From Cloudiness to Clarity: Predictive Modeling for Early Diagnosis of Peritonitis in Peritoneal Dialysis (CLEAR-PD)

Peritonitis is one of the most serious complications of peritoneal dialysis (PD), potentially leading to hospitalization, catheter loss, or even death. Currently, one of the cornerstone diagnostic methods relies on the visual inspection of dialysate turbidity, which is subjective and may delay the initiation of timely treatment. The project aims to integrate physical, biochemical, and image-based diagnostic techniques to develop a machine learning (ML) algorithm capable of identifying early changes in dialysate turbidity—prior to their visual detectability. A comprehensive dataset will be compiled during the study, and the algorithm will be validated in a clinical setting. Additionally, the potential use of bacteriophages will be explored as an alternative diagnostic and therapeutic approach, particularly in cases involving antibiotic-resistant pathogens. The project will generate a large, standardized dataset to serve as a foundation for ML model training. The proposed solutions are expected to improve early peritonitis diagnostics, enhance patient survival, reduce hospitalization duration and treatment costs, and establish a basis for the development and commercialization of new digital diagnostic tools in Latvia.

Planned results

• Original research articles published in the Q1 or Q2 publications listed in the Web of Science or SCOPUS databases – 2
• Scientific databases and datasets prepared according to the FAIR principles – 1
• Project proposal submitted in a Latvian call for research and development projects – 1
• Other project results according to the specific nature of the project complementary to those listed above (including pre-prints) – 4

Scientific Team

• Kārlis Rācenis – acting lead researcher, principal investigator
• Juta Kroiča – lead researcher
• Dace Eglīte – acting researcher
• Renāte Rūta Apse – acting laboratory technician
• Laima Sevastjanova – acting research assistant
• Gatis Saknītis – acting laboratory technician
• Anna Jana Saulīte – acting researcher
• Anna Popova, Pauls Stradiņš Clinical University Hospital, Scientific institute
• Roberts Kadiķis, Institute of Electronics and Computer Science

Collaborating Partners

• Pauls Stradiņš Clinical University Hospital, Scientific institute
• Institute of Electronics and Computer Science