Fiber-optic sensor empowered by machine learning: a promising integration for C-reactive protein sensing in biological samples

K. Cierpiak; M. Szczerska

doi:10.1117/12.3016946

20 June 2024 Fiber-optic sensor empowered by machine learning: a promising integration for C-reactive protein sensing in biological samples

K. Cierpiak, M. Szczerska

Author Affiliations +

Proceedings Volume 12999, Optical Sensing and Detection VIII; 129992A (2024) https://doi.org/10.1117/12.3016946
Event: SPIE Photonics Europe, 2024, Strasbourg, France

Conference Poster

Abstract

C-reactive protein (CRP) is a protein made by the liver in response to inflammation anywhere in the body. Early and accurate detection of CRP levels is essential for diagnosing various diseases. The proposed method uses a spectroscopy to analyze urine samples and machine learning to classify them as infected or non-infected based on CRP levels. Three machine learning models were employed: Extra Trees, Random Forest, XGBoost, K-Nearest Neighbors and Decision Tree. These models aimed to classify urine samples into two categories: infected (CRP level above 10⁻⁴ μg/mL) and non-infected (CRP level below or equal 10⁻⁴ μg/mL). The accuracy of the best model, Extra Trees is up to 68%. This method has the potential for faster and more user-friendly CRP detection compared to traditional methods.

Citation Download Citation

K. Cierpiak and M. Szczerska "Fiber-optic sensor empowered by machine learning: a promising integration for C-reactive protein sensing in biological samples", Proc. SPIE 12999, Optical Sensing and Detection VIII, 129992A (20 June 2024); https://doi.org/10.1117/12.3016946

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available