Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Jun 20;9(2):e31029.
doi: 10.2196/31029.

A Reference Architecture for Data-Driven and Adaptive Internet-Delivered Psychological Treatment Systems: Software Architecture Development and Validation Study

Affiliations

A Reference Architecture for Data-Driven and Adaptive Internet-Delivered Psychological Treatment Systems: Software Architecture Development and Validation Study

Suresh Kumar Mukhiya et al. JMIR Hum Factors. .

Abstract

Background: Internet-delivered psychological treatment (IDPT) systems are software applications that offer psychological treatments via the internet. Such IDPT systems have become one of the most commonly practiced and widely researched forms of psychotherapy. Evidence shows that psychological treatments delivered by IDPT systems can be an effective way of treating mental health morbidities. However, current IDPT systems have high dropout rates and low user adherence. The primary reason is that the current IDPT systems are not flexible, adaptable, and personalized as they follow a fixed tunnel-based treatment architecture. A fixed tunnel-based architecture follows predefined, sequential treatment content for every patient, irrespective of their context, preferences, and needs. Moreover, current IDPT systems have poor interoperability, making it difficult to reuse and share treatment materials. There is 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 have tended to reinvent new versions of IDPT systems, making them more complex and less interoperable.

Objective: This study aimed to design, develop, and evaluate a reference architecture (RA) for adaptive systems that can facilitate the design and development of adaptive, interoperable, and reusable IDPT systems.

Methods: This study was conducted in collaboration with a large interdisciplinary project entitled INTROMAT (Introducing Mental Health through Adaptive Technology), which brings together information and communications technology researchers, information and communications technology industries, health researchers, patients, clinicians, and patients' next of kin to reach its vision. First, we investigated previous studies and state-of-the-art works based on the project's problem domain and goals. On the basis of the findings from these investigations, we identified 2 primary gaps in current IDPT systems: lack of adaptiveness and limited interoperability. Second, we used model-driven engineering and Domain-Driven Design techniques to design, develop, and validate the 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 open-source implementation using empirical (case study) and nonempirical approaches (software architecture analysis method, expert evaluation, and software quality attributes).

Results: This paper outlines an RA that supports flexible user modeling and the adaptive delivery of treatments. To evaluate the proposed RA, we developed an open-source software based on the proposed RA. The open-source framework aims to improve development productivity, facilitate interoperability, increase reusability, and expedite communication with domain experts.

Conclusions: Our results showed that the proposed RA is flexible and capable of adapting interventions based on patients' needs, preferences, and context. Furthermore, developers and researchers can extend the proposed RA to various health care interventions.

Keywords: ICBT; IDPT system; adaptive strategies; adaptive system; health care systems; personalized therapies; reference architecture; software architecture.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: None declared.

Figures

Figure 1
Figure 1
The figure depicts our proposed model of a data-driven adaptive internet-delivered psychological treatment system. The patients interact with the intervention, and an analytics server captures those interactions. On the basis of the logged data analysis, a process referred to as user profiling maintains an up-to-date user model to provide the adaptive effect.
Figure 2
Figure 2
Reference architecture of data-driven adaptive internet-delivered psychological treatment system. AI: artificial intelligence; API: application programming interface; CMS: Content Management System; DL: deep learning; EDA: exploratory data analysis; ML: machine learning; NLP: natural language processing; REST API: RESTful API.
Figure 3
Figure 3
The figure depicts the conceptual model of any intervention that is always associated with a case. A case contains ≥1 module. Each module has ≥1 task, which can be learning materials or exercises. An exercise can be physical or computerized activities. LOINC: Logical Observation Identifiers Names and Codes; SNOMED-CT: Systematized Nomenclature of Medicine–Clinical Terms.
Figure 4
Figure 4
Example data structure of a case.
Figure 5
Figure 5
Data structure of a task.
Figure 6
Figure 6
States of cases, modules, and tasks of an internet-delivered psychological treatment system.
Figure 7
Figure 7
An example scenario of human emotion taxonomy.
Figure 8
Figure 8
An example of different tasks inside a module in an internet-delivered psychological treatment system. Here, the dotted arrow denotes dependencies. For example, Task 2 is dependent on Task 1. Such dependency indicates that a patient cannot start Task 2 before Task 1. Each task has ≥1 evaluation criterion denoted as E.x.

Similar articles

Cited by

References

    1. Evidence-based Psychotherapy: Where Practice and Research Meet. Washington, D.C., United States: American Psychological Association; 2006.
    1. Kelders SM, Kok RN, Ossebaard HC, Van Gemert-Pijnen JE. Persuasive system design does matter: a systematic review of adherence to web-based interventions. J Med Internet Res. 2012 Nov 14;14(6):e152. doi: 10.2196/jmir.2104. https://www.jmir.org/2012/6/e152/ v14i6e152 - DOI - PMC - PubMed
    1. Mukhiya SK, Wake JD, Inal Y, Lamo Y. Adaptive systems for internet-delivered psychological treatments. IEEE Access. 2020;8:112220–36. doi: 10.1109/access.2020.3002793. - DOI - PMC - PubMed
    1. Mukhiya SK, Wake JD, Inal Y, Pun KI, Lamo Y. Adaptive elements in internet-delivered psychological treatment systems: systematic review. J Med Internet Res. 2020 Nov 27;22(11):e21066. doi: 10.2196/21066. https://www.jmir.org/2020/11/e21066/ v22i11e21066 - DOI - PMC - PubMed
    1. Bonaccorsi A, Rossi C. Why Open Source software can succeed. Res Policy. 2003 Jul;32(7):1243–58. doi: 10.1016/s0048-7333(03)00051-9. - DOI