Traditional Chinese Medicine Pulse Diagnosis Research Articles

Advanced Pressure-Sending Wristband for Disease Detection Based on Traditional Chinese Medicine Pulse Diagnosis

This paper explores the integration of Traditional Chinese Medicine (TCM) pulse diagnosis with modern sensor technology to develop a sophisticated wristband system for monitoring vital organ health. Leveraging the principles of TCM, the proposed system focuses on the “Three regions and nine indicators” method to accurately detect pulse variations at different wrist positions and depths. By utilizing a pressure sensor array that covers the Cun, Guan, and Chi pulse positions, the wristband aims to enhance diagnostic accuracy beyond conventional wearable technologies. The system incorporates advanced micro-electro-mechanical techniques to minimize size while maintaining functionality, enabling continuous health monitoring through a coplanar crossed sensing array. Additionally, the use of machine learning algorithms facilitates the analysis of pulse data to identify potential health issues related to the heart, lungs, liver, kidneys, and spleen. An accompanying mobile app provides real-time feedback and health insights, promoting proactive health management. This innovative approach merges TCM’s holistic diagnosis methods with cutting-edge technology to offer a powerful tool for early disease detection and health monitoring, potentially transforming the landscape of personal healthcare devices.

Pulse signal may be a key bridge connecting cardiology and pulse diagnosis of TCM

ObjectiveThis study extracts atherosclerosis indices from six channels of Cunkou and discusses the data distribution, aims to explore the connection between cardiology of modern medicine (MM) and traditional Chinese medicine (TCM) pulse diagnosis. MethodsWe use a device capable of simultaneously collecting the pulse signals of the Cun, Guan and Chi to test the population participating in routine physical examinations. Firstly, we collected pressure pulse waves from six channels of Cunkou of 1045 healthy subjects (578 men and 467 women, average age=37.99±16.02 years). Secondly, we extracted the two most common arteriosclerosis indices pulse transit time (PTT) and Augmentation index (AIx) from six-channel pulse waves. Lastly, T-test and correlation test were taken to analyze the differences and relevance of the atherosclerosis indices extracted from six channels of Cunkou. ResultsWhen analyzing AIx and PTT at different wrist, it was found that AIx of left wrist is significantly higher than that of right wrist (P<0.001), while the PTT of left wrist is significantly lower than that of right wrist (P<0.001), a phenomenon that is common in both men and women. Furthermore, regardless of whether it is left or right wrist, the AIx at Chi channel is higher than that at Cun (P<0.05) and Guan (P<0.05). At the same time, the PTT at Guan is bigger than that at Cun in two wrists (P<0.05). However, when the specific channel is not considered, there is no significant difference in AIx and PTT between each channel and the corresponding wrist (P>0.05). In addition, regardless of gender, when the specific channel is not considered, AIx and PTT of each wrist are significantly correlated with age (P<0.001). ConclusionsThe differences of the atherosclerosis indices AIx and PTT in six channels support that the method of six-channel pulse diagnosis is indispensable in TCM. Additionally, the pulse waves obtained from each channel can be utilized as a dependable foundation for diagnosing atherosclerotic conditions. This study is beneficial for promoting the integration of TCM and MM in diagnosing disease.

Wearable multichannel-active pressurized pulse sensing platform

With the modernization of traditional Chinese medicine (TCM), creating devices to digitalize aspects of pulse diagnosis has proved to be challenging. The currently available pulse detection devices usually rely on external pressure devices, which are either bulky or poorly integrated, hindering their practical application. In this work, we propose an innovative wearable active pressure three-channel pulse monitoring device based on TCM pulse diagnosis methods. It combines a flexible pressure sensor array, flexible airbag array, active pressure control unit, advanced machine learning approach, and a companion mobile application for human–computer interaction. Due to the high sensitivity (460.1 kPa−1), high linearity (R2 > 0.999) and flexibility of the flexible pressure sensors, the device can accurately simulate finger pressure to collect pulse waves (Cun, Guan, and Chi) at different external pressures on the wrist. In addition, by measuring the change in pulse wave amplitude at different pressures, an individual’s blood pressure status can be successfully predicted. This enables truly wearable, actively pressurized, continuous wireless dynamic monitoring of wrist pulse health. The innovative and integrated design of this pulse monitoring platform could provide a new paradigm for digitizing aspects of TCM and other smart healthcare systems.

Pioneering Data Processing for Convolutional Neural Networks to Enhance the Diagnostic Accuracy of Traditional Chinese Medicine Pulse Diagnosis for Diabetes.

Traditional Chinese medicine (TCM) has relied on pulse diagnosis as a cornerstone of healthcare assessment for thousands of years. Despite its long history and widespread use, TCM pulse diagnosis has faced challenges in terms of diagnostic accuracy and consistency due to its dependence on subjective interpretation and theoretical analysis. This study introduces an approach to enhance the accuracy of TCM pulse diagnosis for diabetes by leveraging the power of deep learning algorithms, specifically LeNet and ResNet models, for pulse waveform analysis. LeNet and ResNet models were applied to analyze TCM pulse waveforms using a diverse dataset comprising both healthy individuals and patients with diabetes. The integration of these advanced algorithms with modern TCM pulse measurement instruments shows great promise in reducing practitioner-dependent variability and improving the reliability of diagnoses. This research bridges the gap between ancient wisdom and cutting-edge technology in healthcare. LeNet-F, incorporating special feature extraction of a pulse based on TMC, showed improved training and test accuracies (73% and 67%, respectively, compared with LeNet's 70% and 65%). Moreover, ResNet models consistently outperformed LeNet, with ResNet18-F achieving the highest accuracy (82%) in training and 74% in testing. The advanced preprocessing techniques and additional features contribute significantly to ResNet18-F's superior performance, indicating the importance of feature engineering strategies. Furthermore, the study identifies potential avenues for future research, including optimizing preprocessing techniques to handle pulse waveform variations and noise levels, integrating additional time-frequency domain features, developing domain-specific feature selection algorithms, and expanding the scope to other diseases. These advancements aim to refine traditional Chinese medicine pulse diagnosis, enhancing its accuracy and reliability while integrating it into modern technology for more effective healthcare approaches.

Classification research of TCM pulse conditions based on multi-label voice analysis

ObjectiveTo explore the feasibility of remotely obtaining complex information on traditional Chinese medicine (TCM) pulse conditions through voice signals. MethodsWe used multi-label pulse conditions as the entry point and modeled and analyzed TCM pulse diagnosis by combining voice analysis and machine learning. Audio features were extracted from voice recordings in the TCM pulse condition dataset. The obtained features were combined with information from tongue and facial diagnoses. A multi-label pulse condition voice classification DNN model was built using 10-fold cross-validation, and the modeling methods were validated using publicly available datasets. ResultsThe analysis showed that the proposed method achieved an accuracy of 92.59% on the public dataset. The accuracies of the three single-label pulse manifestation models in the test set were 94.27%, 96.35%, and 95.39%. The absolute accuracy of the multi-label model was 92.74%. ConclusionVoice data analysis may serve as a remote adjunct to the TCM diagnostic method for pulse condition assessment.

Machine learning classification of polycystic ovary syndrome based on radial pulse wave analysis.

Patients with Polycystic ovary syndrome (PCOS) experienced endocrine disorders that may present vascular function changes. This study aimed to classify and predict PCOS by radial pulse wave parameters using machine learning (ML) methods and to provide evidence for objectifying pulse diagnosis in traditional Chinese medicine (TCM). A case-control study with 459 subjects divided into a PCOS group and a healthy (non-PCOS) group. The pulse wave parameters were measured and analyzed between the two groups. Seven supervised ML classification models were applied, including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Trees, Random Forest, Logistic Regression, Voting, and Long Short Term Memory networks (LSTM). Parameters that were significantly different were selected as input features and stratified k-fold cross-validations training was applied to the models. There were 316 subjects in the PCOS group and 143 subjects in the healthy group. Compared to the healthy group, the pulse wave parameters h3/h1 and w/t from both left and right sides were increased while h4, t4, t, As, h4/h1 from both sides and right t1 were decreased in the PCOS group (P < 0.01). Among the ML models evaluated, both the Voting and LSTM with ensemble learning capabilities, demonstrated competitive performance. These models achieved the highest results across all evaluation metrics. Specifically, they both attained a testing accuracy of 72.174% and an F1 score of 0.818, their respective AUC values were 0.715 for the Voting and 0.722 for the LSTM. Radial pulse wave signal could identify most PCOS patients accurately (with a good F1 score) and is valuable for early detection and monitoring of PCOS with acceptable overall accuracy. This technique can stimulate the development of individualized PCOS risk assessment using mobile detection technology, furthermore, gives physicians an intuitive understanding of the objective pulse diagnosis of TCM. Not applicable.

Wearable Photoelectric Fingertip Force Sensing System Based on Blood Volume Changes without Sensory Interference.

Monitoring the force of fingertip manipulation without disturbing the natural sense of touch is crucial for digitizing the skills of experienced craftsmen. However, conventional force sensors need to be put between the skin and the objects, which affects the natural sense of the skin. Here, we proposed a fingertip force sensing method based on changes of blood volume and designed a wearable photoelectric fingertip force sensing system (PFFS) for digitalization of traditional Chinese medicine (TCM) pulse diagnosis. The PFFS does not interfere with the fingertips' tactile sense while detecting fingertip force. This PFFS detects the change of blood volume in fingertip by photoelectric plethysmography and can obtain the change of output current under different fingertip forces. We also studied the effect of various factors on PFFS output signals, including emission lights of different wavelengths, ambient temperature, and the user's heartbeat artifact. We further established the relationship between the change of blood volume and fingertip force by combining experimental and theoretical methods. Moreover, we demonstrated the feasibility of the PFFS to detect fingertip forces under commonly used conditions in TCM pulse diagnosis without sensory interference. This PFFS also shows promise for perceiving the viscosity of objects and recognizing gestures in human-computer interaction. This work paves the way for the digitalization of fingertip forces during TCM pulse diagnosis and other fingertip forces under natural conditions.

A low-cost flexible piezoresistive sensor with high sensitivity and broad detection range based on porous random microstructures for wearable electronics

Due to their simple structures and high sensitivity, flexible piezoresistive sensors have great potential for physiological monitoring, tactile recognition of prosthetics, and electronic skin. Here, a flexible piezoresistive sensor based on porous random microstructures and having high sensitivity and a wide detection range is proposed. Conductive carbon black was used as an active filler and thermoplastic expandable microspheres and sandpaper were used as templates for the fabrication of the pore structures and random microstructures of the substrates, respectively. Synergistic interactions between these two components in the sensor led to a high sensitivity of 11.02 kPa−1 (0–6 kPa), wide measuring range (0–30 kPa), rapid response time (<200 ms), and long-term durability (>2000 cycles). The sensor was effective for monitoring a variety of hand movements, including bending of the fingers and wrist. In addition, the sensors were effective when attached to a robotic hand to simulate the traditional Chinese medicine pulse diagnosis and to grasp objects. This device thus has broad application prospects in the field of human-machine interactions and robot teleoperation.

Cocklebur-inspired “branch-seed-spininess” 3D hierarchical structure bionic electronic skin for intelligent perception

Traditional electronic skin (e-skin) with single micro-nano structures has a limited capacity to optimize the comprehensive sensing properties, which greatly hinders the intellectualization process. Herein, cocklebur-inspired bionic e-skin consisting of the “branch-seed-spininess” three-dimensional hierarchical structure, namely the P(VDF-TrFE) fiber-TiO2 pillar-TiO2 thorn structure (FPTS), is proposed. Benefiting from the hierarchical characteristics of the FPTS, the e-skin exhibits a high sensitivity of 0.163 kPa−1 (<20 kPa), wide pressure sensing range of 0–200 kPa, and ultrafast response/relaxation time of < 5.6 ms. In light of these salient features, versatile intelligent perception applications are explored. First, robot fingers are equipped with the FPTS e-skins and realize the traditional Chinese medicine pulse diagnosis of the radial artery in different positions and pressing degrees. Second, a flexible perception array with 100 FPTS e-skin units enables the spatial pressure mapping of flat/curved surfaces and the perception of different Braille characters. Most importantly, by making full use of the FPTS e-skin with a five-layer deep neural network, an intelligent gesture perception system is developed for accurate recognition (average accuracy: 98.33%) of sign language and precise control of the robot hand, which is of great significance for the development of intelligent sign language translation in artificial intelligence.

A new interpretation of TCM pulse diagnosis based on quantum physical model of the human body

Following the quantum theory-based physical model of the human body, a new interpretation of the traditional Chinese medicine (TCM) principle of “Cunkou reads viscera” is presented. Then, a Gaussian pulse wave model as a solution to the Schrodinger equation is shown to accurately describe 19 different pulse shapes, and to quantitatively capture the degree of Yin-Yang attributes of 13 pulse shapes. Furthermore, the model suggests using pulse depth and strength as leading-order quantity and pulse shape as first-order quantity, to characterize the hierarchical resonance between the human body and the environment. The future pulse informatics will focus on determining an individual’s unique quantum human equilibrium state, and diagnose its health state according to the pulse deviation from its equilibrium state, to truly achieve the high level of TCM: “knowing the normal state and reaching the change”.

Refined Multiscale Entropy Analysis of Wrist Pulse for Gender Difference in Traditional Chinese Medicine among Young Individuals.

Pulse signal analysis plays an important role in promoting the objectification of traditional Chinese medicine (TCM). Like electrocardiogram (ECG) signals, wrist pulse signals are mainly caused by cardiac activities and are valuable in analyzing cardiac diseases. A large number of studies have reported ECG signals can distinguish gender characteristics of normal healthy subjects using entropy complexity measures, consistently showing more complexity in females than males. No research up to date, however, has been found on examining gender differences with wrist pulse signals of healthy subjects on entropy complexity measures. This paper is aimed to fill in the research gap, which could, in turn, provide a deeper insight into the pulse signal and might identify potential differences between ECG signals and pulse signals. In particular, several complementary entropy measures with corresponding refined composite multiscale versions are established to perform the analysis for the filtered TCM pulse signals. Experimental results reveal that regardless of entropy measures used, there is no statistically significant gender difference in terms of entropy complexity, indicating that the pulse signal holds less gender characteristics than the ECG signal. In view of these findings, wrist pulse signals could be likely to provide different pieces of information to ECG signals. The present study is the first to quantitatively evaluate gender differences in healthy pulse signals with measures of entropy complexity and more importantly; we expect this study could make contribution to the ongoing pulse intelligent diagnosis and objective analysis, further facilitating the modernization of TCM pulse diagnosis.

Research on feature mining algorithm and disease diagnosis of pulse signal based on piezoelectric sensor

The human pulse contains various information reflecting the internal environment of the human body. However, the classical method of pulse diagnosis in traditional Chinese medicine (TCM) has the disadvantages of relying too much on the doctor's experience and the diagnosis result is too subjective. Based on the principle of TCM pulse diagnosis, the use of photoelectric sensors to collect the pulse signals of multiple healthy people and patients with chronic diseases, and organize the detailed pulse information into a data set and analyze it with algorithms, is a solution to overcome this problem through modern technology. However, this method is still difficult to understand the patient's physiological condition in detail, and it is also difficult to explain the internal connection between abnormal pulse conditions and their physiological conditions. In the experiment, after denoising, smoothing, and eliminating the baseline drift of the subjects' pulse data, we designed two algorithms to describe the difference between the two-dimensional images of the pulse data of normal people and patients with chronic diseases. The specific feature values obtained are converted into a multi-dimensional array and trained in a support vector machine (SVM) classifier. The classification accuracy is higher than the basic temporal features. Experimental results show that it is feasible to use specific feature mining algorithms for disease detection. Through analysis, this paper found the pathological characteristics reflected in the two-dimensional pulse image, discovered the internal connection between the pulse waveform characteristics of the human body and the disease, and tried to describe it through algorithms, trying to establish a method for detecting specific diseases using photoelectric signals.

Traditional Chinese Medicine Pulse Diagnosis on a Smartphone Using Skin Impedance at Acupoints: A Feasibility Study.

In traditional Chinese medicine (TCM), pulse diagnosis is one of the most important methods for diagnosis. A pulse can be felt by applying firm fingertip pressure to the skin where the arteries travel. The pulse diagnosis has become an important tool not only for TCM practitioners but also for several areas of Western medicine. Many pulse measuring devices have been proposed to obtain objective pulse conditions. In the past, pulse diagnosis instruments were single-point sensing methods, which missed a lot of information. Later, multi-point sensing instruments were developed that resolved this issue but were much higher in cost and lacked mobility. In this article, based on the concept of sensor fusion, we describe a portable low-cost system for TCM pulse-type estimation using a smartphone connected to two sensors, including one photoplethysmography (PPG) sensor and one galvanic skin response (GSR) sensor. As a proof of concept, we collected five-minute PPG pulse information and skin impedance on 24 acupoints from 80 subjects. Based on these collected data, we implemented a fully connected neural network (FCN), which was able to provide high prediction accuracy (>90%) for patients with a TCM wiry pulse.

A high gauge-factor wearable strain sensor array via 3D printed mold fabrication and size optimization of silver-coated carbon nanotubes

The development of 3D print technology provided an opportunity to achieve fast and accurate fabrication of wearable sensor arrays. In this paper, high-sensitivity flexible and stretchable silver-coated carbon nanotube (Ag@CNT) wearable strain sensor arrays are fabricated using 3D printing technology and composite nanomaterial synthesis. Ag@CNTs with uniform and compact particles were synthesized with different sizes of carbon nanotubes (CNTs) using a reduction method. Strain sensor arrays were fabricated accurately and efficiently with the aid of 3D printed molds. Sensors with different Ag@CNTs were then compared comprehensively, and it was found that the Ag@CNT (short) sensor, which had a gauge factor (GF) of 62.8 in the 0% to 14.44% stretch range and a GF of 831.3 in the 14.44% to 21.11% stretch range, can significantly enhance the detection of small movements. These wearable strain sensor arrays were utilized in the application of traditional Chinese medicine pulse diagnosis and gesture recognition.

Colectomy influences the radial pulse parameters of traditional Chinese medicine pulse diagnosis in patients with colorectal cancer

IntroductionIn Traditional Chinese Medicine (TCM), manual palpation of the radial pressure pulse (RPP) has remained a traditional method of clinical diagnoses for centuries. Arterial mechanics have been studied by various researchers. Time-domain and frequency-domain analyses of the RPP has typically provided a quantitative and non-biased assessment that gives complex physiological and pathological information. To date, no preceding research has clarified the relationship of the radial pulse and the large intestine in TCM theory. In this pre-post intervention study, we compared the RPP parameters of patients with colorectal cancer before and after colectomy. MethodsThirty patients aged between 18 and 80 years old from the Department of Colorectal Surgery in Taichung Tzu Chi Hospital, Taiwan were enrolled into this study based on predefined inclusion and exclusion criteria before the colectomy. The assessment of RPP was performed before the colectomy and within 24 h after the colectomy. The mean value of the spectral energy (SE0―10 Hz, SE10―50 Hz, and SE13―50 Hz) and the radial augmentation index (AI) were obtained. ResultsWe observed that the SE10―50 Hz and SE13―50 Hz of the right Chy was significantly increased after the colectomy while the SE13―50 Hz of the right Chun was significantly decreased after the colectomy procedures. The radial AI of the right Chy was significantly reduced after the colectomy compared to the remaining pulse positions. ConclusionsTo our best knowledge, this preliminary study is the first attempt to investigate the influence of colectomy on the radial pulse parameters in patients with colorectal cancer. The major findings from this study include a significant reduction of the radial AI at the right Chy pulse, and a significant difference in the SE at the right Chy and Chun pulses after colectomy. It is also the first study using modern scientific tools to validate the TCM theory that the right Chy pulse corresponds to the changes in the large intestine through surgical removal of the visceral organs.

High‐Performance Flexible Tactile Sensor Enabling Intelligent Haptic Perception for a Soft Prosthetic Hand

AbstractCompared to the traditional motor‐driven prosthetic hand, a soft prosthetic hand (SPD) has intrisic advantages such as kinematics dexterity and friendly external interaction. In order for an SPD to realize the function of a real hand, the integration of flexible high‐performance tactile sensors is essential. Current research on flexible tactile sensors is mainly focused on increasing sensitivity, but ignores other issues, such as the complexity of arraying and compatibility with soft actuators. A high‐performance flexible force sensor enabling intelligent tactile perception for an SPD is reported. With the aid of reasonable arrangement of functional material and effective 3D structure design, the force sensor exhibits good linearity (R2 = 0.982), accuracy and repeatability, very low hysteresis, fast dynamical response (&lt;1 ms), high stability (30000 loading–unloading cycles), stable performance under high frequency (&gt;50 Hz), and can easily be arrayed and integrated with an SPD. With such a sensor mounted on its surface, an SPD achieves various complicated tasks in the same manner as a real hand, including feeling the softness of objects and imitating the process of traditional Chinese medicine pulse diagnosis to monitor a pulse wave in the radial artery. Finally, through use of a force‐sensor array, an SPD provides real‐time spatial distribution of pressure during the grabbing of objects.

Accurate targeting in robot-assisted TCM pulse diagnosis using adaptive sensor fusion

Accurate targeting plays an important role in the study of human-robot interaction under dynamic environments. Especially for robot-assisted Traditional Chinese Medicine (TCM) pulse diagnosis, the localization and accuracy of diagnose positions at wrist needs to be addressed. In this work, imaging photoplethysmography (iPPG) which measures the physiological changes of blood flow in artery is used as an extra modal information in addition to computer vision at localization, to alleviate the effect of approaching distance varying during the robot arm movement. Both computer vision and iPPG are fed into an adaptive fusion expert of convolutional neural networks (CNN) architecture, and this boosts the accuracy at targeting of TCM radial artery at wrist. A coherence weight of their contributions was calculated and reflected the adaptation of the CNN to distance varying.

A Wearable Multifunctional Pulse Monitor Using Thermosensation-Based Flexible Sensors.

This study proposes a novel wearable pulse monitoring system, which can realize the synchronous measurements of pulse wave, skin, temperature, and pulse wave velocity (PWV). A flexible sensor based on thermosensation is used to detect pressure and temperature stimuli simultaneously. A total of two sensors are integrated to detect pulse transit along two specific points of the artery, e.g., Cun and Chi at a wrist, the data of which are subsequently used to figure out the PWV by using a tailor-designed algorithm conducted in a microprocessor. Calibration experiments and application cases are conducted to validate the effectiveness of the monitor. The developed monitor detects the physiological signals of pulse wave, PWV, and skin temperature simultaneously. In addition, the monitor can measure the pulse changes before and after exercises and track skin temperature variations when warming and cooling. Moreover, the monitor can be also used to detect the local PWV at the wrist. The synchronous measurements of pulse wave, skin temperature, and PWV using a wearable monitor are feasible. The monitor is small, simple-structured, with multifunction, and thus provides a promising auxiliary approach for traditional Chinese medicine pulse diagnosis.

An innovative method to evaluate the severe level of general Qi deficiency

OBJECTIVEThe study aim was to use existing relevant indexes to establish an index series for the quantitative measurement of Qi deficiency pattern (QDP) in Traditional Chinese Medicine (TCM). METHODSSeventeen indexes of arterial oxygen saturation (SaO2), TCM pulse diagnosis, heart rate, and blood pressure were integrated into an index series, and 94 selected subjects were divided into a healthy control group, a mild QDP group, and a typical QDP group. All three groups were then synchronously given a breath-holding (BH) test and index detections using TCM apparatus for auxiliary diagnosis and treatment and a photoplethysmograph. The detections were carried out repeatedly until there was no monotonic change in the value of the minimal SaO2 during a BH measurement (SaO2MIN) or in the duration of BH during a BH measurement (TBH). RESULTSBH measurement and index detection data from 380 eligible cases were analyzed and a significant intergroup difference was found for 12 indexes. CONCLUSIONAn index series for quantitative QDP measurement could comprise the 12 effective indexes: RSaO2d (rate of decline of SaO2 during a BH measurement), RSaO2r (recovery rate of SaO2 after a BH measurement), SaO2min, BFV (blood flow velocity), TSaO2d (the time at which SaO2 started declining during a BH measurement), TBH, TSaO2min (the time of occurrence of the minimal SaO2 during a BH measurement), TSaO2max (the time of occurrence of the maximal SaO2 after a BH measurement), PTP (pulse-touching pressure), SBP (systolic blood pressure), PWV (pulse wave velocity), and DBP (diastolic blood pressure). Of the indexes, RSaO2d could play a key role in quantitative QDP measurement; RSaO2r and SaO2min could be used to differentiate the QDP symptom of shortness of breath and as early-warning indexes for chronic obstructive pulmonary disease. BFV, TSaO2d, and TBH could be used to quantitatively assess the QDP symptoms of spontaneous perspiration and shortness of breath.

Pulse Wave Cycle Features Analysis of Different Blood Pressure Grades in the Elderly.

Background and Objective The same range of blood pressure values may reflect different vascular functions, especially in the elderly. Therefore, a single blood pressure value may not comprehensively reveal cardiovascular function. This study focused on identifying pulse wave features in the elderly that can be used to show functional differences when blood pressure values are in the same range. Methods First, pulse data were preprocessed and pulse cycles were segmented. Second, time domain, higher-order statistics, and energy features of wavelet packet decomposition coefficients were extracted. Finally, useful pulse wave features were evaluated using a feature selection and classifier design. Results A total of 6,075 pulse wave cycles were grouped into 3 types according to different blood pressure levels and each group was divided into 2 categories according to a history of hypertension. The classification accuracy of feature selection in the 3 groups was 97.91%, 95.24%, and 92.28%, respectively. Conclusion Selected features could be appropriately used to analyze cardiovascular function in the elderly and can serve as the basis for research on a cardiovascular risk assessment model based on Traditional Chinese Medicine pulse diagnosis.