The aim of this single center observational study is to determine the feasibility of using non-invasive imaging methods, including smartphone photography and infrared thermography, for detecting of DLIs in LVAD patients in terms of severity, extent and natural healing process.
Observational data of the driveline exit of LVAD patients will be collected during a follow-up period of 26 weeks. Two non-invasive imaging methods will be used. Smartphone photos will be taken weekly by the patient during routine wound care in the home environment. In case the patient is admitted for driveline infection, infrared thermographic (IRT) photography will be used to make thermographic photos of the driveline exit and the abdominal area of the subcutaneous driveline. Furthermore, existing smartphone images and diagnostic data regarding prior DLI status will be obtained from the electronic patient records. Imaging data will additionally be retrospectively analyzed using artificial intelligence (AI) and machine learning for the development of a predictive AI model.
Study Type
OBSERVATIONAL
Enrollment
70
Erasmus MC
Rotterdam, Netherlands
Extent and severity of driveline infections in LVAD patients using non-invasive imaging
Assess the extent, severity, and healing process of LVAD driveline infections in patients on LVAD support
Time frame: 26 weeks
Driveline exit healing process and risk of infection of the LVAD driveline
Assess the healing process of the driveline exit using non-invasive imaging (smartphone and thermographic)
Time frame: 26
Sceptic complications
Occurance of systemic infection, positive blood cultures, and VAD-related infections.
Time frame: 26 weeks
Machine learning model for predicting DLIs.
Assess whether a machine learning model can be developed and validated based on smartphone photography and IRT to predict the occurrence of DLIs.
Time frame: 26 weeks
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.