A comprehensive review on technological advancements for sensor-based Nadi Pariksha: An ancient Indian science for human health diagnosis

Nadi Pariksha is a significant, rather symbolic term for Ayurveda. Ancient Ayurvedic literature has prominently stated its importance in the judgment of Tridoshas (Vata, Pitta, and Kapha) which are the base of ailment diagnosis and prediction. The knowledge about Nadi Pariksha is uncovered in various ancient Ayurvedic literature like Ravansamhita, Bhavprakash, Nadivigyan by Kanad, Sharangdhar, and Yogratnakar. The various Nadi parameters are indicative of the diagnosis of diseases. These techniques were used as popular diagnostic tools in Indian culture from ancient days. Still, nowadays, these are not being used explicitly due to the lack of expertise, so it is necessary to establish their results once gained so that they can be used along with technical aspects in today's era. Ayurveda believes that all the elements of the Universe are present in any human body in minute, proportionate quantity, and the Nadi represents these elements, that is, Vata, Pitta, and Kapha (VPK). To facilitate the Nadi Pariksha using appropriate sensors may help the Ayurveda practitioners diagnose Prakriti and predict some diseases, making the Nadi Pariksha more reliable and faster. This review paper lists, 2 books and 67 research papers, mostly from countries like India, China, Japan, Korea, etc., from various reputed databases. The review primarily concentrates on six research themes: sensors and devices used for Nadi signal acquisition, signal pre-processing methods, feature extraction methods, feature selection approaches, classification practices, diseases diagnosed, and results attained. The paper also reviews the challenges in implementing the automated Nadi Pariksha with technological aid, which is a necessity of this period and is a very vibrant research arena. Yet significant work remains to be done, like bridging the gaps between technical and commercial development, and the procedure standardization is also required.

Pulse Feature-Enhanced Classification of Microalgae and Cyanobacteria Using Polarized Light Scattering and Fluorescence Signals

Harmful algal blooms (HABs) pose a global threat to the biodiversity and stability of local aquatic ecosystems. Rapid and accurate classification of microalgae and cyanobacteria in water is increasingly desired for monitoring complex water environments. In this paper, we propose a pulse feature-enhanced classification (PFEC) method as a potential solution. Equipped with a rapid measurement prototype that simultaneously detects polarized light scattering and fluorescence signals of individual particles, PFEC allows for the extraction of 38 pulse features to improve the classification accuracy of microalgae, cyanobacteria, and other suspended particulate matter (SPM) to 89.03%. Compared with microscopic observation, PFEC reveals three phyla proportions in aquaculture samples with an average error of less than 14%. In this paper, PFEC is found to be more accurate than the pulse-average classification method, which is interpreted as pulse features carrying more detailed information about particles. The high consistency of the dominant and common species between PFEC and microscopy in all field samples also demonstrates the flexibility and robustness of the former. Moreover, the high Pearson correlation coefficient accounting for 0.958 between the cyanobacterial proportion obtained by PFEC and the cyanobacterial density given by microscopy implies that PFEC serves as a promising early warning tool for cyanobacterial blooms. The results of this work suggest that PFEC holds great potential for the rapid and accurate classification of microalgae and cyanobacteria in aquatic environment monitoring.

Pressure wrist pulse signal analysis by sparse decomposition using improved Gabor function

BACKGROUND AND OBJECTIVE

In traditional Chinese medicine and Ayurvedic medicine, wrist pulse wave fluctuations are an important indicator for distinguishing different health states. Owing to the development of modern sensing technology, computational methods have been used in the analysis of pulse wave signals. The description and quantification of the peaks in the pulse wave is significant for the identification of health status.

METHODS

In this study, we decomposed the pressure pulse waveform of the radial artery into several components by sparse decomposition with an improved Gabor function. To better represent the position, shape, and relationship of the peaks, we designed an improved Gabor function structure based on the characteristics of the pulse waveform to generate a time-frequency dictionary. Compared with conventional representation methods, the shape of the Gabor function is more variable. In addition, owing to the limitation of windowing, the Gabor function can reduce the influence on other positions when it represents a specific position. Feature vectors consisting of decomposed components can be used for computerized pulse signal analysis and disease diagnosis.

RESULTS

In the binary classification of healthy and diseased pulse signals, the proposed method achieved the best results for health/diabetes, health/cardiac disease, health/hypertension, and health/nephropathy with accuracies of 93.54%, 73.42%, 88.42%, and 82.28%, respectively. The multi-classification performance of the different types of features was evaluated by six classifiers, and the proposed method obtained the highest classification performance with support vector machine-radial basis function for both balanced and imbalanced data.

CONCLUSIONS

The results indicated that the proposed method enabled to obtain a smaller representation error and exhibited superior performance in distinguishing between the signals collected from patients and healthy individuals. Moreover, for the multi-classification of the pulse signals, the proposed method performed better than the state-of-the-art methods.

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.

Wrist pulse diagnosis of stable coronary heart disease based on acoustics waveforms

BACKGROUND AND OBJECTIVE

As a common pathological pulse, unsmooth pulse has important diagnostic value in traditional Chinese medicine (TCM). In modern pulse diagnosis, unsmooth pulse plays an important role in the diagnosis of disease location and nature, but there are few studies on it. In this paper, a pulse diagnosis approach based on acoustic waveforms was proposed, the wrist pulse was divided into five layers vertically for the first time. Five layers acoustic waves of the radial artery in stable coronary heart disease (CHD) patients and relatively healthy people were compared to explore whether there are abnormal changes in acoustic pulse in stable CHD patients.

METHODS

The acoustic features of unsmooth pulse in patients with stable CHD were analyzed in time domain, frequency domain and empirical mode decomposition, combined with shannon entropy and multi-scale entropy. Sixteen pulse characteristics were discovered, and one-way analysis of variance were performed. The characteristics of the two groups were tested by T test. 13 features were used to identify patients with stable CHD by support vector machine (SVM).

RESULTS

Compared to healthy people, all parameters of the third layer of the stable CHD left Cun pulse were significantly different from those of the healthy people. The identification rates of the fourth and third layer of the left Cun pulse were the first (90.79%) and the second (88.16%), respectively.

CONCLUSION

Abnormal acoustic pulse appeared in the radial artery in patients with stable CHD. According to these changes, patients with stable CHD can be effectively identified from the perspective of pulse.

Multitask Interactive Attention Learning Model Based on Hand Images for Assisting Chinese Medicine in Predicting Myocardial Infarction

Acute myocardial infarction (AMI) is one of the most serious and dangerous cardiovascular diseases. In recent years, the number of patients around the world has been increasing significantly, among which people under the age of 45 have become the high-risk group for sudden death of AMI. AMI occurs quickly and does not show obvious symptoms before onset. In addition, postonset clinical testing is also a complex and invasive test, which may cause some postoperative complications. Therefore, it is necessary to propose a noninvasive and convenient auxiliary diagnostic method. In traditional Chinese medicine (TCM), it is an effective auxiliary diagnostic strategy to complete the disease diagnosis through some body surface features. It is helpful to observe whether the palmar thenar undergoes hypertrophy and whether the metacarpophalangeal joint is swelling in detecting acute myocardial infarction. Combined with deep learning, we propose a depth model based on traditional palm image (MTIALM), which can help doctors of traditional Chinese medicine to predict myocardial infarction. By building the shared network, the model learns information that covers all the tasks. In addition, task-specific attention branch networks are built to simultaneously detect the symptoms of different parts of the palm. The information interaction module (IIM) is proposed to further integrate the information between task branches to ensure that the model learns as many features as possible. Experimental results show that the accuracy of our model in the detection of metacarpophalangeal joints and palmar thenar is 83.16% and 84.15%, respectively, which are significantly improved compared with the traditional classification methods.

Task-Coupling Elastic Learning for Physical Sign-based Medical Image Classification

Physical signs of patients indicate crucial evidence for diagnosing both location and nature of the disease, where there is a sequential relationship between the two tasks. Thus their joint learning can utilize intrinsic association by transferring related knowledge across relevant tasks. Choosing the right time to transfer is a critical problem for joint learning. However, how to dynamically adjust when tasks interact to capture the right time for transferring related knowledge is still an open issue. To this end, we propose a Task-Coupling Elastic Learning (TCEL) framework to model the task relatedness for classifying disease-location and disease-nature based on physical sign images. The main idea is to dynamically transfer relevant knowledge by progressively shifting task-coupling from loose to tight during the multi-stage training. In the early stage of training, we relax the constraints of modeling relations to focus more in learning the generic task-common features. In the later stage, the semantic guidance will be strengthened to learn the task-specific features. Specifically, a dynamic sequential module (DSM) is proposed to explicitly model the sequential relationship and enable multi-stage training. Moreover, to address the side effect of DSM, a new loss regularization is proposed. The extensive experiments on these two clinical datasets show the superiority of the proposed method over the baselines, and demonstrate the effectiveness of the proposed task-coupling elastic mechanism.

Computational Traditional Chinese Medicine diagnosis: A literature survey

BACKGROUND AND OBJECTIVE

Traditional Chinese Medicine (TCM) diagnosis is based on the theoretical principles and knowledge, where it is steeped in thousands of years of history to diagnose various types of diseases and syndromes. It can be generally divided into four main diagnostic approaches: 1. Inspection, 2. Auscultation and olfaction, 3. Inquiry, and 4. Palpation, which are widely used in TCM hospitals in China and around the world. With the development of intelligent computing technology in recent years, computational TCM diagnosis has grown rapidly.

METHODS

In this paper, we aim to systematically summarize the development of computational TCM diagnosis based on four diagnostic approaches, mainly focusing on digital acquisition devices, collected datasets, and computational detection approaches (algorithms). Furthermore, all related works of this field are compared and explored in detail.

RESULTS

This survey provides the principles, applications, and current progress in computing for readers and researchers in terms of computational TCM diagnosis. Moreover, the future development direction, prospect, and technological trend of computational TCM diagnosis will also be discussed in this study.

CONCLUSIONS

Recent computational TCM diagnosis works are compared in detail to show the pros/cons, where we provide some meaningful suggestions and opinions on the future research approaches in this area. This work is useful for disease detection in computational TCM diagnosis as well as health management in the smart healthcare area.

INDEX TERMS

Computational diagnosis, Traditional Chinese Medicine, survey, smart healthcare.

The novel three-dimensional pulse images analyzed by dynamic L-cube polynomial model

A dynamic L-cube polynomial is proposed to analyze dynamic three-dimensional pulse images (d3DPIs), as an extension of the previous static L-cube polynomial. In this paper, a weighted least squares (WLS) method is proposed to fit the amplitude C(t) of d3DPI at four physiological key points in addition to the best fit of L-cube polynomials to the measured normal and cold-pressor-test (CPT)-induced taut 3DPIs. Compared with other two fitting functions, C(t) of a dynamic L-cube polynomial can be well matched by the proposed WLS method with the least relative error at four physiological key points in one beat with statistical significance, in addition to the best fit of the measured 3DPIs. Therefore, a dynamic L-cube polynomial can reflect dynamic time characteristics of normal and CPT-induced hypertensive taut 3DPIs, which can be used as an evidence of hypertension diagnosis.

A Novel MOGA-SVM Multinomial Classification for Organ Inflammation Detection

Wrist pulse signal (WPS) contains crucial information of humans’ health condition. It can serve as an alternative method for diagnosing of organ inflammation instead of traditional clinical measurement. In this paper, a novel multi-objective genetic algorithm based support vector machine (MOGA-SVM) has been proposed for the multinomial classification of the inflammations of appendix, pancreas, and duodenum. A customized similarity kernel (KCS) has been optimally designed. The performance of multinomial classification using KCS is compared with five types of kernels, linear, radial basis function (RBF), polynomial and sigmoid kernel, as well as mixtures of polynomial and RBF, to verify the effectiveness of KCS. The sensitivity, specificity and accuracy (Acc) of the proposed method are 92%, 91.2%, and 91.6% respectively. The results have demonstrated that KCS improves the accuracy of classification from 8.9% to 59.6%. When compared to related work, the proposed method increases the performance by more than 10%. It is believed that WPS can serve as alternative measures to diagnose organ inflammations.