Use of the self-organising map network (SOMNet) as a decision support system for regional mental health planning

Abstract

BackgroundDecision-making in mental health systems should be supported by the evidence-informed knowledge transfer of data. Since mental health systems are inherently complex, involving interactions between its structures, processes and outcomes, decision support systems (DSS) need to be developed using advanced computational methods and visual tools to allow full system analysis, whilst incorporating domain experts in the analysis process. In this study, we use a DSS model developed for interactive data mining and domain expert collaboration in the analysis of complex mental health systems to improve system knowledge and evidence-informed policy planning.MethodsWe combine an interactive visual data mining approach, the self-organising map network (SOMNet), with an operational expert knowledge approach, expert-based collaborative analysis (EbCA), to develop a DSS model. The SOMNet was applied to the analysis of healthcare patterns and indicators of three different regional mental health systems in Spain, comprising 106 small catchment areas and providing healthcare for over 9 million inhabitants. Based on the EbCA, the domain experts in the development team guided and evaluated the analytical processes and results. Another group of 13 domain experts in mental health systems planning and research evaluated the model based on the analytical information of the SOMNet approach for processing information and discovering knowledge in a real-world context. Through the evaluation, the domain experts assessed the feasibility and technology readiness level (TRL) of the DSS model.ResultsThe SOMNet, combined with the EbCA, effectively processed evidence-based information when analysing system outliers, explaining global and local patterns, and refining key performance indicators with their analytical interpretations. The evaluation results showed that the DSS model was feasible by the domain experts and reached level 7 of the TRL (system prototype demonstration in operational environment).ConclusionsThis study supports the benefits of combining health systems engineering (SOMNet) and expert knowledge (EbCA) to analyse the complexity of health systems research. The use of the SOMNet approach contributes to the demonstration of DSS for mental health planning in practice.Electronic supplementary materialThe online version of this article (10.1186/s12961-018-0308-y) contains supplementary material, which is available to authorized users.

A Comparison of Mental Health Care Systems in Northern and Southern Europe: A Service Mapping Study

“…Understanding of the context and mental health care ecosystem is needed prior to implementing new service provision approaches in other environments. Previous findings [ 2 , 35 , 37 , 42 ] support the usability of making standard comparisons of MHS within regions, and across different countries, to guide management and policy planning. Even in the European context, significant differences exist in the structure and resourcing of MHS.…”

“…It is important to note that the Girona model has been developed in a location with a previous large psychiatric institution (Hospital Psiquiatrico de Salt). The analysis of other local areas with old psychiatric hospitals, such as Reus in Catalonia [ 34 ] or Gipuzkoa in the Basque Country [ 42 ], indicates that the local history of health care provision has a significant impact in the development of the mental health reform when compared with neighboring districts or regions. In Girona, the reform process did not involve the closure of the psychiatric hospital and a capital transfer of funding, but the incorporation of this facility into the main general health precinct of the region.…”

What Is Rural Adversity, How Does It Affect Wellbeing and What Are the Implications for Action?

“…Geospatial analyses, e.g., [ 38 , 39 , 40 ] and the Integrated Atlases of Mental Health Care, e.g., [ 41 , 42 , 43 , 44 , 45 ] are highly important decision-making tools to visualise the pattern of rural diversity or adversity and support an integrated and systematic way of collecting information from multi-layered rural ecosystems (communities). Advanced geospatial analyses offer a fundamental capacity to quantify and visualise variations and interaction between contextual factors (i.e., built and social environments, geographic isolation and environmental risk factors, and limited services and resources) and their impacts on rural adversity.…”

Experts’ perceptions on the use of visual analytics for complex mental healthcare planning: an exploratory study

“…The application of visual analytics as a tool for complex data analysis and decision support can be found in healthcare. Examples include a cohort clustering analysis using disk-like visualisation in public healthcare [6], and an associative service pattern analysis using grid map visualisation in mental healthcare [7]. However, a lack of understanding, availability, development, and application of visual analytics methods answering complex questions persists in the process of evidence development and decisionmaking [8,9].…”