C-reactive protein (CRP) evaluation in human urine using optical sensor supported by machine learning.

The rapid and sensitive indicator of inflammation in the human body is C-Reactive Protein (CRP). Determination of CRP level is important in medical diagnostics because, depending on that factor, it may indicate, e.g., the occurrence of inflammation of various origins, oncological, cardiovascular, bacterial or viral events. In this study, we describe an interferometric sensor able to detect the CRP level for distinguishing between no-inflammation and inflammation states. The measurement head was made of a single mode optical fiber with a microsphere structure created at the tip. Its surface has been biofunctionalized for specific CRP bonding. Standardized CRP solutions were measured in the range of 1.9 µg/L to 333 mg/L and classified in the initial phase of the study. The real samples obtained from hospitalized patients with diagnosed Urinary Tract Infection or Urosepsis were then investigated. 27 machine learning classifiers were tested for labeling the phantom samples as normal or high CRP levels. With the use of the ExtraTreesClassifier we obtained an accuracy of 95% for the validation dataset. The results of real samples classification showed up to 100% accuracy for the validation dataset using XGB classifier.

Optical method supported by machine learning for dynamics of C-reactive protein concentrations changes detection in biological matrix samples.

In this article we present the novel spectroscopy method supported with machine learning for real-time detection of infectious agents in wastewater. In the case of infectious diseases, wastewater monitoring can be used to detect the presence of inflammation biomarkers, such as the proposed C-reactive protein, for monitoring inflammatory conditions and mass screening during epidemics for early detection in communities of concern, such as hospitals, schools, and so on. The proposed spectroscopy method supported with machine learning for real-time detection of infectious agents will eliminate the need for time-consuming processes, which contribute to reducing costs. The spectra in range 220-750 nm were used for the study. We achieve accuracy of our prediction model up to 68% with using only absorption spectrophotometer and machine learning. The use of such a set makes the method universal, due to the possibility of using many different detectors.

Optical method supported by machine learning for urinary tract infection detection and urosepsis risk assessment.

The study presents an optical method supported by machine learning for discriminating urinary tract infections from an infection capable of causing urosepsis. The method comprises spectra of spectroscopy measurement of artificial urine samples with bacteria from solid cultures of clinical E. coli strains. To provide a reliable classification of results assistance of 27 algorithms was tested. We proved that is possible to obtain up to 97% accuracy of the measurement method with the use of use of machine learning. The method was validated on urine samples from 241 patients. The advantages of the proposed solution are the simplicity of the sensor, mobility, versatility, and low cost of the test.