XI. STRATEGIES FOR IMPROVING DIABETES CARE D iabetes is a chronic illness that requires continuing medical care and patient self-management education to prevent acute complications and to reduce the risk of long-term complications. Diabetes care is complex and requires that many issues, beyond glycemic control, be addressed. A large body of evidence exists that supports a range of interventions to improve diabetes outcomes. These standards of care are intended to provide clinicians, patients, researchers, payors, and other interested individuals with the components of diabetes care, treatment goals, and tools to evaluate the quality of care. While individual preferences, comorbidities, and other patient factors may require modification of goals, targets that are desirable for most patients with diabetes are provided. These standards are not intended to preclude more extensive evaluation and management of the patient by other specialists as needed. For more detailed information, refer to Bode (Ed.): Medical Management of Type 1 Diabetes (1), Burant (Ed): Medical Management of Type 2 Diabetes (2), and Klingensmith (Ed): Intensive Diabetes Management (3). The recommendations included are diagnostic and therapeutic actions that are known or believed to favorably affect health outcomes of patients with diabetes. A grading system (Table 1), developed by the American Diabetes Association (ADA) and modeled after existing methods, was utilized to clarify and codify the evidence that forms the basis for the recommendations. The level of evidence that supports each recommendation is listed after each recommendation using the letters A, B, C, or E.

Standards of Medical Care in Diabetes

D iabetes is a chronic illness that requires continuing medical care and ongoing patient self-management education and support to prevent acute complications and to reduce the risk of long-term complications. Diabetes care is complex and requires that many issues, beyond glycemic control, be addressed. A large body of evidence exists that supports a range of interventions to improve diabetes outcomes. These standards of care are intended to provide clinicians, patients, researchers, payors, and other interested individuals with the components of diabetes care, general treatment goals, and tools to evaluate the quality of care. While individual preferences, comorbidities, and other patient factors may require modification of goals, targets that are desirable for most patients with diabetes are provided. These standards are not intended to preclude clinical judgment or more extensive evaluation and management of the patient by other specialists as needed. For more detailed information about management of diabetes, refer to references 1–3. The recommendations included are screening, diagnostic, and therapeutic actions that are known or believed to favorably affect health outcomes of patients with diabetes. A grading system (Table 1), developed by the American Diabetes Association (ADA) and modeled after existing methods, was used to clarify and codify the evidence that forms the basis for the recommendations. The level of evidence that supports each recommendation is listed after each recommendation using the letters A, B, C, or E. These standards of care are revised annually by the ADA multidisciplinary Professional Practice Committee, and new evidence is incorporated. Members of the Professional Practice Committee and their disclosed conflicts of interest are listed in the Introduction. Subsequently, as with all position statements, the standards of care are reviewed and approved by the Executive Committee of ADA’s Board of Directors.

Standards of Medical Care in Diabetes—2010

Statistical Analysis with Missing Data

https://www.scienceopen.com/document_file/8305f7ff-79d5-49cd-b9e1-28a26f4ca691/PubMedCentral/8305f7ff-79d5-49cd-b9e1-28a26f4ca691.pdf

Standards of Medical Care in Diabetes—2009

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems-patient classification, fundamental biological processes and treatment of patients-and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.

https://royalsocietypublishing.org/doi/pdf/10.1098/rsif.2017.0387

Opportunities and obstacles for deep learning in biology and medicine.

Convolutional Neural Networks for Diabetic Retinopathy

https://www.thelancet.com/pdfs/journals/lancet/PIIS0140-6736(03)12267-2.pdf

Incidence of sight-threatening retinopathy in patients with type 2 diabetes in the Liverpool Diabetic Eye Study: a cohort study.

Objective: To measure the cost effectiveness of systematic photographic screening for sight threatening diabetic eye disease compared with existing practice. Design: Cost effectiveness analysis Setting: Liverpool. Subjects: A target population of 5000 diabetic patients invited for screening. Main outcome measures: Cost effectiveness (cost per true positive) of systematic and opportunistic programmes; incremental cost effectiveness of replacing opportunistic with systematic screening. Results: Baseline prevalence of sight threatening eye disease was 14.1%. The cost effectiveness of the systematic programme was £209 (sensitivity 89%, specificity 86%, compliance 80%, annual cost £104 996) and of the opportunistic programme was £289 (combined sensitivity 63%, specificity 92%, compliance 78%, annual cost £99 981). The incremental cost effectiveness of completely replacing the opportunistic programme was £32. Absolute values of cost effectiveness were highly sensitive to varying prevalence, sensitivity and specificity, compliance, and programme size. Conclusion: Replacing existing programmes with systematic screening for diabetic eye disease is justified.

https://www.bmj.com/content/bmj/320/7250/1627.full.pdf

Cost effectiveness analysis of screening for sight threatening diabetic eye disease

Aim To measure the cumulative incidence of any retinopathy, maculopathy and sight-threatening diabetic retinopathy (STDR), and calculate optimal screening intervals by retinopathy grade at baseline for patients with Type 1 diabetes attending an established systematic retinal screening programme.



Methods All patients with Type 1 diabetes registered with enrolled general practitioners, excluding only those attending an ophthalmologist, were studied if retinopathy data was available at baseline and at least one further screen event. Screening utilized non-stereoscopic 3-field mydriatic photography and modified Wisconsin grading. STDR was defined as moderate pre-proliferative retinopathy or greater and/or significant maculopathy in any eye.



Results Patients (n = 501) underwent 2742 screen events. Cumulative incidence of STDR in patients without baseline retinopathy was 0.3% (95% CI 0.0–0.9) at 1 year, rising to 3.9% (1.4–5.4) at 5 years. Rates of progression to STDR in patients with background and mild pre-proliferative retinopathy at 1 year were 3.6% (0.5–6.6) and 13.5% (4.2–22.7), respectively. Progression to STDR was greater in patients with a higher grade of baseline retinopathy (P = 0.001) or a longer disease duration (P = 0.003). For a 95% likelihood of remaining free of STDR, mean screening intervals by baseline status were: no retinopathy 5.7 (95% CI 3.5–7.6) years, background 1.3 (0.4–2.0) years and mild pre-proliferative 0.4 (0–0.8) years.



Conclusions Screening at 2–3 year intervals, rather than annually, for patients without retinopathy in Type 1 diabetes is feasible because of the low risk of progression to STDR, and may result in significant cost savings for a screening programme. Patients with higher grades of retinopathy require screening at least annually or more frequent.

Incidence of sight-threatening retinopathy in Type 1 diabetes in a systematic screening programme

Aims Large-scale, baseline prevalence measurements in a population at the institution of systematic retinal screening are currently unavailable. We report the prevalence of all grades of retinopathy at entry into a systematic primary care-based diabetic eye screening programme.



Methods Primary care-based photographic screening utilizing mydriasis and three-field non-stereoscopic photography for all patients with diabetes (except those under continuing care of an ophthalmologist) in Liverpool. Sight-threatening diabetic eye disease (STED) was defined as any of: moderate preproliferative retinopathy or worse, circinate maculopathy or exudates within one disc diameter of the centre of fovea.



Results Type 1 diabetes mellitus (DM) (n = 831): baseline prevalence (95% confidence interval (CI)) of any retinopathy, proliferative diabetic retinopathy (PDR) and STED was 45.7% (42.3–49.1), 3.7% (2.4–5.0) and 16.4% (13.9–18.9), respectively. Presence of STED was associated with increased disease duration (odds ratio (OR) 1.09 per year; P < 0.0001) and higher in men (OR 2.15; P = 0.001). Type 2 DM (n = 7231): baseline prevalence (95% CI) of any retinopathy, PDR and STED was 25.3% (24.3–26.3), 0.5% (0.3–0.7) and 6.0% (5.5–6.5), respectively. Presence of STED was associated with longer time since diagnosis of DM (OR 1.03; P < 0.0001) and insulin use (OR 2.46; P < 0.0001).



Conclusion This study provides baseline information for health providers on prevalence of all grades of retinopathy and STED in a large population at the establishment of systematic screening. Baseline prevalence of STED was high and highest in patients with a longer disease duration in both Type 1 and Type 2 DM.



Diabet. Med. 19, 1014–1021 (2002)

Deborah Broadbent

Papers

Convolutional Neural Networks for Diabetic Retinopathy

Incidence of sight-threatening retinopathy in patients with type 2 diabetes in the Liverpool Diabetic Eye Study: a cohort study.

Cost effectiveness analysis of screening for sight threatening diabetic eye disease

Incidence of sight-threatening retinopathy in Type 1 diabetes in a systematic screening programme

Prevalence of diabetic eye disease in patients entering a systematic primary care-based eye screening programme