Apr 29, 2022
Diagnosis of hypertension based on TCM (Traditional Chinese Medicine) constitution and wrist pulse wave signal
This protocol is a draft, published without a DOI.
- Lin Fan1,
- Zhong-Ming Wang1,
- Rong zhang1,
- Yan Li1,
- Xiao-Kang Zhang1,
- Anonymous1
- 11 School of Computer Science and Technology, Xi’an University of Posts and Telecommunications, Xi’an 710121, Shaanxi, China
Protocol Citation: Lin Fan, Zhong-Ming Wang, Rong zhang, Yan Li, Xiao-Kang Zhang, Anonymous 2022. Diagnosis of hypertension based on TCM (Traditional Chinese Medicine) constitution and wrist pulse wave signal. protocols.io https://protocols.io/view/diagnosis-of-hypertension-based-on-tcm-traditional-b8d5rs86
License: This is an open access protocol distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited
Protocol status: Working
We use this protocol and it’s working
Created: April 28, 2022
Last Modified: April 29, 2022
Protocol Integer ID: 61597
Keywords: TCM constitution, Constitution in the Chinese Medicine Questionnaire, wrist pulse wave signal, Hypertension
Disclaimer
DISCLAIMER – FOR INFORMATIONAL PURPOSES ONLY; USE AT YOUR OWN RISK
The protocol content here is for informational purposes only and does not constitute legal, medical, clinical, or safety advice, or otherwise; content added to protocols.io is not peer reviewed and may not have undergone a formal approval of any kind. Information presented in this protocol should not substitute for independent professional judgment, advice, diagnosis, or treatment. Any action you take or refrain from taking using or relying upon the information presented here is strictly at your own risk. You agree that neither the Company nor any of the authors, contributors, administrators, or anyone else associated with protocols.io, can be held responsible for your use of the information contained in or linked to this protocol or any of our Sites/Apps and Services.
Abstract
In previous studies, pulse signals have been analysed primarily to standardise and objectify pulse diagnosis, but the influence of TCM constitution on pulse signals and disease has been neglected. Our study links the wrist pulse wave signal to TCM constitution to find TCM constitution factors that predispose to disease while improving the accuracy of disease classification. Our specific approach is set out below. A wrist pulse signal sampler based on a piezoelectric sensor was designed and 95 healthy subjects and 20 hypertensive patients were invited to complete the CCMQ (Constitution in the Chinese Medicine Questionnaire), of which 48 completed the pulse wave signal. Meanwhile, we improved the Butterworth filtering algorithm to denoise the pulse wave signals, and after smoothing and period segmentation, we finally extracted 27 time-domain features and 8 wavelet packet energy features. Then, we used the independent sample t-test and binary logistic regression analysis to analyze the correlation between the prevalence of hypertension and TCM constitution and found that the three constitutions of YaD (Yang-deficiency), YiD (Yin-deficiency), and PW (Phlegm-wet) were significantly associated with whether the subjects suffered from hypertension. The final classification results showed that the fusion features after adding the three constitution features with a high correlation with hypertension had a 17.46% higher F-score than the classification model without the constitution features. It can be seen that the incorporation of constitution characteristics into pulse characteristics in this paper has important implications for disease classification. This also provides a basis for studying the correlation between TCM physical characteristics and certain diseases, and patients can adopt targeted TCM management techniques to prevent diseases in advance.
Pulse sampler
Proposed pulse preprocessing method
Pulse de-noising
Period segmentation
Design of pulse sampler
Pulse signal feature extract
Time-domain features
Energy features of wavelet packet
Statistical analysis
Test of normality.
Linearity test.
Independent sample t-test.
Binary Logistic Regression.
Untitled case1 step
Disease classification