Search

Artificial intelligence is able to read and interpret Ecg traces quickly and precisely, increasing the diagnostic capacity and offering the possibility of anticipating preventive therapies. However, there is no evidence on the clinical utility and cost-effectiveness of certain practical applications. In fact, the literature shows the prognostic importance in favor of prevention, but clear evidence is not available that correcting strokes, embolisms, heart failure early improves quality and life span of patients.

This article is about current challenges to evidence-based medicine (EMB) in Italy. The authors, who share a 20-year commitment to the field of clinical research, discuss what they define as a phase of "stagnation" in practicing and teaching methods and research tactics, both in clinical and academic settings. Early success of EBM cultural movement was not persistent. The authors reason about how the teaching of EBM has remained a niche, concerning few professionals compared to the needs of the country. The authors identify some reasons that might have led to inconsistent attention to research methodology and address ways to strengthen the contribution of academic medicine to clinical research.

Decisional support systems based on machine learning (ML) in medicine are gaining a growing interest as some recent articles have highlighted the high diagnostic accuracy exhibited by these systems in specific medical contexts. However, it is implausible that any potential advantage can be obtained without some potential drawbacks. In light of the current gaps in medical research about the side effects of the application of these new AI systems in medical practice, in this article we summarize the main unexpected consequences that may result from the widespread application of "oracular" systems, that is highly accurate systems that cannot give reasonable explanations of their advice as those endowed with predictive models developed with ML techniques usually are. These consequences range from the intrinsic uncertainty in the data that are used to train and feed these systems, to the inadequate explainability of their output; through the risk of overreliance, deskilling and context desensitization of their end-users. Although some of these issues may be currently hard to evaluate due to the still scarce adoption of these decisional systems in medical practice, we advocate the study of these potential consequences also for a more informed policy of approval beyond hype and disenchantment.