Implementation of a Distributed Guideline-Based Decision Support Model Within a Patient-Guidance Framework

Abstract

Abstract. We report on new projection engine which was developed in order to implement a distributed guideline-based decision support system (DSS) within the European project MobiGuide.In this model, small portions of the guideline knowledge are projected, i.e. 'downloaded', from a central DSS server to a local DSS in the patient's mobile device, which then applies that knowledge using the mobile device's local resources. Furthermore, the projection engine generates guideline projections which are adapted to the patient's previously defined preferences and, implicitly, to the patient's current context, which is embodied in the projected knowledge. We evaluated this distributed guideline application model for two complex guidelines: one for Gestational Diabetes Mellitus, and one for Atrial Fibrillation. We found that the initial specification of what we refer to as the customized guideline should be in the terms of the distributed DSS, i.e., include two levels: one for the central DSS, and one for the local DSS. In addition, we found significant differences between the customized, distributed versions of the two guidelines, indicating further research directions and possibly additional ways to analyze and characterize guidelines.

Assessment of a personalized and distributed patient guidance system

“…The Backend DSS has access to the full knowledge base of CIGs and to the complete, historical PHR [19]. Based on the current state of the patient and of the system (e.g., battery level, bandwidth), the Backend DSS projects [20,21] an appropriate part of its knowledge, using a specially developed generic projection language, to the mDSS, which can then deliver decision-support to the patient even when there is no connectivity to the internet, based on projected knowledge, the sensor data, the patient's preferences and daily schedule (e.g., meal times, reminder times), and data entered by the patient himself; (5) performance of intelligent data analysis, to discover clinical data patterns in individual patients, thus providing additional decision-support.…”

Quality of clinical data aware telemedicine systems

“…The CIG can be applied in systems such as a clinical decision support system (CDSS), which can interpret and execute these guidelines. In this research study, we apply a CDSS integrated in a telemedicine system that uses the guidelines as the CDSS knowledge-base [6,43]. Typically, this guideline-based CDSS analyzes the clinical data from different sources and applies the guideline to provide decisions by means of, for example, clinical recommendations.…”

A guideline representation language for pervasive healthcare

“…• A back-end server that resides at the hospital, performing any necessary but expensive tasks and providing decision support to clinicians. This back-end server is also responsible for "projecting" the appropriate portions of a clinical guideline to the smartphone component for local execution [70].…”

“…As a result, they assume a centralized system architecture in which a supervisory component controls the execution of guidelines. To reduce reliance on such components, Shalom et al in 2015 proposed a projection mechanism whereby self-contained portions of a clinical guideline are identified for execution in parallel with the overall plan [70]. This mechanism was implemented in the MobiGuide system, which as described in Sec.…”

“…This mechanism was implemented in the MobiGuide system, which as described in Sec. 1.4 contains two decision support systems, a front-end system running on the patient's smartphone to execute guideline fragments locally; and a back-end system running on hospital servers to execute the overall guideline and "project" the appropriate portions to recipient devices [70]. While this projection mechanism can be extended to an arbitrary number of "local" devices, it still requires a supervisory component to project guideline fragments.…”