Deborah Jane Wake
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Deborah Jane Wake has a total of 214 co-authors. Here are the top co-authors by number of shared publications:
- Scott Gordon Cunningham
School of Medicine, University of Dundee, Dundee, UK
7 shared publications - Doogie Brodie
My Way Digital Health LTD, Dundee, UK
4 shared publications - Scott C. Mackenzie
MRC Centre for Reproductive Health, University of Edinburgh, Edinburgh, UK
4 shared publications - Cathy Shields
School of Dentistry, University of Dundee, Nethergate, School of Dentistry, Dundee, DD1 4HN Scotland, UK
3 shared publications Salma Mehar
Department of Diabetes, Endocrinology & Metabolism, Imperial College London, UK
3 shared publicationsAlex Bickerton
Dept Diabetes & Endocrinology Yeovil District Hospital NHS Foundation Trust Yeovil UK
2 shared publications
Latest Publications
- Open Access
Understanding the acceptability of digital diabetes self-management tools among non-users: A qualitative study of personal, social and healthcare contexts
Background: Diabetes poses a major global health and economic burden, and effective self-management is essential for preventing complications. The National Health Service in England has recently announced plans to shift from analogue to digital services in their 10-year plan. However, digital health technology may also risk widening existing inequalities. MyWay Diabetes is a digital self-management intervention implemented in three regions across England. Understanding the acceptability of online and digital tools to support diabetes self-management, particularly among non-users and underserved groups, is essential to ensure equitable engagement and implementation. Objectives: To (1) explore barriers to using online and digital support across diverse demographic groups with type 1 and type 2 diabetes who had not used the MyWay Diabetes platform, and (2) identify factors that could improve uptake and continued engagement. Design: Cross-sectional qualitative study. Methods: We conducted six focus groups with n=35 people living with diabetes (27F, 8M; 40% Asian British Pakistani) across three regions in England. The Theoretical Framework of Acceptability (TFA) informed data collection and analysis. Data were transcribed and analysed thematically using template analysis, mapped onto constructs of the TFA. Results: Digital engagement in diabetes self-management was shaped by intersecting personal, social, and healthcare system factors. Participants’ confidence with navigating digital environments was constrained by the emotional and practical burden of living with diabetes. Social and structural barriers, including cultural mismatch, accessibility challenges, financial constraints, and reliance on family further limited meaningful use of digital tools. Engagement was strongly influenced by trust in healthcare professionals and services; digital tools were considered acceptable when they complemented person-centred care, but resisted when perceived as replacing personalised, face-to-face support. Conclusions: Digital support for diabetes self-management is more likely to be acceptable when it aligns with people’s capabilities, social circumstances, and trusted healthcare relationships. Therefore, to prevent widening inequalities, digital tools should be accessible, culturally relevant, and embedded within supportive, person-centred models of care. Lived Experience or Public Contribution: Public contributors with lived experience of diabetes (3F, 3M) reviewed participant materials and pseudonymised focus group transcripts, providing feedback on recruitment, data collection, and interpretation. Their insights informed analysis and theme development, ensuring a lived-experience perspective. Our public co-applicant is a co-author on this manuscript.
Open AccessUnderstanding the acceptability of digital diabetes self-management tools among non-users: A qualitative study of personal, social and healthcare contexts
Background: Diabetes poses a major global health and economic burden, and effective self-management is essential for preventing complications. The National Health Service in England has recently announced plans to shift from analogue to digital services in their 10-year plan. However, digital health technology may also risk widening existing inequalities. MyWay Diabetes is a digital self-management intervention implemented in three regions across England. Understanding the acceptability of online and digital tools to support diabetes self-management, particularly among non-users and underserved groups, is essential to ensure equitable engagement and implementation. Objectives: To (1) explore barriers to using online and digital support across diverse demographic groups with type 1 and type 2 diabetes who had not used the MyWay Diabetes platform, and (2) identify factors that could improve uptake and continued engagement. Design: Cross-sectional qualitative study. Methods: We conducted six focus groups with n=35 people living with diabetes (27F, 8M; 40% Asian British Pakistani) across three regions in England. The Theoretical Framework of Acceptability (TFA) informed data collection and analysis. Data were transcribed and analysed thematically using template analysis, mapped onto constructs of the TFA. Results: Digital engagement in diabetes self-management was shaped by intersecting personal, social, and healthcare system factors. Participants’ confidence with navigating digital environments was constrained by the emotional and practical burden of living with diabetes. Social and structural barriers, including cultural mismatch, accessibility challenges, financial constraints, and reliance on family further limited meaningful use of digital tools. Engagement was strongly influenced by trust in healthcare professionals and services; digital tools were considered acceptable when they complemented person-centred care, but resisted when perceived as replacing personalised, face-to-face support. Conclusions: Digital support for diabetes self-management is more likely to be acceptable when it aligns with people’s capabilities, social circumstances, and trusted healthcare relationships. Therefore, to prevent widening inequalities, digital tools should be accessible, culturally relevant, and embedded within supportive, person-centred models of care. Lived Experience or Public Contribution: Public contributors with lived experience of diabetes (3F, 3M) reviewed participant materials and pseudonymised focus group transcripts, providing feedback on recruitment, data collection, and interpretation. Their insights informed analysis and theme development, ensuring a lived-experience perspective. Our public co-applicant is a co-author on this manuscript.
- Open Access
- 18 November 2025
- Published by Wiley in Diabetic Medicine
- Vol. 43 (2) , e70171
The use of machine learning to predict pharmacological therapy in gestational diabetes: A scoping review
Aims: Early identification of pharmacological therapy for gestational diabetes mellitus (GDM), a common pregnancy complication, through machine learning could allow for better therapeutic strategies and improved treatment efficiency. This scoping review aimed to comprehensively review the machine learning models used to predict the need for pharmacological therapy in GDM. Methods: Four electronic databases—Embase, Medline, IEEE Xplore and Web of Science—were searched for publications between 1 July 2007 and 31 August 2024. Studies predicting pharmacological therapy for GDM using machine learning were included. The Joanna Briggs Institute and PRISMA‐ScR checklist was followed, and the Prediction model Risk Of Bias ASsessment Tool (PROBAST) was used to assess quality. Results: Included were 17 studies presenting 44 models, 61.4% (27/44) predicted any pharmacological therapy use and 38.6% (17/44) predicted insulin use alone. All were binary classifiers, and logistic regression was typically used. The overall area under the receiver operating curve had a median of 0.75. Common clinical variables were found to be predictors, such as history of GDM, gestational week at GDM diagnosis, pregestational body mass index, maternal age, HbA1c, fasting and 1 h glucose from 75 g oral glucose tolerance test. Though 65.9% of models were validated, there was a lack of external validation. There was no evidence of clinical application of the models. Conclusion: Logistic regression with common clinical variables was often used to predict pharmacological therapy for GDM. Few models were externally validated or clinically applicable.
- 18 November 2025
- Published by Wiley in Diabetic Medicine
- Vol. 43 (2) , e70171
Open AccessThe use of machine learning to predict pharmacological therapy in gestational diabetes: A scoping review
Aims: Early identification of pharmacological therapy for gestational diabetes mellitus (GDM), a common pregnancy complication, through machine learning could allow for better therapeutic strategies and improved treatment efficiency. This scoping review aimed to comprehensively review the machine learning models used to predict the need for pharmacological therapy in GDM. Methods: Four electronic databases—Embase, Medline, IEEE Xplore and Web of Science—were searched for publications between 1 July 2007 and 31 August 2024. Studies predicting pharmacological therapy for GDM using machine learning were included. The Joanna Briggs Institute and PRISMA‐ScR checklist was followed, and the Prediction model Risk Of Bias ASsessment Tool (PROBAST) was used to assess quality. Results: Included were 17 studies presenting 44 models, 61.4% (27/44) predicted any pharmacological therapy use and 38.6% (17/44) predicted insulin use alone. All were binary classifiers, and logistic regression was typically used. The overall area under the receiver operating curve had a median of 0.75. Common clinical variables were found to be predictors, such as history of GDM, gestational week at GDM diagnosis, pregestational body mass index, maternal age, HbA1c, fasting and 1 h glucose from 75 g oral glucose tolerance test. Though 65.9% of models were validated, there was a lack of external validation. There was no evidence of clinical application of the models. Conclusion: Logistic regression with common clinical variables was often used to predict pharmacological therapy for GDM. Few models were externally validated or clinically applicable.
- Top Cited PapersOpen Access
- 17 November 2025
- Published by Springer Nature in Diabetologia
- Vol. 69 (2) , 259-273
Artificial intelligence-driven clinical decision support systems to assist healthcare professionals and people with diabetes in Europe at the point of care: a Delphi-based consensus roadmap
The use of artificial intelligence (AI) to improve the diagnosis, assessment and treatment of people with diabetes has the potential to drive a paradigm shift in diabetes care, both minimising treatment inertia and optimising clinical outcomes. This is a significant opportunity, given the predicted increase in the burden of diabetes over the next 20 years. However, there are concerns that regulatory processes for development and implementation of AI-driven technologies are not adequate for systems that may adapt to new data and change from their original performance characteristics as evaluated. The European Diabetes Forum (EUDF) convened a working group to review and investigate the unmet needs around implementation of AI technology in diabetes care. The working group developed the framework and focus of the accompanying analysis through a series of virtual and face-to-face meetings, including email conversations. The working group examined the key objectives for good diabetes care in the context of current and predicted AI-driven clinical decision support systems (AI-CDSS), including the outcomes for people with diabetes, the goals for personalised medicine and the implications for guideline-driven diabetes services and healthcare professionals. The process covered the needs of primary care healthcare professionals, who will shoulder the majority of diabetes care. The challenge of developing regulatory concepts and processes that are sufficiently robust to be AI inclusive was considered as central to the outcomes. Based on the available evidence, the EUDF working group believes that AI-CDSS will deliver benefits for people with diabetes, although there are clear challenges to moving AI-CDSS into the practical clinical space. To encourage debate on how this can be achieved safely and effectively, at the conclusion of the process a series of 14 recommendations was agreed using a nominal group technique and Delphi methodology, which are discussed in context in this article. Graphical Abstract
- 17 November 2025
- Published by Springer Nature in Diabetologia
- Vol. 69 (2) , 259-273
Top Cited PapersOpen AccessArtificial intelligence-driven clinical decision support systems to assist healthcare professionals and people with diabetes in Europe at the point of care: a Delphi-based consensus roadmap
The use of artificial intelligence (AI) to improve the diagnosis, assessment and treatment of people with diabetes has the potential to drive a paradigm shift in diabetes care, both minimising treatment inertia and optimising clinical outcomes. This is a significant opportunity, given the predicted increase in the burden of diabetes over the next 20 years. However, there are concerns that regulatory processes for development and implementation of AI-driven technologies are not adequate for systems that may adapt to new data and change from their original performance characteristics as evaluated. The European Diabetes Forum (EUDF) convened a working group to review and investigate the unmet needs around implementation of AI technology in diabetes care. The working group developed the framework and focus of the accompanying analysis through a series of virtual and face-to-face meetings, including email conversations. The working group examined the key objectives for good diabetes care in the context of current and predicted AI-driven clinical decision support systems (AI-CDSS), including the outcomes for people with diabetes, the goals for personalised medicine and the implications for guideline-driven diabetes services and healthcare professionals. The process covered the needs of primary care healthcare professionals, who will shoulder the majority of diabetes care. The challenge of developing regulatory concepts and processes that are sufficiently robust to be AI inclusive was considered as central to the outcomes. Based on the available evidence, the EUDF working group believes that AI-CDSS will deliver benefits for people with diabetes, although there are clear challenges to moving AI-CDSS into the practical clinical space. To encourage debate on how this can be achieved safely and effectively, at the conclusion of the process a series of 14 recommendations was agreed using a nominal group technique and Delphi methodology, which are discussed in context in this article. Graphical Abstract
- Open Access
Study protocol for an open-label, single-arm, mixed methods feasibility study of the MWIQ AI-powered decision support tool for diabetes management in GP practices
Introduction Diabetes affects ~10% of the world’s population and is rising. Treatment costs in the UK are ~15% of the NHS budget. Diabetes-related complications can be lowered through better evidence-based clinician management and patient self-management. MyWay intelligence quotient (MWIQ) is an electronic platform that will provide clinical decision support around the diagnosis and treatment of patients with diabetes. This study evaluates the safety and clinical performance (clinical appropriateness/applicability, clinical impact and clinical usability) of MWIQ. Methods and analysis The system will be implemented in real time in four to seven general practitioner (GP) practices. Clinicians with diabetes expertise will be recruited as validators, who will inspect records to ensure system robustness before use, and up to 14 healthcare professionals will use and evaluate the system. Quantitative and qualitative analyses will be triangulated to assess the MWIQ system. Assessment of clinical outcomes will be made using pseudonymised routinely collected clinical data, including adherence to quality performance indicators, diabetes diagnosis, diabetes investigations (eg, genetic testing), HbA1c, blood pressure, body mass index, cholesterol and foot risk score for the diabetes population concerned. Clinical and validator participants will also submit a weekly questionnaire, and these, along with interviews, which are scheduled during the testing process, will be analysed to provide data on the utility, safety and usability of the system. Ethics and dissemination This study was approved, 08/01/2024, by the North of Scotland Research Ethics Committee (REC), IRAS project ID: 305267, REC, reference 23/NS/0134. The study has gained confidentiality advisory group (CAG) support (reference: 24/CAG/0002), medicines and healthcare products regulatory agency (MHRA) and health research authority (27/08/2024) approvals. Findings will be reported to (1) The funding body, (2) The participating GP practices, (3) The study PPIE group, (4) The MHRA to support a submission for recognition as a class 2 CE/UKCA marked device, (5) Presented at local, national and international conferences and (6) Disseminated by peer-reviewed publications. Trial registration number ISRCTN17422256.
Open AccessStudy protocol for an open-label, single-arm, mixed methods feasibility study of the MWIQ AI-powered decision support tool for diabetes management in GP practices
Introduction Diabetes affects ~10% of the world’s population and is rising. Treatment costs in the UK are ~15% of the NHS budget. Diabetes-related complications can be lowered through better evidence-based clinician management and patient self-management. MyWay intelligence quotient (MWIQ) is an electronic platform that will provide clinical decision support around the diagnosis and treatment of patients with diabetes. This study evaluates the safety and clinical performance (clinical appropriateness/applicability, clinical impact and clinical usability) of MWIQ. Methods and analysis The system will be implemented in real time in four to seven general practitioner (GP) practices. Clinicians with diabetes expertise will be recruited as validators, who will inspect records to ensure system robustness before use, and up to 14 healthcare professionals will use and evaluate the system. Quantitative and qualitative analyses will be triangulated to assess the MWIQ system. Assessment of clinical outcomes will be made using pseudonymised routinely collected clinical data, including adherence to quality performance indicators, diabetes diagnosis, diabetes investigations (eg, genetic testing), HbA1c, blood pressure, body mass index, cholesterol and foot risk score for the diabetes population concerned. Clinical and validator participants will also submit a weekly questionnaire, and these, along with interviews, which are scheduled during the testing process, will be analysed to provide data on the utility, safety and usability of the system. Ethics and dissemination This study was approved, 08/01/2024, by the North of Scotland Research Ethics Committee (REC), IRAS project ID: 305267, REC, reference 23/NS/0134. The study has gained confidentiality advisory group (CAG) support (reference: 24/CAG/0002), medicines and healthcare products regulatory agency (MHRA) and health research authority (27/08/2024) approvals. Findings will be reported to (1) The funding body, (2) The participating GP practices, (3) The study PPIE group, (4) The MHRA to support a submission for recognition as a class 2 CE/UKCA marked device, (5) Presented at local, national and international conferences and (6) Disseminated by peer-reviewed publications. Trial registration number ISRCTN17422256.
- Open Access
- 29 November 2024
- Published by SAGE Publications in Journal of Diabetes Science and Technology
- Vol. 20 (3) , 930-941
The User-Centered Design of a Clinical Dashboard and Patient-Facing App for Gestational Diabetes
Background: The number of pregnancies affected by gestational diabetes mellitus (GDM) is growing. With the increased use of smartphones and predictive modeling, a mobile health (mHealth) solution could be developed to improve care and management of GDM while streamlining care through risk stratification. Methods: A user-centered mHealth tool was designed from ethnographic observations and 11 semi-structured interviews (six health care professionals [HCPs] and five women with GDM), followed by iterative changes and evaluation from three feedback groups with 31 participants (17 HCPs, 14 researchers) and 13 questionnaires with women with GDM. Results: “MyGDM” includes a clinical dashboard that centralizes the clinic’s patients, highlighting off-target blood glucose and predicting the need for pharmacological intervention. It is linked with a patient-facing app that includes structured education, culturally inclusive language options, and meal ideas. Through the feedback sessions, iterative changes were made around visualization and patient safety, and participants were positive toward the potential user experience. In the 13 questionnaires with women with GDM, 100% said it would fit into their lifestyle and help them manage GDM. Educational resources and the “request a call” functions were well received with 61.5% (8/13) and 69.2% (9/13) saying they were very likely or likely to use these, respectively. Conclusion: A user-centered mHealth tool consisting of a clinical dashboard linked with a patient-facing app for GDM care and management has been designed. Evaluation of the interactive design by end users was positive and showed that it met their needs.
- 29 November 2024
- Published by SAGE Publications in Journal of Diabetes Science and Technology
- Vol. 20 (3) , 930-941
Open AccessThe User-Centered Design of a Clinical Dashboard and Patient-Facing App for Gestational Diabetes
Background: The number of pregnancies affected by gestational diabetes mellitus (GDM) is growing. With the increased use of smartphones and predictive modeling, a mobile health (mHealth) solution could be developed to improve care and management of GDM while streamlining care through risk stratification. Methods: A user-centered mHealth tool was designed from ethnographic observations and 11 semi-structured interviews (six health care professionals [HCPs] and five women with GDM), followed by iterative changes and evaluation from three feedback groups with 31 participants (17 HCPs, 14 researchers) and 13 questionnaires with women with GDM. Results: “MyGDM” includes a clinical dashboard that centralizes the clinic’s patients, highlighting off-target blood glucose and predicting the need for pharmacological intervention. It is linked with a patient-facing app that includes structured education, culturally inclusive language options, and meal ideas. Through the feedback sessions, iterative changes were made around visualization and patient safety, and participants were positive toward the potential user experience. In the 13 questionnaires with women with GDM, 100% said it would fit into their lifestyle and help them manage GDM. Educational resources and the “request a call” functions were well received with 61.5% (8/13) and 69.2% (9/13) saying they were very likely or likely to use these, respectively. Conclusion: A user-centered mHealth tool consisting of a clinical dashboard linked with a patient-facing app for GDM care and management has been designed. Evaluation of the interactive design by end users was positive and showed that it met their needs.
- Open Access
iDiabetes platform—enhanced phenotyping of patients with diabetes for precision diagnosis, prognosis and treatment: study protocol for a cluster-randomised controlled study in Tayside, Scotland
Introduction and aim: Diabetes is a global health emergency with increasing prevalence and diabetes-associated morbidity and mortality. One of the challenges in optimising diabetes care is translating research advances in this heterogeneous disease into clinical care. A potential solution is the introduction of precision medicine approaches into diabetes care. We aim to develop a digital platform called ‘intelligent Diabetes’ (iDiabetes) to support a precision diabetes care model in Scotland and assess its impact on the primary composite outcome of all-cause mortality, hospitalisation rate, renal function decline and glycaemic control. Methods and analysis: The impact of iDiabetes will be evaluated through a cluster-randomised controlled study, recruiting up to 22 500 patients with diabetes. Primary care general practices (GPs) in the National Health Service (NHS) Scotland Tayside Health Board are the units (clusters) of randomisation. Each primary care GP will form one cluster (approximately 400 patients per cluster), with up to 60 clusters recruited. Randomisation will be to iDiabetes (guideline support ), iDiabetesPlus or usual diabetes care (control arm). Patients of participating primary care GPs are automatically enrolled on the study when they attend for their annual diabetes screening or are newly diagnosed with diabetes. A composite hierarchical primary outcome, evaluated using Win-Ratio statistical methodology, will consist of (1) all-cause mortality, (2) all-cause hospitalisation rate, (3) proportion with >40% estimated glomerular filtration rate [eGFR] reduction from baseline or new development of end-stage renal disease, (4) proportion with absolute HbA1C reduction >0.5%. Outcomes will be evaluated after a 2-year median follow-up period. Comprehensive qualitative and health economic analyses will be conducted, assessing the cost-effectiveness, budget impact and user acceptability of the iDiabetes platform. Ethics and dissemination: This study was reviewed by the NHS Health Research Authority and approved by the East of Scotland Research Ethics Committee (reference: 23/ES/0008). Study findings will be disseminated via publications, presented at scientific conferences and shared with patients and the public on the study website and social media. Trial registration number: ISRCTN18000901 .
Open AccessiDiabetes platform—enhanced phenotyping of patients with diabetes for precision diagnosis, prognosis and treatment: study protocol for a cluster-randomised controlled study in Tayside, Scotland
Introduction and aim: Diabetes is a global health emergency with increasing prevalence and diabetes-associated morbidity and mortality. One of the challenges in optimising diabetes care is translating research advances in this heterogeneous disease into clinical care. A potential solution is the introduction of precision medicine approaches into diabetes care. We aim to develop a digital platform called ‘intelligent Diabetes’ (iDiabetes) to support a precision diabetes care model in Scotland and assess its impact on the primary composite outcome of all-cause mortality, hospitalisation rate, renal function decline and glycaemic control. Methods and analysis: The impact of iDiabetes will be evaluated through a cluster-randomised controlled study, recruiting up to 22 500 patients with diabetes. Primary care general practices (GPs) in the National Health Service (NHS) Scotland Tayside Health Board are the units (clusters) of randomisation. Each primary care GP will form one cluster (approximately 400 patients per cluster), with up to 60 clusters recruited. Randomisation will be to iDiabetes (guideline support ), iDiabetesPlus or usual diabetes care (control arm). Patients of participating primary care GPs are automatically enrolled on the study when they attend for their annual diabetes screening or are newly diagnosed with diabetes. A composite hierarchical primary outcome, evaluated using Win-Ratio statistical methodology, will consist of (1) all-cause mortality, (2) all-cause hospitalisation rate, (3) proportion with >40% estimated glomerular filtration rate [eGFR] reduction from baseline or new development of end-stage renal disease, (4) proportion with absolute HbA1C reduction >0.5%. Outcomes will be evaluated after a 2-year median follow-up period. Comprehensive qualitative and health economic analyses will be conducted, assessing the cost-effectiveness, budget impact and user acceptability of the iDiabetes platform. Ethics and dissemination: This study was reviewed by the NHS Health Research Authority and approved by the East of Scotland Research Ethics Committee (reference: 23/ES/0008). Study findings will be disseminated via publications, presented at scientific conferences and shared with patients and the public on the study website and social media. Trial registration number: ISRCTN18000901 .
- Open Access
- 15 March 2024
- Published by Elsevier in Primary Care Diabetes
- Vol. 18 (3) , 340-346
Digitising diabetes education for a safer Ramadan: Design, delivery, and evaluation of massive open online courses in Ramadan-focused diabetes education
- 15 March 2024
- Published by Elsevier in Primary Care Diabetes
- Vol. 18 (3) , 340-346
Open AccessDigitising diabetes education for a safer Ramadan: Design, delivery, and evaluation of massive open online courses in Ramadan-focused diabetes education
- Open Access
- 18 November 2023
- Published by Springer Nature in Diabetologia
- Vol. 67 (2) , 223-235
Diabetes and artificial intelligence beyond the closed loop: a review of the landscape, promise and challenges
The discourse amongst diabetes specialists and academics regarding technology and artificial intelligence (AI) typically centres around the 10% of people with diabetes who have type 1 diabetes, focusing on glucose sensors, insulin pumps and, increasingly, closed-loop systems. This focus is reflected in conference topics, strategy documents, technology appraisals and funding streams. What is often overlooked is the wider application of data and AI, as demonstrated through published literature and emerging marketplace products, that offers promising avenues for enhanced clinical care, health-service efficiency and cost-effectiveness. This review provides an overview of AI techniques and explores the use and potential of AI and data-driven systems in a broad context, covering all diabetes types, encompassing: (1) patient education and self-management; (2) clinical decision support systems and predictive analytics, including diagnostic support, treatment and screening advice, complications prediction; and (3) the use of multimodal data, such as imaging or genetic data. The review provides a perspective on how data- and AI-driven systems could transform diabetes care in the coming years and how they could be integrated into daily clinical practice. We discuss evidence for benefits and potential harms, and consider existing barriers to scalable adoption, including challenges related to data availability and exchange, health inequality, clinician hesitancy and regulation. Stakeholders, including clinicians, academics, commissioners, policymakers and those with lived experience, must proactively collaborate to realise the potential benefits that AI-supported diabetes care could bring, whilst mitigating risk and navigating the challenges along the way. Graphical Abstract
- 18 November 2023
- Published by Springer Nature in Diabetologia
- Vol. 67 (2) , 223-235
Open AccessDiabetes and artificial intelligence beyond the closed loop: a review of the landscape, promise and challenges
The discourse amongst diabetes specialists and academics regarding technology and artificial intelligence (AI) typically centres around the 10% of people with diabetes who have type 1 diabetes, focusing on glucose sensors, insulin pumps and, increasingly, closed-loop systems. This focus is reflected in conference topics, strategy documents, technology appraisals and funding streams. What is often overlooked is the wider application of data and AI, as demonstrated through published literature and emerging marketplace products, that offers promising avenues for enhanced clinical care, health-service efficiency and cost-effectiveness. This review provides an overview of AI techniques and explores the use and potential of AI and data-driven systems in a broad context, covering all diabetes types, encompassing: (1) patient education and self-management; (2) clinical decision support systems and predictive analytics, including diagnostic support, treatment and screening advice, complications prediction; and (3) the use of multimodal data, such as imaging or genetic data. The review provides a perspective on how data- and AI-driven systems could transform diabetes care in the coming years and how they could be integrated into daily clinical practice. We discuss evidence for benefits and potential harms, and consider existing barriers to scalable adoption, including challenges related to data availability and exchange, health inequality, clinician hesitancy and regulation. Stakeholders, including clinicians, academics, commissioners, policymakers and those with lived experience, must proactively collaborate to realise the potential benefits that AI-supported diabetes care could bring, whilst mitigating risk and navigating the challenges along the way. Graphical Abstract
- Open Access
- 17 August 2022
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 11 (8) , e26237
Digital Interventions Supporting Self-care in People With Type 2 Diabetes Across Greater Manchester (Greater Manchester Diabetes My Way): Protocol for a Mixed Methods Evaluation
Background: Type 2 Diabetes (T2D) is common, with a prevalence of approximately 7% of the population in the United Kingdom. The quality of T2D care is inconsistent across the United Kingdom, and Greater Manchester (GM) does not currently achieve the National Institute for Health and Care Excellence treatment targets. Barriers to delivery of care include low attendance and poor engagement with local T2D interventions, which tend to consist of programs of education delivered in traditional, face-to-face clinical settings. Thus, a flexible approach to T2D management that is accessible to people from different backgrounds and communities is needed. Diabetes My Way (DMW) is a digital platform that offers a comprehensive self-management and educational program that should be accessible to a wide range of people through mobile apps and websites. Building on evidence generated by a Scotland-wide pilot study, DMW is being rolled out and tested across GM. Objective: The overarching objectives are to assess whether DMW improves outcomes for patients with T2D in the GM area, to explore the acceptability of the DMW intervention to stakeholders, and to assess the cost-effectiveness of the intervention. Methods: A mixed methods approach will be used. We will take a census approach to recruitment in that all eligible participants in GM will be invited to participate. The primary outcomes will be intervention-related changes compared with changes observed in a matched group of controls, and the secondary outcomes will be within-person intervention-related changes. The cost-effectiveness analysis will focus on obtaining reliable estimates of how each intervention affects risk factors such as HbA1c and costs across population groups. Qualitative data will be collected via semistructured interviews and focus groups and organized using template analysis. Results: As of May 10, 2021, a total of 316 participants have been recruited for the quantitative study and have successfully enrolled. A total of 278 participants attempted to register but did not have appropriate permissions set by the general practitioners to gain access to their data. In total, 10 participants have been recruited for the qualitative study (7 practitioners and 3 patients). An extension to recruitment has been granted for the quantitative element of the research, and analysis should be complete by December 2022. Recruitment and analysis for the qualitative study should be complete by December 2021. Conclusions: The findings from this study can be used both to develop the DMW system and improve accessibility and usability in more deprived populations generally, thus improving equity in access to support for T2D self-management.
- 17 August 2022
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 11 (8) , e26237
Open AccessDigital Interventions Supporting Self-care in People With Type 2 Diabetes Across Greater Manchester (Greater Manchester Diabetes My Way): Protocol for a Mixed Methods Evaluation
Background: Type 2 Diabetes (T2D) is common, with a prevalence of approximately 7% of the population in the United Kingdom. The quality of T2D care is inconsistent across the United Kingdom, and Greater Manchester (GM) does not currently achieve the National Institute for Health and Care Excellence treatment targets. Barriers to delivery of care include low attendance and poor engagement with local T2D interventions, which tend to consist of programs of education delivered in traditional, face-to-face clinical settings. Thus, a flexible approach to T2D management that is accessible to people from different backgrounds and communities is needed. Diabetes My Way (DMW) is a digital platform that offers a comprehensive self-management and educational program that should be accessible to a wide range of people through mobile apps and websites. Building on evidence generated by a Scotland-wide pilot study, DMW is being rolled out and tested across GM. Objective: The overarching objectives are to assess whether DMW improves outcomes for patients with T2D in the GM area, to explore the acceptability of the DMW intervention to stakeholders, and to assess the cost-effectiveness of the intervention. Methods: A mixed methods approach will be used. We will take a census approach to recruitment in that all eligible participants in GM will be invited to participate. The primary outcomes will be intervention-related changes compared with changes observed in a matched group of controls, and the secondary outcomes will be within-person intervention-related changes. The cost-effectiveness analysis will focus on obtaining reliable estimates of how each intervention affects risk factors such as HbA1c and costs across population groups. Qualitative data will be collected via semistructured interviews and focus groups and organized using template analysis. Results: As of May 10, 2021, a total of 316 participants have been recruited for the quantitative study and have successfully enrolled. A total of 278 participants attempted to register but did not have appropriate permissions set by the general practitioners to gain access to their data. In total, 10 participants have been recruited for the qualitative study (7 practitioners and 3 patients). An extension to recruitment has been granted for the quantitative element of the research, and analysis should be complete by December 2022. Recruitment and analysis for the qualitative study should be complete by December 2021. Conclusions: The findings from this study can be used both to develop the DMW system and improve accessibility and usability in more deprived populations generally, thus improving equity in access to support for T2D self-management.
- Open Access
- 22 April 2022
- Published by Wiley in Diabetic Medicine
- Vol. 39 (8) , e14842
Education at scale: Improvements in type 1 diabetes self‐management following a massive open online course
- 22 April 2022
- Published by Wiley in Diabetic Medicine
- Vol. 39 (8) , e14842
Open AccessEducation at scale: Improvements in type 1 diabetes self‐management following a massive open online course