Email this article 
Development of a portable spectrophotometer using artificial neural networks for non-invasive determination of glycated hemoglobin in blood by Raman spectroscopy
- Authors: Poliker E.E.1, Zemskikh B.L.1, Koshechkin K.A.1
-
Affiliations:
- I.M. Sechenov First Moscow State Medical University
- Issue: Vol 4, No 1S (2023)
- Pages: 102-104
- Section: Conference proceedings
- URL: https://jdigitaldiagnostics.com/DD/article/view/430359
- DOI: https://doi.org/10.17816/DD430359
- ID: 430359
Cite item
Full Text
Abstract
BACKGROUND: Non-invasive diagnosis of diabetes is one of the major problems of contemporary medicine. The system being planned could be a new technology for measuring hemoglobin A1c (HbA1c) accurately and non-invasively. Therefore, a series of studies are to be conducted to assess the efficiency of the method under study and determine its potential for medical diagnosis and monitoring of HbA1c.
AIMS:
- Investigation of the feasibility of Raman spectroscopy for non-invasive measurement of HbA1c.
- Development and design of a portable analyzer using this technology.
- Assessment of the efficiency and accuracy of the developed device.
METHODS: Neural network creation requires collecting a training sample of measurements for subsequent application of TensorFlow library tools and performing laboratory measurements to calibrate the system for determining HbA1c. The device will use a 785-nm laser to take spectra according to the Raman spectroscopy. The obtained data will be fed to the input of the neural network based on the architecture of convolutional neural networks. Experiments will be conducted to train the model to determine the accuracy and efficiency of the device. A two-step data collection procedure is planned. First, a preliminary test will be done on 50 patients to see how the proposed method handles different age and gender groups and different HbA1c levels. Later, the data will continue to be collected on a larger scale, including patients with different types of diabetes and healthy individuals. Data will be collected using a portable spectrophotometer and monitored by high-performance liquid chromatography. Various metrics will be used to assess the efficiency and accuracy of the device such as accuracy, precision, recall, and F1-score.
RESULTS: An analysis of the available literature was conducted and the following conclusions were drawn. In addition, a neural network model was developed using HbA1c measurements. Currently, our model is optimized to improve the accuracy and reliability of the results.
CONCLUSIONS: The non-invasive Raman spectroscopy-based method has several advantages in measuring HbA1c levels. The procedure is faster and non-traumatic, and HbA1c levels can be monitored continuously. In particular, the non-invasive method eliminates errors associated with protein leakage outside the bloodstream.
Full Text
BACKGROUND: Non-invasive diagnosis of diabetes is one of the major problems of contemporary medicine. The system being planned could be a new technology for measuring hemoglobin A1c (HbA1c) accurately and non-invasively. Therefore, a series of studies are to be conducted to assess the efficiency of the method under study and determine its potential for medical diagnosis and monitoring of HbA1c.
AIMS:
- Investigation of the feasibility of Raman spectroscopy for non-invasive measurement of HbA1c.
- Development and design of a portable analyzer using this technology.
- Assessment of the efficiency and accuracy of the developed device.
METHODS: Neural network creation requires collecting a training sample of measurements for subsequent application of TensorFlow library tools and performing laboratory measurements to calibrate the system for determining HbA1c. The device will use a 785-nm laser to take spectra according to the Raman spectroscopy. The obtained data will be fed to the input of the neural network based on the architecture of convolutional neural networks. Experiments will be conducted to train the model to determine the accuracy and efficiency of the device. A two-step data collection procedure is planned. First, a preliminary test will be done on 50 patients to see how the proposed method handles different age and gender groups and different HbA1c levels. Later, the data will continue to be collected on a larger scale, including patients with different types of diabetes and healthy individuals. Data will be collected using a portable spectrophotometer and monitored by high-performance liquid chromatography. Various metrics will be used to assess the efficiency and accuracy of the device such as accuracy, precision, recall, and F1-score.
RESULTS: An analysis of the available literature was conducted and the following conclusions were drawn. In addition, a neural network model was developed using HbA1c measurements. Currently, our model is optimized to improve the accuracy and reliability of the results.
CONCLUSIONS: The non-invasive Raman spectroscopy-based method has several advantages in measuring HbA1c levels. The procedure is faster and non-traumatic, and HbA1c levels can be monitored continuously. In particular, the non-invasive method eliminates errors associated with protein leakage outside the bloodstream.
About the authors
Ekaterina E. Poliker
I.M. Sechenov First Moscow State Medical University
Author for correspondence.
Email: katepoliker@gmail.com
ORCID iD: 0000-0002-9610-4511
Russian Federation, Moscow
Boris L. Zemskikh
I.M. Sechenov First Moscow State Medical University
Email: boriama@yandex.ru
ORCID iD: 0009-0002-1874-0157
Russian Federation, Moscow
Konstantin A. Koshechkin
I.M. Sechenov First Moscow State Medical University
Email: koshechkin_k_a@staff.sechenov.ru
ORCID iD: 0000-0001-7309-2215
Russian Federation, Moscow
References
- Qui Y, Hang Y, Xiaoliang S, et al. Raman Spectroscopy for Non-invasive, Real-time Hemoglobin A1c Monitoring. Scientific Reports. 2019;9:1–9.
- Chengjian Y, Xinyang W, Haibo X, et al. Raman spectroscopy-based noninvasive glycated hemoglobin detection in blood samples: A machine learning approach. Analytical Chemistry. 2021;93(7):3273–3279.
- Demircioglu N, Erdogan I, Ersoy YE, Abbasoglu AA. Raman spectroscopy for the non-invasive detection of glycated haemoglobin: A systematic review. Advances in Clinical Chemistry. 2019;88:71–90.
- Zhang J, et al. Deep learning-based automatic detection of pulmonary nodules on CT images with TensorFlow. Journal of X-Ray Science and Technology. 2018;26(3):427–434.
- Chen L, Wang J, Yan X, Chen H, Ni X. Non-invasive measurement of hemoglobin A1c using Raman spectroscopy. Analytical Methods. 2019;11(37):4743–4750.
- Trenerry MI, et al. Validation of high-performance liquid chromatography assays for determination of glycated hemoglobin in diabetic studies. Clinica Chimica Acta. 1996;246(1–2):91–102.
- Rüdiger S, Etzrodt T. Noninvasive Raman Spectroscopy Detection of Diabetes: Investigation of In Vivo Skin Perfusion and In Vitro Blood Samples. Journal of Diabetes Science and Technology. 2011;5(2):1153–1162. doi: 10.1177/19322968110050024
- Rashid MM, et al. Exploring the Potential of Non-invasive Raman Spectroscopy in Monitoring Serum Glycated Haemoglobin in Patients with Type II Diabetes Mellitus. Journal of Spectroscopy. 2016;2016:1–10.
Supplementary files
