Low-Cost Raman Spectroscopy Setup Combined with a Machine Learning Model

被引:0
|
作者
Domingos, Catarina [1 ]
Fantoni, Alessandro [1 ,2 ]
Fernandes, Miguel [1 ,2 ]
Fidalgo, Jorge [1 ]
Pereira, Sofia Azeredo [3 ]
机构
[1] Polytech Univ Lisbon IPL, Lisbon Sch Engn ISEL, Dept Elect Telecommun & Comp, Rua Conselheiro Emidio Navarro 1, P-1959007 Lisbon, Portugal
[2] Ctr Technol & Syst UNINOVA CTS & Associated Lab In, P-2829516 Caparica, Portugal
[3] Univ Nova Lisboa, Fac Ciencias Med, NOVA Med Sch, NMS,FCM,iNOVA4Health, P-1169056 Lisbon, Portugal
关键词
sensor; point of care; Raman spectroscopy; instrumentation; diagnosis; kidney disease; KIDNEY INJURY;
D O I
10.3390/s25030659
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
The diagnosis of kidney diseases presents significant challenges, including the reliance on variable and unstable biomarkers and the necessity for complex and expensive laboratory tests. Raman spectroscopy emerges as a promising technique for analyzing complex fluids, like urine, and detecting important disease biomarkers. However, its complexity, high cost and limited accessibility outside clinical contexts complicate its application. Moreover, the analysis of Raman spectra is a challenging and intensive task. In response to these challenges, in this study, we developed a portable, simplified and low-cost Raman system designed to acquire high-quality spectra of liquid complex samples. Using the "Starter Edition" methodology from the OpenRAMAN project, the system was optimized through laser temperature adjustments, by evaluating the laser emission spectrum under different temperatures with a spectrometer, and through adjustment of the acquisition parameters of the software used, by acquiring the ethanol spectra. The system validation was performed through the acquisition of Raman spectra from five urine samples, demonstrating its consistency and sensitivity to composition variations in urine samples. Additionally, a neural network was designed and trained using methanol and ethanol solutions. The model's hyperparameters were optimized to maximize its precision and accuracy, achieving 99.19% accuracy and 99.21% precision, with a training time of approximately 3 min, underlining the model's potential for classifying simple Raman spectra. While further system validation with more samples, a more in-depth analysis of the biomarkers present in urine and the integration with more sophisticated elements are necessary, this approach demonstrates the system characteristics of affordability and portability, making it a suitable solution for point-of-care applications and offering simplified accessibility for assessing the diseases risk outside clinical contexts.
引用
收藏
页数:22
相关论文
共 50 条
  • [21] Development of machine learning enhanced low-cost spectrophotometer for pesticide prediction
    Murathathunyaluk, S.
    Jinorose, M.
    Janpetch, K.
    Chanthapanya, N.
    Sombatsri, W.
    Wongsricha, A.
    Chawuthai, R.
    Mansouri, S. S.
    Anantpinijwatna, A.
    MEASUREMENT, 2025, 248
  • [22] Wind Power Forecasting with Machine Learning Algorithms in Low-Cost Devices
    Buestan-Andrade, Pablo Andres
    Penacoba-Yague, Mario
    Sierra-Garcia, Jesus Enrique
    Santos, Matilde
    ELECTRONICS, 2024, 13 (08)
  • [23] Addressing Low-Cost Methane Sensor Calibration Shortcomings with Machine Learning
    Kiplimo, Elijah
    Riddick, Stuart N.
    Mbua, Mercy
    Upreti, Aashish
    Anand, Abhinav
    Zimmerle, Daniel J.
    ATMOSPHERE, 2024, 15 (11)
  • [24] Discrimination of periodontal pathogens using Raman spectroscopy combined with machine learning algorithms
    Zhang, Juan
    Liu, Yiping
    Li, Hongxiao
    Cao, Shisheng
    Li, Xin
    Yin, Huijuan
    Li, Ying
    Dong, Xiaoxi
    Zhang, Xu
    JOURNAL OF INNOVATIVE OPTICAL HEALTH SCIENCES, 2022, 15 (03)
  • [25] Programmable low-cost ultrasound machine
    Shamdasani, V
    Kim, Y
    PROCEEDINGS OF THE 25TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-4: A NEW BEGINNING FOR HUMAN HEALTH, 2003, 25 : 1164 - 1167
  • [26] VERSATILE LOW-COST TESTING MACHINE
    不详
    METALLURGIA AND METAL FORMING, 1975, 42 (11): : 387 - 388
  • [27] LOW-COST DIES SAVE MACHINE
    不详
    PLASTICS WORLD, 1969, 27 (10): : 45 - &
  • [28] COUPLINGS RECLAIMED WITH LOW-COST MACHINE
    不详
    ENGINEERING MATERIALS AND DESIGN, 1975, 19 (08): : 29 - 29
  • [29] A LOW-COST AUTOMATION TRANSFER MACHINE
    BARKER, AJ
    MACHINERY AND PRODUCTION ENGINEERING, 1969, 114 (2947): : 738 - &
  • [30] MACHINE AILMENTS - LOW-COST DIAGNOSIS
    WHELAN, T
    CRAFT, J
    BRITISH PLASTICS AND RUBBER, 1978, (JUN): : 56 - 57