Use of Machine-learning Algorithms, Biomarkers and Measures of Quality of Life to Personalize Medical Management of Liver and Heart Transplant Recipients

Use of Machine-learning Algorithms, Biomarkers and Measures of Quality of Life to Personalize Medical Management of Liver and Heart Transplant Recipients

This is an observational, low risk tissue based, non-pharmacological, retrospective-prospective study for adults heart and liver transplant patients, related to IRCCS Azienda Ospedaliero-Universitaria di Bologna (IRCCS AOUBO).

This clinical study is part of the national multicentric project DARE. The project has the wide overarching aim to develop digital solutions for personalized healthcare.

This study is structured in two phases: 1) a retrospective phase that aims to develop ML-based scores that can allow to predict at patient level the risk of infections, cardiovascular diseases, new onset malignancies and chronic graft dysfunction, and describing the trajectory of this risk over time; 2) a prospective phase in which we test the association of biomarkers, QoL and frailty assessments with the ML-scores applied prospectively in heart and liver transplant recipients.

Retrospective cohort Inclusion criteria Receiving a heart or liver transplantation at IRCCS AOUBO between January 2008 and December 2020.

Surviving at least 6 months after surgery Receiving at least one outpatient clinical assessment, comprising clinical evaluation, standard laboratory tests, and graft ultrasound Older than 18 years old

Exclusion criteria Unavailability of medical records in the standard data repositories of IRCCS AOUBO

Prospective cohort

Inclusion criteria Older thant 18 years old Receiving a heart or liver transplantation at least 6 months before study entry and being in active follow up at IRCCS AOUBO Obtaining informed consent

Exclusion criteria None