Technological maturity model for digital decision support systems in mental healthcare:

A scoping review comparing the Finnish Therapy Navigator services to international alternatives

Authors

• Tino Karolaakso Faculty of Social Sciences, Tampere University; HUS Psychiatry https://orcid.org/0000-0002-7875-8079
• Kasperi Mikkonen University of Helsinki; HUS Psychiatry https://orcid.org/0009-0000-4659-5183
• Tiina Tantarimäki HUS Psychiatry
• Samuli I. Saarni HUS Psychiatry; Faculty of Medicine and Health Technology, Tampere University; Pirkanmaa Wellbeing services county (Pirha) https://orcid.org/0000-0002-9348-5435

DOI:

https://doi.org/10.23996/fjhw.157407

Keywords:

mental disorders, digital health technology, clinical decision support systems, self-assessment, access to treatment, AI (artificial intelligence)

Abstract

Mental disorders are among the leading causes of disability worldwide, creating an increasing demand for timely and effective mental healthcare. Digital decision support systems (DDSS) have emerged as promising tools for enhancing the assessment and treatment navigation of mental disorders. This review examines the international development and maturity levels of DDSS in mental healthcare. The objective is to identify recent systems, analyze their key features, and propose a technological maturity model for these systems, while comparing them to the Finnish Therapy Navigator (FTN) services.

The study used a scoping review methodology to map the existing literature and identify relevant DDSS. The review was conducted in accordance with the PRISMA extension for scoping reviews (PRISMA-ScR) guidelines. A framework for a technological maturity model was developed through a thematic analysis of findings based on the prevalence, complexity, and clinical utility of system features, comparing functional features across systems to identify emerging patterns in technological sophistication.

A total of 35 studies on adult DDSS and 38 studies on adolescent DDSS met the inclusion criteria, of which 10 distinct DDSS were identified for adults and 9 for adolescents, with one system designed for both groups. The most prevalent features included multi-disorder screening (100%), summary report generation (100%), and contextual factor mapping (65%). Less common but potentially more advanced features included automated treatment recommendations (35%), response-based therapeutic content (20%), and AI-driven capabilities such as chatbot with natural language processing and probabilistic reasoning (5%).

Based on the prevalence and perceived clinical utility of these features, we propose a three-tiered technological maturity model to classify DDSS for mental healthcare assessment and treatment navigation: 1) structured data collection, 2) rule-based decision support, and 3) intelligent and adaptive decision support. FTN services fall within the first maturity level, as they primarily facilitate structured assessments without automated treatment recommendations. The proposed model highlights the transition from passive tools to interactive systems and to intelligent and adaptive platforms. The development of mental healthcare DDSS is still in its early stages, with significant potential for future advancements.