JMIR Publications

ABSTRACT

Background:

Current urinary and drainage catheter systems collect fluids for visual inspection or manual sampling, offering limited diagnostic value while being labor-intensive and prone to error. Machine learning (ML) has the potential to automate the analysis of these fluids. However, existing methods rely on complex preprocessing steps, which hinder real-time analysis.

Objective:

To develop and evaluate a fully automated, real-time diagnostic approach for smart urinary and drainage catheter systems by leveraging spectral data and machine learning to differentiate pathological from healthy excreted fluids without the need for manual preprocessing.

Methods:

This study proposes a novel and fully automated approach for smart urinary and drainage catheter systems that utilizes spectra and ML for direct feature extraction from excreted fluids, enabling real-time analysis. 454 surgical drainage fluid samples (from 181 patients) and 401 urine catheter samples (from 168 patients) were analyzed using smart catheters and drains equipped with compact mini-spectrometer sensors. The collected spectral data was fed into three different ML models: a Random Forest (RF), a Partial Least Squares Discriminant Analysis regression (PLS-DA), and a Convolutional Neural Network (CNN). Each model aimed to extract features and differentiate between pathological and healthy urine and drainage samples based on the various biomarkers available from previously conducted laboratory analyses.

Results:

All three approaches (RF, PLS-DA, and CNN) achieved promising results, demonstrating the potential of the overall approach. In particular, the CNN models trained on the drainage biomarkers hemoglobin and bilirubin achieved the best results. Matthew's correlation coefficient (MCC) scores of 0.83 and 0.81 were measured for hemoglobin and bilirubin, respectively, when differentiating between pathological and healthy samples based on the extracted spectral features.

Conclusions:

This work demonstrates the potential of spectral-driven ML for smart urinary and drainage catheter systems. This approach offers a real-time, non-invasive method for analyzing excreted fluids, paving the way for improved diagnostics and personalized patient care. Further research will explore the optimal machine learning model for this application.