Peritoneal dialysis (PD) offers specific advantages over hemodialysis, enabling increased autonomy of patients with end-stage renal disease, but PD-related complications need to be detected in a timely manner. Fourier transform infrared (FTIR) spectroscopy could provide rapid and essential insights into the patients' risk profiles via molecular fingerprinting of PD effluent, an abundant waste material that is rich in biological information. In this study, we measured FTIR spectroscopic profiles in PD effluent from patients taking part in a randomized controlled trial of alanyl-glutamine addition to the PD-fluid. Principal component analysis of FTIR spectra enabled us to differentiate between effluent samples from patients immediately after completion of instillation of the PD-fluid into the patients' cavity and 4 h later as well as between patients receiving PD-fluid supplemented with 8 mM alanyl-glutamine compared with control. Moreover, feasibility of FTIR spectroscopy coupled to supervised classification algorithms to predict patient-, PD-, as well as immune-associated parameters were investigated. PD modality (manual continuous ambulatory PD (CAPD) vs. cycler-assisted automated PD (APD)), residual urine output, ultrafiltration, transport parameters, and cytokine concentrations showed high predictive potential. This study provides proof-of-principle that molecular signatures determined by FTIR spectroscopy of PD effluent, combined with machine learning, are suitable for cost-effective, high-throughput diagnostic purposes in PD.
Grunert Tom, Herzog Rebecca, Wiesenhofer Florian M, Vychytil Andreas, Ehling-Schulz Monika, Kratochwill Klaus
FTIR, machine learning, metabolites, molecular signatures, peritoneal dialysis, peritoneum, peritonitis, photonic-based diagnostics, vibrational spectroscopy