Use of Continuous Biomonitoring for Detection of Infectious Complications in Kidney Transplant Recipients
Overview
- Phase
- Not Applicable
- Intervention
- Not specified
- Conditions
- Kidney Transplant Infection
- Sponsor
- Institute for Clinical and Experimental Medicine
- Enrollment
- 200
- Locations
- 1
- Primary Endpoint
- Accuracy of the algorithm at detecting infections at presymptomatic stage
- Status
- Not yet recruiting
- Last Updated
- 2 years ago
Overview
Brief Summary
The goal of this observational study is to develop a machine learning algorithm for early detection of infections in kidney transplant recipients using data recorded by wearable digital health technologies.
The main questions it aims to answer are:
- What are the biometric data pattern changes in impending infections?
- What accuracy the machine learning algorithm can achieve?
Participants will be given/use their own wearable device that will record biometric data. Any infection event will be recorded and an algorithm will be trained to recognize changes in biometric data preceding symptomatic infection.
Investigators
Prof. Ondřej Viklický, M.D., Ph.D.
Head of Transplantation Center, Principal Investigator
Institute for Clinical and Experimental Medicine
Eligibility Criteria
Inclusion Criteria
- •kidney transplant recipient
- •age 18 years or more
- •kidney allograft function (eGFR based on CKD-EPI more than 15ml/min/1.73m2)
Exclusion Criteria
- •recipient of another transplanted organ
- •terminal failure of another organ (heart, liver, lung)
- •diabetes mellitus type 1
- •pregnant or breastfeeding woman
- •refusal to give informed consent
Outcomes
Primary Outcomes
Accuracy of the algorithm at detecting infections at presymptomatic stage
Time Frame: The primary endpoint will be assessed periodically throughout the study, up to 24 months.
Accuracy, sensitivity, specificity, negative and positive predictive value of the machine learning algorithm at detecting infections in presymptomatic stage in kidney transplant recipients.