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

An ecosystem approach to the evaluation and impact analysis of heterogeneous preventive and/or early interventions projects for veterans and first responders in seven countries

BACKGROUND

Cumulative exposure to critical incidents and life-threatening events leads to significant risk for Veterans and First Responders (VFRs) developing mental ill health and disorders. Philanthropic organisations, Movember and Distinguished Gentleman's Ride, funded 15 organisations to conduct early intervention Projects across seven countries. The Projects aim to improve the mental health and wellbeing of VFRs, their families/significant others. This paper describes the novel external evaluation and impact analysis methods to identify effective Projects having positive impact on VFRs and their families, provide return on investment and the overall Grant Program.

METHODS

We take an ecosystem real-world approach, which recognises the context and aims to manage the complexities involved, uses a complexity and systems perspective, multi-step mixed methods and approaches. The evaluation is from three perspectives of: Projects; Project comparisons; Grant program. Embedded in the evaluation design are methods, knowledge sharing and organisational learning activities for all stakeholders. Data is collected by the Projects and evaluation team on input, throughputs, and output indicators. Analysis tools include Global Impact Analytics Framework, multi-layered statistical analysis, performance evaluation using an efficient decision support approach, Project and Grant program social return on investment, visual linking and data connection platform and assessment of gendered lens approaches.

IMPLICATIONS

The complexity and heterogeneity of Projects implemented in the real world continues to present significant evaluation challenges and limitations for project leads, stakeholders, researchers and evaluators. Our ecosystem approach and novel evaluation methodology will reduce the uncertainty around real world implementation, provide key learnings for project stakeholders and more broadly implementation researchers.

Data Analytics to Support Policy Making for Noncommunicable Diseases: Scoping Review

BACKGROUND

There is an emerging need for evidence-based approaches harnessing large amounts of health care data and novel technologies (such as artificial intelligence) to optimize public health policy making.

OBJECTIVE

The aim of this review was to explore the data analytics tools designed specifically for policy making in noncommunicable diseases (NCDs) and their implementation.

METHODS

A scoping review was conducted after searching the PubMed and IEEE databases for articles published in the last 10 years.

RESULTS

Nine articles that presented 7 data analytics tools designed to inform policy making for NCDs were reviewed. The tools incorporated descriptive and predictive analytics. Some tools were designed to include recommendations for decision support, but no pilot studies applying prescriptive analytics have been published. The tools were piloted with various conditions, with cancer being the least studied condition. Implementation of the tools included use cases, pilots, or evaluation workshops that involved policy makers. However, our findings demonstrate very limited real-world use of analytics by policy makers, which is in line with previous studies.

CONCLUSIONS

Despite the availability of tools designed for different purposes and conditions, data analytics is not widely used to support policy making for NCDs. However, the review demonstrates the value and potential use of data analytics to support policy making. Based on the findings, we make suggestions for researchers developing digital tools to support public health policy making. The findings will also serve as input for the European Union-funded research project ONCODIR developing a policy analytics dashboard for the prevention of colorectal cancer as part of an integrated platform.

The EMPOWER Occupational e-Mental Health Intervention Implementation Checklist to Foster e-Mental Health Interventions in the Workplace: Development Study

BACKGROUND

Occupational e-mental health (OeMH) interventions significantly reduce the burden of mental health conditions. The successful implementation of OeMH interventions is influenced by many implementation strategies, barriers, and facilitators across contexts, which, however, are not systematically tracked. One of the reasons is that international consensus on documenting and reporting the implementation of OeMH interventions is lacking. There is a need for practical guidance on the key factors influencing the implementation of interventions that organizations should consider. Stakeholder consultations secure a valuable source of information about these key strategies, barriers, and facilitators that are relevant to successful implementation of OeMH interventions.

OBJECTIVE

The objective of this study was to develop a brief checklist to guide the implementation of OeMH interventions.

METHODS

Based on the results of a recently published systematic review, we drafted a comprehensive checklist with a wide set of strategies, barriers, and facilitators that were identified as relevant for the implementation of OeMH interventions. We then used a 2-stage stakeholder consultation process to refine the draft checklist to a brief and practical checklist comprising key implementation factors. In the first stage, stakeholders evaluated the relevance and feasibility of items on the draft checklist using a web-based survey. The list of items comprised 12 facilitators presented as statements addressing "elements that positively affect implementation" and 17 barriers presented as statements addressing "concerns toward implementation." If a strategy was deemed relevant, respondents were asked to rate it using a 4-point Likert scale ranging from "very difficult to implement" to "very easy to implement." In the second stage, stakeholders were interviewed to elaborate on the most relevant barriers and facilitators shortlisted from the first stage. The interview mostly focused on the relevance and priority of strategies and factors affecting OeMH intervention implementation. In the interview, the stakeholders' responses to the open survey's questions were further explored. The final checklist included strategies ranked as relevant and feasible and the most relevant facilitators and barriers, which were endorsed during either the survey or the interviews.

RESULTS

In total, 26 stakeholders completed the web-based survey (response rate=24.8%) and 4 stakeholders participated in individual interviews. The OeMH intervention implementation checklist comprised 28 items, including 9 (32.1%) strategies, 8 (28.6%) barriers, and 11 (39.3%) facilitators. There was widespread agreement between findings from the survey and interviews, the most outstanding exception being the idea of proposing OeMH interventions as benefits for employees.

CONCLUSIONS

Through our 2-stage stakeholder consultation, we developed a brief checklist that provides organizations with a guide for the implementation of OeMH interventions. Future research should empirically validate the effectiveness and usefulness of the checklist.

A Machine Learning Framework for Diagnosing and Predicting the Severity of Coronary Artery Disease

BACKGROUND

Although machine learning (ML)-based prediction of coronary artery disease (CAD) has gained increasing attention, assessment of the severity of suspected CAD in symptomatic patients remains challenging.

METHODS

The training set for this study consisted of 284 retrospective participants, while the test set included 116 prospectively enrolled participants from whom we collected 53 baseline variables and coronary angiography results. The data was pre-processed with outlier processing and One-Hot coding. In the first stage, we constructed a ML model that used baseline information to predict the presence of CAD with a dichotomous model. In the second stage, baseline information was used to construct ML regression models for predicting the severity of CAD. The non-CAD population was included, and two different scores were used as output variables. Finally, statistical analysis and SHAP plot visualization methods were employed to explore the relationship between baseline information and CAD.

RESULTS

The study included 269 CAD patients and 131 healthy controls. The eXtreme Gradient Boosting (XGBoost) model exhibited the best performance amongst the different models for predicting CAD, with an area under the receiver operating characteristic curve of 0.728 (95% CI 0.623-0.824). The main correlates were left ventricular ejection fraction, homocysteine, and hemoglobin (p < 0.001). The XGBoost model performed best for predicting the SYNTAX score, with the main correlates being brain natriuretic peptide (BNP), left ventricular ejection fraction, and glycated hemoglobin (p < 0.001). The main relevant features in the model predictive for the GENSINI score were BNP, high density lipoprotein, and homocysteine (p < 0.001).

CONCLUSIONS

This data-driven approach provides a foundation for the risk stratification and severity assessment of CAD.

CLINICAL TRIAL REGISTRATION

The study was registered in www.clinicaltrials.gov protocol registration system (number NCT05018715).

[Everything is on the map: Integrated Mental Health Atlases as support tools for service planning. SESPAS Report 2020]

OBJECTIVE

This article reviews the usability of the Integrated Atlases of Mental Health as a decision support tool for service planning following a health ecosystem research approach.

METHOD

This study describes the types of atlases and the procedure for their development. Atlases carried out in Spain are presented and their impact in mental health service planning is assessed. Atlases comprise information on the local characteristics of the health care system, geographical availability of resources collected with the DESDE-LTC instrument and their use. Atlases use geographic information systems and other visualisation tools. Atlases follow a bottom-up collaborative approach involving decision-makers from planning agencies for their development and external validation.

RESULTS

Since 2005, Integrated Atlases of Mental Health have been developed for nine regions in Spain comprising over 65% of the Spanish inhabitants. The impact on service planning has been unequal for the different regions. Catalonia, Biscay and Gipuzkoa, and Andalusia reach the highest impact. In these areas, health advisors have been actively involved in their co-design and implementation in service planning.

CONCLUSIONS

Atlases allow detecting care gaps and duplications in care provision; monitoring changes of the system over time, and carrying out national and international comparisons, efficiency modelling and benchmarking. The knowledge provided by atlases could be incorporated to decision support systems in order to support an efficient mental health service planning based on evidence-informed policy.