RESUMEN
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.
Asunto(s)
Inteligencia Artificial , Diabetes Mellitus Tipo 1 , Humanos , Disparidades en el Estado de Salud , Diabetes Mellitus Tipo 1/terapiaRESUMEN
BACKGROUND: There is a lack of consensus on prescribing alternatives to initial metformin therapy and intensification therapy for type 2 diabetes mellitus (T2DM) management. This review aimed to identify/quantify factors associated with prescribing of specific antidiabetic drug classes for T2DM. METHODS: Five databases (Medline/PubMed, Embase, Scopus, Web of Science) were searched using the synonyms of each concept (patients with T2DM, antidiabetic drugs and factors influencing prescribing) in both free text and Medical Subject Heading (MeSH) forms. Quantitative observational studies evaluating factors associated with antidiabetic prescribing of metformin, sulfonylurea, thiazolidinedione, Dipeptidyl-peptidase 4 inhibitors (DPP4-I), sodium glucose transporter 2 inhibitors (SGLT2-I), Glucagon-Like peptide receptor agonist (GLP1-RA) and insulin in outpatient settings and published from January 2009 to January 2021 were included. Quality assessment was performed using a Newcastle-Ottawa scale. The validation was done for 20% of identified studies. The pooled estimate was measured using a three-level random-effect meta-analysis model based on odds ratio [95% confidence interval]. Age, sex, body mass index (BMI), glycaemic control (HbA1c) and kidney-related problems were quantified. RESULTS: Of 2331 identified studies, 40 met the selection criteria. Of which, 36 and 31 studies included sex and age, respectively, while 20 studies examined baseline BMI, HbA1c and kidney-related problems. The majority of studies (77.5%, 31/40) were rated as good and despite that the overall heterogeneity for each studied factor was more than 75%, it is mostly related to within-study variance. Older age was significantly associated with higher sulfonylurea prescription (1.51 [1.29-1.76]), yet lower prescribing of metformin (0.70 [0.60-0.82]), SGLT2-I (0.57 [0.42-0.79]) and GLP1-RA (0.52 [0.40-0.69]); while higher baseline BMI showed opposite significant results (sulfonylurea: 0.76 [0.62-0.93], metformin: 1.22 [1.08-1.37], SGLT2-I: 1.88 [1.33-2.68], and GLP1-RA: 2.35 [1.54-3.59]). Both higher baseline HbA1c and having kidney-related problems were significantly associated with lower metformin prescription (0.74 [0.57-0.97], 0.39 [0.25-0.61]), but more insulin prescriptions (2.41 [1.87-3.10], 1.52 [1.10-2.10]). Also, DPP4-I prescriptions were higher for patients with kidney-related problems (1.37 [1.06-1.79]) yet lower among patients with higher HbA1c (0.82 [0.68-0.99]). Sex was significantly associated with GLP1-RA and thiazolidinedione prescribing (F:M; 1.38 [1.19-1.60] and 0.91 [0.84-0.98]). CONCLUSION: Several factors were identified as potential determinants of antidiabetic drug prescribing. The magnitude and significance of each factor differed by antidiabetic class. Patient's age and baseline BMI had the most significant association with the choice of four out of the seven studied antidiabetic drugs followed by the baseline HbA1c and kidney-related problems which had an impact on three studied antidiabetic drugs, whereas sex had the least impact on prescribing decision as it was associated with GLP1-RA and thiazolidinedione only.
Asunto(s)
Diabetes Mellitus Tipo 2 , Inhibidores de la Dipeptidil-Peptidasa IV , Metformina , Tiazolidinedionas , Humanos , Hipoglucemiantes/uso terapéutico , Hipoglucemiantes/farmacología , Diabetes Mellitus Tipo 2/tratamiento farmacológico , Transportador 2 de Sodio-Glucosa/uso terapéutico , Hemoglobina Glucada , Dipeptidil Peptidasa 4/uso terapéutico , Metformina/uso terapéutico , Compuestos de Sulfonilurea/uso terapéutico , Inhibidores de la Dipeptidil-Peptidasa IV/uso terapéutico , Insulina/uso terapéutico , Tiazolidinedionas/uso terapéuticoRESUMEN
AIMS: People with pre-diabetes are at high risk of progressing to type 2 diabetes. This progression is not well characterised by ethnicity, deprivation and age, which we describe in a large cohort of individuals with pre-diabetes. METHODS: A retrospective cohort study with The Health Improvement Network (THIN) database was conducted. Patients aged 18 years and over and diagnosed with pre-diabetes [HbA1c 42 mmol/mol (6.0%) to 48 mmol/mol (6.5%) were included]. Cox proportional hazards regression was used to calculate adjusted hazard rate ratios (aHR) for the risk of progression from pre-diabetes to type 2 diabetes for each of the exposure categories [ethnicity, deprivation (Townsend), age and body mass index (BMI)] separately. RESULTS: Of the baseline population with pre-diabetes (n = 397,853), South Asian (aHR 1.31; 95% CI 1.26-1.37) or Mixed-Race individuals (aHR 1.22; 95% CI 1.11-1.33) had an increased risk of progression to type 2 diabetes compared with those of white European ethnicity. Likewise, deprivation (aHR 1.17; 95% CI 1.14-1.20; most vs. least deprived) was associated with an increased risk of progression. Both younger (aHR 0.63; 95% CI 0.58-0.69; 18 to <30 years) and older individuals (aHR 0.85; 95% CI 0.84-0.87; ≥65 years) had a slower risk of progression from pre-diabetes to type 2 diabetes, than middle-aged (40 to <65 years) individuals. CONCLUSIONS: South Asian or Mixed-Race individuals and people with social deprivation had an increased risk of progression from pre-diabetes to type 2 diabetes. Clinicians need to recognise the differing risk across their patient populations to implement appropriate prevention strategies.
Asunto(s)
Diabetes Mellitus Tipo 2 , Estado Prediabético , Persona de Mediana Edad , Humanos , Adulto , Adolescente , Diabetes Mellitus Tipo 2/epidemiología , Diabetes Mellitus Tipo 2/diagnóstico , Estado Prediabético/epidemiología , Estudios Retrospectivos , Etnicidad , Reino Unido/epidemiología , Factores de RiesgoRESUMEN
The QRISK cardiovascular disease (CVD) risk assessment model is not currently optimized for patients with type 2 diabetes mellitus (T2DM). We aim to identify if the abundantly available repeatedly measured data for patients with T2D improves the predictive capability of QRISK to support the decision-making process regarding CVD prevention in patients with T2DM. We identified patients with T2DM aged 25 to 85, not on statin treatment and without pre-existing CVD from the IQVIA Medical Research Data United Kingdom primary care database and then followed them up until the first diagnosis of CVD, ischemic heart disease, or stroke/transient ischemic attack. We included traditional, nontraditional risk factors and relevant treatments for our analysis. We then undertook a Cox's hazards model accounting for time-dependent covariates to estimate the hazard rates for each risk factor and calculated a 10-year risk score. Models were developed for males and females separately. We tested the performance of our models using validation data and calculated discrimination and calibration statistics. The study included 198,835 (180,143 male with 11,976 outcomes and 90,466 female with 8,258 outcomes) patients. The 10-year predicted survival probabilities for females was 0.87 (0.87 to 0.87), whereas the observed survival estimates from the Kaplan-Meier curve for all female models was 0.87 (0.86 to 0.87). The predicted and observed survival estimates for males were 0.84 (0.84 to 0.84) and 0.84 (0.83 to 0.84) respectively. The Harrell's C-index of all female models and all male models were 0.71 and 0.69 respectively. We found that including time-varying repeated measures, only mildly improved CVD risk prediction for T2DM patients in comparison to the current practice standard. We advocate for further research using time-varying data to identify if the involvement of further covariates may improve the accuracy of currently accepted prediction models.
Asunto(s)
Enfermedades Cardiovasculares , Diabetes Mellitus Tipo 2 , Humanos , Diabetes Mellitus Tipo 2/complicaciones , Diabetes Mellitus Tipo 2/epidemiología , Masculino , Femenino , Medición de Riesgo/métodos , Persona de Mediana Edad , Enfermedades Cardiovasculares/epidemiología , Anciano , Reino Unido/epidemiología , Adulto , Anciano de 80 o más Años , Factores de Riesgo , Modelos de Riesgos Proporcionales , Factores de Riesgo de Enfermedad CardiacaRESUMEN
The prevalence of type 2 diabetes in North West London (NWL) is relatively high compared to other parts of the United Kingdom with outcomes suboptimal. This presents a need for more effective strategies to identify people living with type 2 diabetes who need additional support. An emerging subset of web-based interventions for diabetes self-management and population management has used artificial intelligence and machine learning models to stratify the risk of complications from diabetes and identify patients in need of immediate support. In this study, two prototype risk prediction tools on the MyWay Diabetes and MyWay Clinical platforms were evaluated with six clinicians and six people living with type 2 diabetes in NWL using the think aloud method. The results of the sessions with people living with type 2 diabetes showed that the concept of the tool was intuitive, however, more instruction on how to correctly use the risk prediction tool would be valuable. The feedback from the sessions with clinicians was that the data presented in the tool aligned with the key diabetes targets in NWL, and that this would be useful for identifying and inviting patients to the practice who are overdue for tests and at risk of complications. The findings of the evaluation have been used to support the development of the prototype risk predictions tools. This study demonstrates the value of conducting usability testing on web-based interventions designed to support the targeted management of type 2 diabetes in local communities.
RESUMEN
The COVID-19 pandemic is a major international emergency leading to unprecedented medical, economic and societal challenges. Countries around the globe are facing challenges with diabetes care and are similarly adapting care delivery, with local cultural nuances. People with diabetes suffer disproportionately from acute COVID-19 with higher rates of serious complications and death. In-patient services need specialist support to appropriately manage glycaemia in people with known and undiagnosed diabetes presenting with COVID-19. Due to the restrictions imposed by the pandemic, people with diabetes may suffer longer-term harm caused by inadequate clinical support and less frequent monitoring of their condition and diabetes-related complications. Outpatient management need to be reorganised to maintain remote advice and support services, focusing on proactive care for the highest risk, and using telehealth and digital services for consultations, self-management and remote monitoring, where appropriate. Stratification of patients for face-to-face or remote follow-up should be based on a balanced risk assessment. Public health and national organisations have generally responded rapidly with guidance on care management, but the pandemic has created a tension around prioritisation of communicable vs non-communicable disease. Resulting challenges in clinical decision-making are compounded by a reduced clinical workforce. For many years, increasing diabetes mellitus incidence has been mirrored by rising preventable morbidity and mortality due to complications, yet innovation in service delivery has been slow. While the current focus is on limiting the terrible harm caused by the pandemic, it is possible that a positive lasting legacy of COVID-19 might include accelerated innovation in chronic disease management.