Proposal of statistical twin as transition to full digital twin technology for cardiovascular interventions.

OBJECTIVES:We introduce Statistical Twin as aggregates of multiple virtual patients' data throughout the treatment at any chosen timepoint. The aim of this manuscript is to provide the proof-of-concept of Statistical Twin by evaluating the feasibility of detection of distinctive aggregates of patients throughout the perioperative trajectory (prerequisite for development of Statistical Twin). METHODS:We used a retrospective validated cohort of all-comers with mitral valve disease treated (2014-2020) at tertiary academic hospital. The end-point was overall survival from decision of the heart team. We applied two-steps cluster analysis to detect distinct aggregated of virtual patients throughout the process of care. RESULTS:Cluster procedure resulted in five distant clusters with relatively equal number of patients. Effects of the treatment (Surgery, Transcatheter or Optimal Medical Therapy on survival were: for Optimal Medical Therapy expected survival ranged from 95-96% in 30 days to 58-75% in 10 years independent from baseline characteristics. However, for transcatheter interventions five years survival was 60-92% and was dependant from the initial characteristic of virtual patient. Furthermore, survival for uncomplicated and normal duration of surgery was higher through all observation period. The aggregated virtual patients of cluster 5 would have better survival rate at all times if intervention would be done by a dedicated surgeon. CONCLUSIONS:It is possible to detect distinctive aggregates of virtual patients based on baseline characteristics and to capture the impact of perioperative events, external and other factors at multiple timepoints throughout the postoperative phase.