Multiple Linear Regression Model of Blood Oxygen Saturation

  • Jinghao Yao Shenyang Aerospace University
  • Yuhan Gao Shenyang Aerospace University
  • Xueqing Dong Shenyang Aerospace University
DOI: https://doi.org/10.18686/aem.v11i1.216
Keywords: Standardized Regression, Neural Network

Abstract

We used standardized regression analysis to analyze the influence of age and recent smoking status on blood oxygen saturation. We found that blood oxygen saturation was negatively correlated with age and recent smoking status, but whether smoking had a greater influence on blood oxygen saturation than age. In order to further explore whether age and recent smoking status could jointly affect oxygen saturation of blood, we used k-means clustering algorithm and took age as the control variable to conduct clustering analysis. Is obtained by polynomial fitting, and then the blood oxygen saturation under all ages about age, smoking status of recent expression of partial derivatives of recent smoking status, get the following conclusion: smoking is oxygen desaturation, and compared with the young, the elderly smoking more effect on the blood oxygen saturation degree, are more likely to suffer from cardiovascular disease.

When the regression results were tested for significance, the significance of all variables was investigated, and it was found that only age and current smoking status were significant for oxygen saturation, while BMI and gender showed no difference from zero in T test, indicating that oxygen saturation was not affected by BMI and gender. Then, taking oxygen saturation as the dependent variable and age and current smoking status as independent variables, the spline interpolation method with the best fitting effect was found, and its expression was given in the text.

References

[1] Zhang Z, Pi Z, Liu B. TROIKA: A general framework for heart rate monitoring using wrist-type photoplethysmographic signals during intensive physical exercise[J]. Biomedical Engineering, IEEE Transactions on, 2015, 62(2): 522-531.

[2] Sun X, Yang P, Li Y, et al. Robust heart beat detection from photo plethysmography interlaced with motion artifacts based on empirical mode decomposition [C] Biomedical and Health Informatics (BHI), 2012 IEEE-EMBS International Conference on. IEEE, 2012: 775-778.

[3] Wei, H.L., Billings, S.A., Liu, J.J., Time-varying parametric modelling and time-dependent spectral characterisation with applications to EEG signals using multiwavelets [J]. International Journal of Modelling, Identification and Control, 2010, 9(3): 215-224.

[4] Mallat, S.G., A theory for multiresolution signal decomposition: the wavelet representation[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1989, 11(7): 674-693.
Published
2022-03-29
Issue
Vol 11 No 1 (2022)
Section
Original Research Article

Copyright (c) 2022 Jinghao Yao

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Authors submitting to USP journals agree to publish their manuscript under the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0) where authors agree to allow third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit, and that in the event of reuse or distribution, the terms of this license are made clear

Authors retain copyright of their work, with first publication rights (online and print) granted to Universe Scientific Publishing or the owner of the journal in question.