JMIR Publications

ABSTRACT

Background:

Due to an increase in life expectancy, the prevalence of chronic diseases is on the rise too. Clinical Practice Guidelines (CPGs) provide recommendations for suitable interventions regarding different chronic diseases. But a deficit in the implementation of these CPGs could be identified. The PITeS-TIiSS tool, a personalized ontology-based Clinical Decision Support System (CDSS), aims to reduce the variability, prevent errors and consider interactions between different CPGs recommendations, among other benefits.

Objective:

To design, develop and validate an ontology-based CDSS which provides personalized recommendations related to drug prescription. The target population is polymedicated elderly patients with chronic diseases aiming to reduce complications related to these types of conditions and, also, offering integrated care.

Methods:

A study scenario about atrial fibrillation and treatment with anticoagulants was selected to validate the tool. After this, a series of knowledge sources were identified, such as CPGs, PROFUND index, LESS/CHRON criteria, and STOP/START criteria, to extract the information. Modeling was carried out using an ontology, and mapping was done with HL7 FHIR and SNOMED CT. Once the CDSS was developed, validation was carried out by using a retrospective case study.

Results:

This project was funded in January 2015 and approved by the Ethics Committee on 24 November 2015. A retrospective validation has been carried out through the analysis of a clinical case and an adoption model through the study of the requirements and features that a CDSS must fulfill to be well accepted by healthcare professionals. The results have been favorable and allow the proposed research to continue to the next phase.

Conclusions:

An ontology-based CDSS has been successfully designed, developed, and validated. However, as future work, the validation in a real environment should be performed to ensure the tool is usable and reliable.