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.
Sepsis and cancer are some of the causes of morbidity and mortality in hospitals. Prompt detection and administration of the appropriate drug targeting the correct causative agent increases the chance of patient survival. The study presents an optical method supported by machine learning for discriminating urinary tract infections from an infection capable of causing urosepsis and urinary changes suggestive of bladder cancer. The method comprises spectra of spectroscopy measurement of patients' urine samples with: urinary tract infection, urosepsis and bladder cancer. To provide reliable classification of results assistance of 27 algorithms were tested. We proved that is possible to obtain up to 95% accuracy of the measurement method with the use of machine learning. The method was validated on urine samples from 93 patients. The advantages of the proposed solution are the simplicity of the sensor, mobility, versatility, and low cost of the test.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
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.
The alert did not successfully save. Please try again later.
P. Sokolowski, P. Wityk, K. Cierpiak, M. Babińska, W. Graczyk, B. Krawczyk, M. Markuszewski, M. Szczerska, "Optical method supported by machine learning for urinary tract infections discrimination and bladder cancer detection.," Proc. SPIE 12999, Optical Sensing and Detection VIII, 129992B (20 June 2024); https://doi.org/10.1117/12.3017050