本研究利用穆勒矩陣偏振測量技術結合XGBoost算法，對人體指尖生物組織在非侵入性血糖感測之預測達到相當不錯的結果。實驗中使用660nm雷射光進行偏振測量以及角度優化以增強測量能力，多方面的掌握線性雙折射（LB）、圓雙折射（CB）、線二色性（LD）、圓二色性（CD）和偏振度（DoP）等特性。先用假體作為模擬生物組織的干擾偏振特性，然後基於XGBoost迴歸模型配合相關矩陣進行特徵工程，在假體和人體測量中均顯示出相吻合的趨勢，在假體混合物中血糖濃度的預測結果為R² = 0.96，平均絕對相對差異（MARD）為8.67%，在人類血糖濃度的預測中，使用特徵R1、m32、45_S1、45_S2、R_S1、DoLPR、Stol達到了均方根誤差（RMSEP）為5.86 mg/dL，R²為0.89，平均絕對相對差異（MARD）為2.92%，研究最終結論發現，在使用機器學習進行人體血糖預測時，CB、CD和DoP特性是對偏振測量系統至關重要的光學偏振特性，這對於未來的發展提供很重要的信息。

This study achieved significant predictive results using Mueller Matrix Polarimetry combined with the XGBoost algorithm for non-invasive glucose sensing of biological tissues on human fingertips. The experiment used a 660 nm laser in polarimetry and angle optimization to enhance measurement capabilities, comprehensively obtaining properties including Linear Birefringence (LB), Circular Birefringence (CB), linear dichroism (LD), Circular Dichroism (CD), and Degree of Polarization (DoP). Using phantom solutions simulated the interference properties of biological tissue polarization measurements. The XGBoost regression model, with feature engineering based on correlation matrices, showed consistent trends in both phantom and human measurements. The prediction results for glucose concentration in phantom mixtures were R² = 0.96 and Mean Absolute Relative Difference (MARD) = 8.67%. The prediction of human glucose concentration achieved RMSEP of 5.86 mg/dL, R² of 0.89, and MARD of 2.92% using the features R1, m32, 45_S1, 45_S2, R_S1, DoLPR, and Stol. In predicting human blood glucose levels using machine learning, the crucial optical polarization properties CB, CD, DoP, and Stol are crucial optical polarization properties for a Polarimetry system, which is essential for future development.

[1] L. Tang, S. J. Chang, C.-J. Chen, and J.-T. Liu, "Non-Invasive Blood Glucose Monitoring Technology: A Review," Sensors, vol. 20, no. 23, p. 6925, 2020. [Online]. Available: https://www.mdpi.com/1424-8220/20/23/6925.
[2] N. Ghosh et al., "Mueller matrix decomposition for polarized light assessment of biological tissues," Journal of biophotonics, vol. 2, no. 3, pp. 145-156, 2009.
[3] H. He et al., "Mueller matrix polarimetry—an emerging new tool for characterizing the microstructural feature of complex biological specimen," Journal of Lightwave Technology, vol. 37, no. 11, pp. 2534-2548, 2018.
[4] M. D. Singh, N. Ghosh, and I. A. Vitkin, "Mueller matrix polarimetry in biomedicine: enabling technology, biomedical applications, and future prospects," in Polarized Light in Biomedical Imaging and Sensing: Clinical and Preclinical Applications: Springer, 2022, pp. 61-103.
[5] L.-H. Lin, Y.-L. Lo, C.-C. Liao, and J.-X. Lin, "Optical detection of glucose concentration in samples with scattering particles," Applied optics, vol. 54, no. 35, pp. 10425-10431, 2015.
[6] Q.-H. Phan and Y.-L. Lo, "Differential Mueller matrix polarimetry technique for non-invasive measurement of glucose concentration on human fingertip," Optics Express, vol. 25, no. 13, pp. 15179-15187, 2017.
[7] T.-L. Chen, Y.-L. Lo, C.-C. Liao, and Q.-H. Phan, "Noninvasive measurement of glucose concentration on human fingertip by optical coherence tomography," Journal of biomedical optics, vol. 23, no. 4, pp. 047001-047001, 2018.
[8] P. Mukherjee, N. Hagen, and Y. Otani, "Glucose sensing in the presence of scattering by analyzing a partial Mueller matrix," Optik, vol. 180, pp. 775-781, 2019.
[9] Q.-H. Phan and Y.-L. Lo, "Stokes-Mueller matrix polarimetry system for glucose sensing," Optics and Lasers in Engineering, vol. 92, pp. 120-128, 2017.
[10] C.-C. Tsai, Y.-L. Lo, C.-M. Chang, and P.-L. Huang, "Characterization of Mean Absorbance of Anisotropic Turbid Media Using Stokes-Mueller Matrix Polarimetry Approach," IEEE Transactions on Instrumentation and Measurement, 2023.
[11] P.-L. Huang, "Measurement of Mean Absorbance and Anisotropic Optical Properties of Glucose by Using Mueller Matrix Polarimetry," Master, Department of Mechanical Engineering, National Cheng Kung University, Tainan City, 2022. [Online]. Available: https://hdl.handle.net/11296/7ews9h
[12] M. Shokrekhodaei, D. P. Cistola, R. C. Roberts, and S. Quinones, "Non-invasive glucose monitoring using optical sensor and machine learning techniques for diabetes applications," IEEE Access, vol. 9, pp. 73029-73045, 2021.
[13] T.-N. Luu, T.-V. Nguyen, N.-T. Huynh, Q.-H. Phan, and T.-H. Le, "Polarimetric imaging combining optical parameters for classification of mice non-melanoma skin cancer tissue using machine learning," Heliyon, vol. 9, no. 11, 2023.
[14] N. T. Luu, T.-H. Le, Q.-H. Phan, and T.-T.-H. Pham, "Characterization of Mueller matrix elements for classifying human skin cancer utilizing random forest algorithm," Journal of biomedical optics, vol. 26, no. 7, pp. 075001-075001, 2021.
[15] Q.-H. Phan, C.-Y. Han, C.-H. Lien, and T.-T.-H. Pham, "Dual-retarder Mueller polarimetry system for extraction of optical properties of serum albumin protein media," Sensors, vol. 21, no. 10, p. 3442, 2021.
[16] J. Li, G. Yao, and L. V. Wang, "Degree of polarization in laser speckles from turbid media: Implications in tissue optics," Journal of Biomedical Optics, vol. 7, no. 3, pp. 307-312, 2002.
[17] J. Lu et al., "Tailoring chiral optical properties by femtosecond laser direct writing in silica," Light: Science & Applications, vol. 12, no. 1, p. 46, 2023.
[18] J. Kobayashi and T. Asahi, "Development of HAUP and its applications to various kinds of solids," in Complex Mediums, 2000, vol. 4097: SPIE, pp. 25-39.
[19] J. Schellman and H. P. Jensen, "Optical spectroscopy of oriented molecules," Chemical Reviews, vol. 87, no. 6, pp. 1359-1399, 1987.
[20] O. Arteaga and A. Canillas, "Analytic inversion of the Mueller-Jones polarization matrices for homogeneous media," Optics letters, vol. 35, no. 4, pp. 559-561, 2010.
[21] Y.-L. Lo and T.-C. Yu, "A polarimetric glucose sensor using a liquid-crystal polarization modulator driven by a sinusoidal signal," Optics communications, vol. 259, no. 1, pp. 40-48, 2006.
[22] T.-T.-H. Pham and Y.-L. Lo, "Extraction of effective parameters of turbid media utilizing the Mueller matrix approach: study of glucose sensing," Journal of biomedical optics, vol. 17, no. 9, pp. 097002-097002, 2012.
[23] R. Azzam, "Photopolarimetric measurement of the Mueller matrix by Fourier analysis of a single detected signal," Optics Letters, vol. 2, no. 6, pp. 148-150, 1978.
[24] Y. Shimojo, T. Nishimura, H. Hazama, T. Ozawa, and K. Awazu, "Measurement of absorption and reduced scattering coefficients in Asian human epidermis, dermis, and subcutaneous fat tissues in the 400-to 1100-nm wavelength range for optical penetration depth and energy deposition analysis," Journal of biomedical optics, vol. 25, no. 4, pp. 045002-045002, 2020.
[25] J. Bruulsema et al., "Correlation between blood glucose concentration in diabetics and noninvasively measured tissue optical scattering coefficient," Optics letters, vol. 22, no. 3, pp. 190-192, 1997.
[26] O. Amir et al., "Continuous noninvasive glucose monitoring technology based on “occlusion spectroscopy”," ed: SAGE Publications, 2007.
[27] R. Ossikovski, "Differential matrix formalism for depolarizing anisotropic media," Optics letters, vol. 36, no. 12, pp. 2330-2332, 2011.
[28] T. G. Mayerhöfer, S. Pahlow, and J. Popp, "The Bouguer‐Beer‐Lambert law: Shining light on the obscure," ChemPhysChem, vol. 21, no. 18, pp. 2029-2046, 2020.
[29] Y. Shindo, M. Nakagawa, and Y. Ohmi, "On the problems of CD spectropolarimeters. II: Artifacts in CD spectrometers," Applied spectroscopy, vol. 39, no. 5, pp. 860-868, 1985.
[30] J. Chue-Sang et al., "Optical phantoms for biomedical polarimetry: a review," Journal of biomedical optics, vol. 24, no. 3, pp. 030901-030901, 2019.
[31] N. Ghosh and I. A. Vitkin, "Tissue polarimetry: concepts, challenges, applications, and outlook," Journal of biomedical optics, vol. 16, no. 11, pp. 110801-110801-29, 2011.
[32] C. He, H. He, J. Chang, B. Chen, H. Ma, and M. J. Booth, "Polarisation optics for biomedical and clinical applications: a review," Light: Science & Applications, vol. 10, no. 1, p. 194, 2021.
[33] B. Kunnen, C. Macdonald, A. Doronin, S. Jacques, M. Eccles, and I. Meglinski, "Application of circularly polarized light for non‐invasive diagnosis of cancerous tissues and turbid tissue‐like scattering media," Journal of biophotonics, vol. 8, no. 4, pp. 317-323, 2015.
[34] N. Nishizawa, B. Al‐Qadi, and T. Kuchimaru, "Angular optimization for cancer identification with circularly polarized light," Journal of Biophotonics, vol. 14, no. 3, p. e202000380, 2021.
[35] K. Laxmikant, R. Bhuvaneswari, and B. Natarajan, "An efficient approach to detect diabetes using XGBoost classifier," in 2023 Winter Summit on Smart Computing and Networks (WiSSCoN), 2023: IEEE, pp. 1-8.
[36] M. Li, X. Fu, and D. Li, "Diabetes prediction based on XGBoost algorithm," in IOP conference series: materials science and engineering, 2020, vol. 768, no. 7: IOP Publishing, p. 072093.
[37] M. Awad and S. Fraihat, "Recursive feature elimination with cross-validation with decision tree: Feature selection method for machine learning-based intrusion detection systems," Journal of Sensor and Actuator Networks, vol. 12, no. 5, p. 67, 2023.
[38] W. Dong, Y. Huang, B. Lehane, and G. Ma, "XGBoost algorithm-based prediction of concrete electrical resistivity for structural health monitoring," Automation in Construction, vol. 114, p. 103155, 2020.
[39] T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, "Optuna: A next-generation hyperparameter optimization framework," in Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, 2019, pp. 2623-2631.
[40] C. Y. Freytes et al., "Recursive Feature Elimination with Cross Validation for Alzheimer’s Disease Classification using Cognitive Exam Scores," in 2023 Intelligent Methods, Systems, and Applications (IMSA), 2023: IEEE, pp. 327-332.
[41] T. L. Troy and S. N. Thennadil, "Optical properties of human skin in the near infrared wavelength range of 1000 to 2200 nm," Journal of biomedical optics, vol. 6, no. 2, pp. 167-176, 2001.
[42] M. F. Wood, A. Rohani, R. Ghazalah, I. A. Vitkin, and R. Pawluczyk, "Multivariate analysis methods for spectroscopic blood analysis," in Biomedical Vibrational Spectroscopy V: Advances in Research and Industry, 2012, vol. 8219: SPIE, pp. 50-58.
[43] M. F. Wood, D. Côté, and I. A. Vitkin, "Combined optical intensity and polarization methodology for analyte concentration determination in simulated optically clear and turbid biological media," Journal of Biomedical Optics, vol. 13, no. 4, pp. 044037-044037-9, 2008.
[44] B. D. Cameron and G. L. Cote, "Noninvasive glucose sensing utilizing a digital closed-loop polarimetric approach," IEEE Transactions on Biomedical Engineering, vol. 44, no. 12, pp. 1221-1227, 1997.
[45] C. Stark, C. A. C. Arrieta, R. Behroozian, B. Redmer, F. Fiedler, and S. Müller, "Broadband polarimetric glucose determination in protein containing media using characteristic optical rotatory dispersion," Biomedical Optics Express, vol. 10, no. 12, pp. 6340-6350, 2019.
[46] E. Menguc and S. Helhel, "Relationship between human glucose level and optical de/polarization information in 600 nm–800 nm wavelength region," in 2019 PhotonIcs & Electromagnetics Research Symposium-Spring (PIERS-Spring), 2019: IEEE, pp. 4343-4347.
[47] D. Derdak, M. Poor, S. Kunsági-Máté, and B. Lemli, "Interaction of amphotericin B with human and bovine serum albumins: A fluorescence polarization study," Chemical Physics Letters, vol. 724, pp. 13-17, 2019.
[48] J. Solanki, O. P. Choudhary, P. Sen, and J. T. Andrews, "Polarization sensitive optical low-coherence reflectometry for blood glucose monitoring in human subjects," Review of Scientific Instruments, vol. 84, no. 7, 2013.
[49] R. M. O’brien, "A caution regarding rules of thumb for variance inflation factors," Quality & quantity, vol. 41, pp. 673-690, 2007.
[50] A. Miles and B. Wallace, "Circular dichroism spectroscopy for protein characterization: biopharmaceutical applications," in Biophysical characterization of proteins in developing biopharmaceuticals: Elsevier, 2015, pp. 109-137.
[51] M. Goodarzi, M. Pornour, A. Kazemnejad, and B. Ranjbar, "Application of Circular Dichroism Spectropolarimetry for Discrimination between Type 2 Diabetic Patients and the Control Group," Biomacromolecular Journal, vol. 6, no. 1, pp. 64-75, 2020.