شیمى کاربردى روز

شیمى کاربردى روز

کنترل کیفیت متفورمین در نمونه‌های پودری با استفاده از تصویربرداری ابرطیفی و مدل‌های یادگیری ماشین

نوع مقاله : مقاله علمی پژوهشی

نویسندگان
دانشکده شیمی، دانشگاه صنعتی شریف، تهران، ایران
چکیده
با توجه به رشد فزاینده تولید و مصرف داروهای ژنریک در سطح جهانی و افزایش خطر ورود محصولات دارویی تقلبی و غیراستاندارد، ابداع روش‌های نوین، سریع و غیرمخرب برای کنترل کیفیت داروها از اهمیت ویژه‌ای برخوردار است. در این پژوهش، از فناوری تصویربرداری ابرطیفی در محدوده مرئی تا زیر قرمز نزدیک (Vis-NIR HSI) به‌همراه روش‌های کمومتریکس /یادگیری ماشین برای ارزیابی دوز ماده مؤثره متفورمین در نمونه‌های پودری استفاده شد. نمونه‌ها در سه دسته با دوز استاندارد(SD)، غیر استاندارد پایین(LD) و غیر استاندارد بالا (HD) تهیه شدند. پس از جمع‌آوری داده‌های تصویری ابرطیفی، از میانگین‌گیری طیفی، تحلیل مؤلفه‌های اصلی (PCA)، روش حداقل مربعات جزئی-تحلیل تمایزی (PLS-DA) و دو الگوریتم یادگیری ماشین شامل شبکه عصبی مصنوعی (ANN) و ماشین بردار پشتیبان (SVM) برای تحلیل و طبقه‌بندی داده‌ها بهره گرفته شد. نتایج نشان داد که مدل‌های کمومتریکسی، به‌ویژه شبکه عصبی مصنوعی و حداقل مربعات جزئی-تحلیل تمایزی ، توانسته‌اند سه گروه مورد نظر را با دقت و صحت بالا از یکدیگر تفکیک نمایند. تصویربرداری ابرطیفی در بازه طول‌موجی 400 تا 950 نانومتر، در کنار پردازش‌های آماری، ابزاری مؤثر و کارآمد در شناسایی کیفیت متفورمین و تمایز نمونه‌های استاندارد و غیراستاندارد فراهم کرده است.
کلیدواژه‌ها
موضوعات

عنوان مقاله English

Quality Control of Powdered Metformin Using Hyperspectral Imaging and Machine Learning Models

نویسندگان English

Fatemeh Hatefi
Zahra Bolhasani
Hadi Parastar
Department of Chemistry, Sharif University of Technology, Tehran, Iran
چکیده English

Given the global growth in the production and consumption of generic drugs and the increasing risk of counterfeit or substandard pharmaceutical products, the development of novel, rapid, and non-destructive quality control methods has become critically important. In this study, hyperspectral imaging (HSI) in the visible to near-infrared range (Vis-NIR, 400–950 nm), combined with chemometric/machine learning techniques, was employed to assess the active pharmaceutical ingredient (API) content of metformin in powder-based samples. Samples were classified into three dosage groups: standard dose (SD), low non-standard dose (LD), and high non-standard dose (HD). Hyperspectral imaging data were processed using spectral averaging, principal component analysis (PCA), partial least squares-discriminant analysis (PLS-DA), and machine learning algorithms including artificial neural network (ANN) and support vector machines (SVM). Results demonstrated that chemometric models, particularly ANN and PLS-DA, could effectively differentiate between the three sample groups with high accuracy. The combination of Vis-NIR HSI and statistical modelling proved to be a powerful tool for detecting metformin dosage levels and distinguishing standard from non-standard pharmaceutical compositions.

کلیدواژه‌ها English

Hyperspectral Imaging
Metformin
Quality Control
Chemometrics
Machine Learning
Artificial Neural Network
[1] Dunne, S., Close, H., & Shanahan, E. (2013). A review of the differences and similarities between generic drugs and their originator counterparts, including economic benefits associated with usage of generic medicines, using Ireland as a case study. BMC Pharmacology and Toxicology, 14, 1–19. 
[2] World Health Organization. (2017). WHO global surveillance and monitoring system for substandard and falsified medical products
[3] Ammassari, A., Trotta, M. P., Shalev, N., Marconi, V. C., Antinori, A., & d’Arminio Monforte, A. (2021). Comparison of demand for drugs used for COVID-19 treatment and other drugs during the early phase of the COVID-19 pandemic in Italy. JAMA Network Open, 4(2), e2037060.
[4] Ranney, M. L., Griffeth, V., & Jha, A. K. (2020). Critical supply shortages—the need for ventilators and personal protective equipment during the Covid-19 pandemic. The New England Journal of Medicine, 382(18), e41.
[5] Mohamed, H. M. (2015). Green, environment-friendly, analytical tools give insights in pharmaceuticals and cosmetics analysis. Trends in Analytical Chemistry, 66, 176–192.
[6] Przybylska, A., Gackowski, M., & Koba, M. (2021). Application of capillary electrophoresis to the analysis of bioactive compounds in herbal raw materials. Molecules, 26(8), 2135. 
[7] Gu, X., Zhang, L., Wang, Y., & Chen, H. (2023). Fast screening of biomembrane-permeable compounds in herbal medicines using bubble generation technology. Journal of Pharmaceutical Analysis, 15(3), 123-135. 
[8] Dispas, A., Sacré, P., Ziemons, E., & Hubert, P. (2022). Emerging analytical techniques for pharmaceutical quality control: Where are we in 2022? Journal of Pharmaceutical and Biomedical Analysis221, 115071.
[9] Seo, C.-S., & Shin, H.-K. (2022). Simultaneous analysis of 19 marker components for quality control of Oncheong-Eum using HPLC-DAD. Molecules, 27(9), 2992. 
[10] Zhao, X., Li, Y., Wang, J., & Zhang, R. (2023). Fast quantification of diclofenac sodium content in commercially available tablets by transmission Raman spectroscopy with PLS. Journal of Chemometrics, 37(2), e3462. 
[11] Wu, X., Chen, B., Wang, Y., & Li, S. (2012). Optimization of a solid phase extraction and hydrophilic interaction liquid chromatography-tandem mass spectrometry method for the determination of metformin in dietary supplements and herbal medicines. Food Chemistry, 133(2), 482-488.
[12] Deidda, R., Schembri, S., Bucaria, F., & Calà, P. (2019). Vibrational spectroscopy in analysis of pharmaceuticals: Critical review of innovative portable and handheld NIR and Raman spectrophotometers. Trends in Analytical Chemistry, 114, 251-259. 
[13] Mirzaei, N., Rezaei, V., & Aibaghi, B. (2018). Preconcentration and determination of diazepam in pharmaceutical and biological samples by graphene oxide based on dispersive solid phase microextraction. Applied Chemistry Today, 14(51), 21-34. (in Persian)
[14] Malarsoli, F. (2025). Development and Step-by-Step Optimization of the HPLC Method with Dilute-and-Shoot Sample Preparation Technique for Determination of Benidipine Hydrochloride in Pharmaceutical and Biological Samples. Applied Chemistry Today, 20(74), 139-160. (in Persian)
[15] Triggle, C. R., Mohammed, I., Bshesh, K., Marei, I., & Ye, K. (2022). Metformin: Is it a drug for all reasons and diseases? Metabolism, 133, 155223. 
[16] Mubeen, G., & Noor, K. (2009). Spectrophotometric method for analysis of metformin hydrochloride. Indian Journal of Pharmaceutical Sciences, 71(1), 100-102. 
[17] Pyzowski, J., Brzezińska, E., & Kościelniak, P. (2017). Fast and convenient NIR spectroscopy procedure for determination of metformin hydrochloride in tablets. Journal of Applied Spectroscopy, 84(4), 710-715. 
[18] Norris, K. (1996). History of NIR. Journal of Near Infrared Spectroscopy, 4(1), 31-37. 
[19] Harthcock, M., & Atkin, S. (1988). Imaging with functional group maps using infrared microspectroscopy. Applied Spectroscopy, 42(3), 449-455.
[20] Mehta, N., Shaik, A., & Parker, A. (2018). Single-cell analysis using hyperspectral imaging modalities. Journal of Biomechanical Engineering, 140(2), 020802. 
[21] Tan, M. I. S. H., Abdullah, A. Z., Rahman, N. A., & Osman, R. (2021). Ganoderma boninense disease detection by near-infrared spectroscopy classification: A review. Sensors, 21(9), 3052.
[22] Sharifizadeh, G., Asghari, A., & Rajabi, M. (2019). Simultaneous analysis of Al(III), Cu(II) and Fe(II) ions in aqueous solutions: using partial least squares (PLS) method-based on UV-Vis spectrophotometry. Applied Chemistry Today, 14(50), 193–208. (in Persian)
[23] Khaje Sharifi, H., & Soleimanzadegan, S. (2013). Partial least squares method for simultaneous spectrophotometric determination of uracil and 5-fluorouracil in spiked biological samples. Applied Chemistry Today, 7(25), 31–38. (in Persian)
[24] Niazi, A., & Bashiri far, A. (2017). Simultaneous Determination Spectrophotometric of New fushin and Victoria blue using chemometric methods. Applied Chemistry Today, 12(43), 137–150. (in Persian)
[25] The United States Pharmacopeia,Metformin Hydrochloride Extended-Release Tablets, https://www.uspnf.com/sites/default/files/usp_pdf/EN/USPNF/revisions/metformin-hcl-ert-sept18-pending-nitr.pdf , 2018 (accessed April 2024).
[26] Bro, R., & Smilde, A. K. (2014). Principal component analysis. Analytical Methods, 6(9), 2812-2831. 
[27] Oliveira, A. D. D., Silva, L. E., Castro, E. V. R., & Filho, J. C. (2018). Use of infrared spectroscopy and near infrared hyperspectral images to evaluate effects of different chemical agents on PET bottle surface. Materials Research, 21(5), e20170949.
[28] Jain, A. K., Duin, R. P. W., & Mao, J. (2000). Statistical pattern recognition: A review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(1), 4-37. 
[29] Ballabio, D., & Consonni, V. (2013). Classification tools in chemistry. Part 1: Linear models. PLS-DA. Analytical Methods, 5(16), 3790-3798. 
[30] Kumar, K. (2017). Principal component analysis: Most favourite tool in chemometrics. Resonance, 22(8), 747-759. 
[31] Brereton, R. G., & Lloyd, G. R. (2010). Support vector machines for classification and regression. Analyst, 135(2), 230-267. 
[32] Cogdill, R. P., & Dardenne, P. (2004). Kernel chemometrics: An introduction to support vector machines. In Near Infrared Spectroscopy: Proceedings of the 11th International Conference (pp. 165-170). IM Publications.
[33] Pavia, D. L., Lampman, G. M., Kriz, G. S., & Vyvyan, J. R. (2015). Introduction to spectroscopy (5th ed., Chapter 2, pp. ۳۱۸۴). Cengage Learning.
[34] Bolhassani, Z., Aghaei, A., & Parastar, H. (2025). Quantification of metformin in pharmaceutical formulations using Vis-SWNIR hyperspectral imaging combined with multivariate curve resolution. Chemometrics and Intelligent Laboratory Systems, 250, 104918.
[35] Xia, Y., Cen, H., He, Y., & Xu, L. (2021). Rapid quantification and visualization of metformin hydrochloride tablets using hyperspectral imaging. Chemometrics and Intelligent Laboratory Systems, 212, 104287.