Systems and methods for processing of fundus images

A system for determining at least one recommendation for management of wellbeing of a first individual, the system comprising one or more processors and one or more storage devices storing instructions that when executed by the one or more processors cause the one or more processors to perform operations comprising:

• determining an indication of relative cardiovascular aging of the first individual,
• wherein determining an indication of relative cardiovascular aging of the first individual comprises:
• determining a degree of similarity between a predicted risk of cardiovascular disease (CVD) of the first individual and the risk of CVD for a set of individuals belonging to a chronological age bracket to which the first individual also belongs, wherein the predicted risk of CVD is determined by a deep learning model based on one or more fundus images;
• determining an average chronological age of individuals closest to the first individual in terms of predicted risk of CVD;
• determining a mean expected chronological age for a person with the predicted risk of CVD of the first individual;
• and
• determining the indication of relative cardiovascular aging of the first individual based on the determined degree of similarity, the determined average chronological age, and the determined mean expected chronological age;
• and
• determining the at least one recommendation for management of the first individual's wellbeing based at least in part on the determined indication of relative cardiovascular aging.

A computer program product for determining a recommendation for management of wellbeing of a first individual, the computer program product comprising a non-transitory computer-readable storage medium containing computer program code for:

• determining an indication of relative cardiovascular aging of the first individual, wherein determining an indication of relative cardiovascular aging of the first individual comprises:
• determining a degree of similarity between a predicted risk of cardiovascular disease (CVD) of the first individual and the risk of CVD for a set of individuals belonging to a chronological age bracket to which the first individual also belongs, wherein the predicted risk of CVD is determined by a deep learning model based on one or more fundus images;
• determining an average chronological age of individuals closest to the first individual in terms of predicted risk of CVD;
• determining a mean expected chronological age for a person with the predicted risk of CVD of the first individual;
• and
• determining the indication of relative cardiovascular aging of the first individual based on the determined degree of similarity, the determined average chronological age, and the determined mean expected chronological age;
• and
• determining the recommendation for management of the first individual's wellbeing based at least in part on the determined indication of relative cardiovascular aging.