The aim of this review is to provide a broad overview of the state-of-the-art works mainly published in the last ten years on expert systems applied in different medical domains. Being able to support and sometimes substitute experts, an expert system may be a precious ally for medical diagnoses. Medical expert system applications provide physicians and patients with an immediate access to knowledge and advice, rooting their flexibility into their knowledge bases, rule sets and graphical interfaces. To be trusted by their users, medical expert systems should follow some criteria, which we investigate along with their different realization, from fuzzy logic to wearable solutions for out-of-clinical-environment care. We also consider the advantages of approaching diagnoses and alert systems through an artificial intelligence counterpart, without forgetting the importance of a good validation to assess the system functionality. Therefore, we show the heterogeneity of the solutions proposed by the literature, bounded to the specific needs a medical expert system is called to answer, the common lack of a system validation and the possible benefits deriving from these systems application.
Saibene, A., Assale, M., Giltri, M. (2021). Expert systems: Definitions, advantages and issues in medical field applications. EXPERT SYSTEMS WITH APPLICATIONS, 177(1 September 2021) [10.1016/j.eswa.2021.114900].
Expert systems: Definitions, advantages and issues in medical field applications
Saibene A.
;Assale M.
;Giltri M.
2021
Abstract
The aim of this review is to provide a broad overview of the state-of-the-art works mainly published in the last ten years on expert systems applied in different medical domains. Being able to support and sometimes substitute experts, an expert system may be a precious ally for medical diagnoses. Medical expert system applications provide physicians and patients with an immediate access to knowledge and advice, rooting their flexibility into their knowledge bases, rule sets and graphical interfaces. To be trusted by their users, medical expert systems should follow some criteria, which we investigate along with their different realization, from fuzzy logic to wearable solutions for out-of-clinical-environment care. We also consider the advantages of approaching diagnoses and alert systems through an artificial intelligence counterpart, without forgetting the importance of a good validation to assess the system functionality. Therefore, we show the heterogeneity of the solutions proposed by the literature, bounded to the specific needs a medical expert system is called to answer, the common lack of a system validation and the possible benefits deriving from these systems application.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.