Computerized Wrist Pulse Signal Diagnosis Using Modified Auto-Regressive Models
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.
KeywordsWrist pulse signal Auto-regressive model Time series analysis
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).
- 2.Hammer, L., Chinese pulse diagnosis—Contemporary approach. Eastland, Vista, 2001.Google Scholar
- 4.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.Google Scholar
- 6.Zhang, A., and Yang, F., Study on recognition of sub-health from pulse signal. Proceedings of the ICNNB Conference. 3:1516–1518, 2005.Google Scholar
- 10.Ljung, L., System identification: Theory for the user. Prentice-Hall PTR, Upper Saddle River, 1999.Google Scholar
- 13.Yoon, Y., Lee, M., and Soh, K., Pulse type classification by varying contact pressure. IEEE Eng. Med. Biol. Mag. 19:106–110, 2000.Google Scholar
- 14.Powis, R., and Schwartz, R., Practical Doppler ultrasound for the clinician. Williams and Wilkins, Baltimore, 1991.Google Scholar
- 15.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.Google Scholar