Fuzzy on FHIR: A decision support service for healthcare applications

Abstract

In the last years, an explosion of interest has been seen with respect to clinical decision support systems based on guidelines, since they have promised to reduce inter-practice variation, to promote evidence-based medicine, and to contain the cost of health care. Despite this great promise, many obstacles lie in the way of their integration into routine clinical care. Indeed, first, the communication with information systems to collect health data is a very thorny task due to the heterogeneity of data sources. Secondly, the machine-readable representation of guidelines can generate an unrealistic oversimplification of reality, since not able to completely handle uncertainty and imprecision typically affecting guidelines. Finally, a large number of existing decision support systems have been implemented as standalone software solutions that cannot be well reused or transported to other medical scenarios. Starting from these considerations, this paper proposes a standards-based decision support service for facilitating the development of healthcare applications enabling: i) the encoding of uncertain and vague knowledge underpinning clinical guidelines by using Fuzzy Logic; ii) the representation of input and output health data by using the emerging standard FHIR (Fast Healthcare Interoperability Resources). As a proof of concept, a WSDL-based SOAP implementation of the service has been tested on a set of clinical guidelines pertaining the evaluation of blood pressure for a monitored patient.