Abstract
The wrist pulse signals can be used to analyze a person’s health status in that they reflect the pathologic changes of the person’s body condition. This paper aims to present a novel time series analysis approach to analyze wrist pulse signals. First, a data normalization procedure is proposed. This procedure selects a reference signal that is ‘closest’ to a newly obtained signal from an ensemble of signals recorded from the healthy persons. Second, an auto-regressive (AR) model is constructed from the selected reference signal. Then, the residual error, which is the difference between the actual measurement for the new signal and the prediction obtained from the AR model established by reference signal, is defined as the disease-sensitive feature. This approach is based on the premise that if the signal is from a patient, the prediction model previously identified using the healthy persons would not be able to reproduce the time series measured from the patients. The applicability of this approach is demonstrated using a wrist pulse signal database collected using a Doppler Ultrasound device. The classification accuracy is over 82% in distinguishing healthy persons from patients with acute appendicitis, and over 90% for other diseases. These results indicate a great promise of the proposed method in telling healthy subjects from patients of specific diseases.






Similar content being viewed by others
References
Shu, J., and Sun, Y., Developing classification indices for Chinese pulse diagnosis. Complement. Ther. Med. 15 (3)190–198, 2007.
Hammer, L., Chinese pulse diagnosis—Contemporary approach. Eastland, Vista, 2001.
Leonard, P., Beattie, T., Addison, P., and Watson, J., Wavelet analysis of pulse oximeter waveform permits identification of unwell children. Emerg. Med. J. 21:59–60, 2004.
Zhang, Y., Wang, Y., Wang, W., and Yu, J., Wavelet feature extraction and classification of Doppler ultrasound blood flow signals. J. Biomed. Eng. 19 (2)244–246, 2002.
Lu, W., Wang, Y., and Wang, W., Pulse analysis of patients with severe liver problems. IEEE Eng. Med. Biol. Mag. 18 (1)73–75, 1999.
Zhang, A., and Yang, F., Study on recognition of sub-health from pulse signal. Proceedings of the ICNNB Conference. 3:1516–1518, 2005.
Zhang, D., Zhang, L., Zhang, D., and Zheng, Y., Wavelet-based analysis of Doppler ultrasonic wrist-pulse signals. Proceedings of the ICBBE Conference, Shanghai. 2:589–543, 2008.
Sohn, H., and Farrar, C., Damage diagnosis using time series analysis of vibration signals. Smart Mater. Struct. 10:446–451, 2001.
Akaike, H., A new look at the statistical model identification. IEEE Trans. Automat. Contr. 19 (6)716–723, 1974.
Ljung, L., System identification: Theory for the user. Prentice-Hall PTR, Upper Saddle River, 1999.
Lukman, S., He, Y., and Hui, S., Computational methods for traditional Chinese medicine: A survey. Comput. Methods Programs Biomed. 88:283–294, 2007.
Burges, C., A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Discov. 2:121–167, 1998.
Yoon, Y., Lee, M., and Soh, K., Pulse type classification by varying contact pressure. IEEE Eng. Med. Biol. Mag. 19:106–110, 2000.
Powis, R., and Schwartz, R., Practical Doppler ultrasound for the clinician. Williams and Wilkins, Baltimore, 1991.
Wang, Y., Wu, X., Liu, B., and Yi, Y., Definition and application of indices in Doppler ultrasound sonogram. J. Biom. Eng. (Shanghai). 18:26–29, 1997.
Leeuwen, G., Hoeks, A., and Reneman, R., Simulation of real-time frequency estimators for pulsed Doppler systems. Ultrason. Imag. 8 (4)252, 1986.
Xu, L., Zhang, D., and Wang, K., Wavelet-based cascaded adaptive filter for removing baseline drift in pulse waveforms. IEEE Trans. Biomed. Eng. 52 (11)1973–1975, 2005.
Acknowledgement
This research is supported by the Hong Kong RGC PPR grant (PolyU 5007-PPR-6) and the Hong Kong Polytechnic University Internal Competitive Research Grant (G-YF25).
Author information
Authors and Affiliations
Corresponding author
Appendix: Doppler ultrasonic diagnostic parameters
Appendix: Doppler ultrasonic diagnostic parameters
Figure 7 illustrates a typical Doppler waveform about the wrist artery blood flow, where S and D are the Systolic peak (maximum velocity) and the end of Diastolic velocity, respectively. Two Doppler ultrasonic parameters, RT and SW, are illustrated in Fig. 7. Other commonly used Doppler parameters are defined as follows [15]:
-
1.
Spectrum Broadening Index (SBI): \(SBI = {{\left( {F_{{avpk}} - F_{{mean}} } \right)}} \mathord{\left/ {\vphantom {{{\left( {F_{{avpk}} - F_{{mean}} } \right)}} {F_{{avpk}} }}} \right. \kern-\nulldelimiterspace} {F_{{avpk}} }\), where F avpk means frequency excursion of peak systolic velocity and F mean means frequency excursion of mean velocity;
-
2.
Stenosis Index (STI): \(STI = 0.9 * {\left( {{1 - V_{m} } \mathord{\left/ {\vphantom {{1 - V_{m} } S}} \right. \kern-\nulldelimiterspace} S} \right)}\), where V m is the mean velocity;
-
3.
Resistance Index (RI): \(RI = {{\left( {S - D} \right)}} \mathord{\left/ {\vphantom {{{\left( {S - D} \right)}} S}} \right. \kern-\nulldelimiterspace} S\);
-
4.
Ratio of Systolic by Diastolic velocity (S/D).
Rights and permissions
About this article
Cite this article
Chen, Y., Zhang, L., Zhang, D. et al. Computerized Wrist Pulse Signal Diagnosis Using Modified Auto-Regressive Models. J Med Syst 35, 321–328 (2011). https://doi.org/10.1007/s10916-009-9368-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10916-009-9368-4