People with serious mental illness (SMI) such as schizophrenia, schizoaffective disorder and bipolar affective disorder have a significantly reduced life expectancy, caused in part by increased incidences of mortality from physical health conditions such as cardiovascular disease (CVD) and diabetes.

Electronic clinical decision support systems (eCDSS) offer clinicians patient-specific advice and recommendations based on clinical guidelines, theoretically overcoming obstacles in the use of existing paper-based guidelines. Adoption of eCDSS to address CVD risk in people with SMI presents a unique opportunity for research, but requires evidence of acceptability and feasibility before scaling up of research.

The key objective of this study is to establish the feasibility and acceptability of an eCDSS (CogStack @ Maudsley) compromising a real-time electronic health record powered alerting and clinical decision support system for diabetes management in secondary inpatient mental healthcare settings. End-users of the eCDSS will be clinicians only.

Firstly we will conduct initial surveys and interviews with clinicians on inpatient wards to scope experiences of managing diabetes in secondary mental healthcare settings and attitudes towards use of digital technologies to aid in clinical decision making.

A feasibility study will then be run to evaluate the acceptability and feasibility of implementing eCDSS on inpatient wards. This will involve a cluster RCT on inpatient general adult psychiatry wards, where 4 months of eCDSS use by clinicians on intervention wards will be compared to 4 months of treatment as usual on control wards. All clinicians on recruited wards will be eligible to participate.

At the end of the study, participating clinicians on intervention wards will be invited to take part in a survey and interview which will explore their experiences and attitudes towards using the eCDSS, and an implementation science framework will be applied to inform future implementation of eCDSS. Group level pseudonymised outcome data will be gathered through a separate study.

People with serious mental illness (SMI) such as schizophrenia, schizoaffective disorder and bipolar affective disorder have a significantly reduced life expectancy in comparison to the general population. Improvements to the primary prevention of physical health illnesses like diabetes in the general population have not been mirrored to the same extent in people with SMI.

Diabetes is a group of metabolic disorders characterized by a high blood sugar level over a prolonged period of time. If left untreated or poorly managed, diabetes can lead to various long term health complications including cardiovascular disease, stroke, chronic kidney disease, foot ulcers, damage to the nerves and damage to the eyes. Diabetes accounts for approximately 10% of healthcare resources in the UK, and this is set to rise to 17% with an estimated cost of £39.8billion by 2035 when direct healthcare costs and indirect costs on productivity are taken into account.

People with SMI have higher rates of cardiovascular disease (CVD) risk factors such as central obesity, high blood pressure, raised cholesterol levels, and raised blood sugar levels compared to the general population. Local rates of diabetes in people with a diagnosis of established psychosis are 20% with a further 30% evidencing dysglycaemia (raised blood sugar levels). Again locally, rates of glucose dysregulation (indicator for high risk of developing diabetes) doubles in the first year after a first psychotic episode, creating a unique window for prevention strategies to address these risks as early as possible.

A key inequality in healthcare provision in people with SMI is the less than adequate assessment and treatment of physical health conditions such as diabetes in secondary mental healthcare settings. There is therefore a need for more targeted and clinically informed interventions, that improve the standard of physical healthcare screening and interventions offered to people with SMI across both primary and secondary care settings.

Globally, studies evaluating the provision of care by clinicians reveal that there is a sub-optimal uptake of guidelines into actual practice. The underlying factors for this are complex and occur at a combination of patient, clinician and system levels.

Adoption of digital technology to improve physical health in people with a diagnosis of SMI presents a unique opportunity, but requires evidence of acceptability, feasibility and effectiveness. Given the rising disease burden from diabetes in SMI, and deficits in providing evidence-based care for diabetes prevention and treatment, there is a pressing need to identify more systems-focused solutions.

Electronic clinical decision support systems (eCDSS) are well established as a strategic method of improving care for prevention and management of chronic conditions. eCDSS is defined as "any electronic information system based on a software algorithm designed to aid directly in clinical decision making, in which characteristics of individual patients are used to generate patient-specific assessments or recommendations that are then presented to clinicians for consideration".

Clinical guidelines remain under-utilized in clinical practice, thus eCDSS has the potential to overcome problems associated with the use of traditional paper-based guidelines. However, the existing evidence base for eCDSSs improving clinical performance and patient outcomes in mental healthcare settings remains sparse. In addition, electronic systems that are not accepted by their users cannot be expected to contribute to improving quality of care, hence facilitators, barriers and other consequences need to be understood for successful implementation of novel digital tools and could also serve as a basis for future system re-engineering. Hence there is call for research to include evaluating its implementation for successful future scalability.

The key digital tool to be used for eCDSS in this study is CogStack, a software platform developed by the National Institute for Health Research Maudsley Biomedical Research Centre (NIHR Maudsley BRC) and PhiDataLab. CogStack is an open source information retrieval and extraction system with the capability to offer near real-time natural language processing (NLP) of electronic health records. CogStack implements new data mining techniques, specifically the ability to search any clinical data source (unstructured and structured), and NLP applications developed to automate information extraction of medical concepts. The platform has shown early potential to be of value to clinicians in monitoring, intervention and follow up for their patients.

The primary objective of this study is to establish the feasibility and acceptability of an eCDSS (Cogstack@Maudsley) compromising a real-time computerised alerting and clinical decision support system for dysglycaemia management in secondary mental healthcare.

Our secondary objectives are to assess whether the system leads to changes in screening and follow-up testing rates for dysglycaemia, and subsequent clinician-led evidence-based interventions for dysglycaemia and diabetes (this will be measured using pseudonymised group observational data gathered from the South London and Maudsley NHS Foundation Trust (SLaM) Biomedical Research Centre (BRC) Clinical Records Interactive Search (CRIS) system once ward access to the eCDSS has ended). Since 2006, South London and Maudsley NHS Trust has operated fully electronic health records. The Clinical Record Interactive Search (CRIS) system, established in 2008, is an ethically approved electronic health records interface system that allows researchers to access deidentified electronic health records from this Trust for research purposes.

We will conduct a process evaluation to assess the barriers, facilitators, unintended consequences, and indicative costs of implementing the system onto inpatient general adult psychiatry wards.

Data gathered from this study will allow the research team to refine the system, address potential problems with future successful implementation, and inform a larger and more definitive effectiveness trial which will examine for hypothesised improvements in;

1. Rates of clinician-delivered evidence-based interventions for patients with dysglycaemia
2. Clinical outcomes relating to diabetes care

Inclusion Criteria:

• General adult psychiatry inpatient wards at South London and Maudsley NHS Foundation Trust. Wards will be entered into the study if their respective management are agreeable to participate.
• All clinical staff on recruited wards will be eligible to participate and will be invited to take part in a preliminary survey and individual interview with the research team at the start of the study.
• Staff on intervention wards will also be asked to complete a survey and individual interview at the end of the study.

Exclusion Criteria:

• Staff on recruited wards who are not of a clinical or healthcare professional background.
• Staff who lack capacity to provide informed consent to participate.