How artificial intelligence tools can be used to assess individual patient risk in cardiovascular disease: problems with the current methods

The author has identified three major pitfalls of these algorithms, linked to the limitation of the classical statistical approach in dealing with this kind of non linear and complex information. The pitfalls are the inability to capture the disease complexity, the inability to capture process dynamics, and the wide confidence interval of individual risk assessment.Artificial Intelligence tools can provide potential advantage in trying to overcome these limitations. The theoretical background and some application examples related to artificial neural networks and fuzzy logic have been reviewed and discussed.The use of predictive algorithms to assess individual absolute risk of cardiovascular future events is currently hampered by methodological and mathematical flaws. The use of newer approaches, such as fuzzy logic and artificial neural networks, linked to artificial intelligence, seems to better address both the challenge of increasing complexity resulting from a correlation between predisposing factors, data on the occurrence of cardiovascular events, and the prediction of future events on an individual level.In the past few years a number of algorithms for cardiovascular risk assessment has been proposed to the medical community [1-6]. Their purpose is to assist physicians in defining the risk level of an individual patient with regard to developing major cardiovascular events in the following years.These algorithms have been drawn from statistical analyses performed on longitudinal study cohorts. These analyses have taken into account events occurring in general populations undergoing adequate follow-up for a sufficient length of time. These algorithms consider a number of variables and express their results as the percentage risk of developing a major fatal or non-fatal cardiovascular event in the following 10 to 20 years. For example, if the algorithm gives origin to a 10% value, it means that 10 out of100 subjects in the reference population at a given time