JMIR Publications

ABSTRACT

Background:

Internet-Delivered Psychological Treatment (IDPT) systems are software applications that offer psychological treatments through the Internet. Such IDPT systems have grown as one of the most commonly practised and widely researched forms of psychotherapy. Evidence shows that psychological treatments delivered by IDPT systems can be an effective way to treat mental health morbidities. However, current IDPT systems suffer from high dropout rates and low user adherence. The primary reasons are that the current IDPT systems are not flexible, adaptable, and personalized since they follow a fixed tunnel-based treatment architecture. A fixed tunnel-based architecture follows pre-defined, sequential treatment content for every patient irrespective of their context, preferences and needs. Moreover, the current IDPT systems have poor interoperability making it difficult to reuse and share treatment materials. There are a lack of development and documentation standards, conceptual frameworks, and established (clinical) guidelines for such IDPT systems. As a result, several ad hoc forms of IDPT models exist. Consequently, developers and researchers tend to reinvent new versions of IDPT systems, making them more complex and less interoperable.

Objective:

The principal objective of this study is to design, develop and evaluate a reference architecture (RA) of adaptive systems that could facilitate the development of adaptive, interoperable and reusable IDPT systems. The RA attempts to assist in the design and development of adaptive, interoperable and reusable IDPT systems.

Methods:

This study is accomplished in collaboration with a large interdisciplinary project entitled INTROMAT, which brings together ICT researchers, ICT industries, health researchers, patients, clinicians, and patients next of kin to reach its vision. First, we started investigating the previous studies and state-of-the-art works based on the project's problem domain and goals. Based on the findings from these investigations, we identified two primary gaps in the current IDPT systems, lack of adaptiveness and limited interoperability. Second, we used Model-Driven Engineering and Domain-Driven Design (DDD) techniques to design, develop, and validate the Reference Architecture (RA) for building adaptive, interoperable and reusable IDPT systems to address these gaps. Third, based on the proposed RA, we implemented a prototype as the open-source software. Finally, we evaluated the RA and the open-source implementation using empirical (case study) and non-empirical approaches (SAAM method, expert evaluation, and software quality attributes).

Results:

This paper outlines a Reference Architecture (RA) that supports flexible user modelling and adaptive delivery of treatments. To evaluate the proposed RA, we developed an open-source software based on the proposed reference architecture. The open-source framework aims to a) improve development productivity, b) facilitate interoperability, c) increase reusability, and d) expedite communication with domain experts.

Conclusions:

Our results show that the proposed RA is flexible and is capable of adapting interventions based on the patients' needs, preferences and context. Furthermore, developers and researchers can extend the proposed RA for various healthcare interventions.