulas and calculated the DOS for clinical assessment. We also designed a pressure sensing module attached to the ultrasound probe to prevent the probe from coming loose, vibrating, and exerting abnormal pressure on the skin. In the phantom test, the results showed that the error of the DOS that was calculated by RUS was less than 3%. The results of clinical trials obtained from ten patients show that the error between the RUS and clinicians' measurement was about 10% and had a highly linear correlation (R Square > 0.95). In addition, the reproducibility error was about 3% and could effectively save about 46% of the time during clinical examinations.