IntroductionEarly screening for diabetic retinopathy (DR) with an efficient and scalable method is highly needed to reduce blindness, due to the growing epidemic of diabetes. The aim of the study was to validate an artificial intelligence-enabled DR screening and to investigate the prevalence of DR in adult patients with diabetes in China.Research design and methodsThe study was prospectively conducted at 155 diabetes centers in China. A non-mydriatic, macula-centered fundus photograph per eye was collected and graded through a deep learning (DL)-based, five-stage DR classification. Images from a randomly selected one-third of participants were used for the DL algorithm validation.ResultsIn total, 47 269 patients (mean (SD) age, 54.29 (11.60) years) were enrolled. 15 805 randomly selected participants were reviewed by a panel of specialists for DL algorithm validation. The DR grading algorithms had a 83.3% (95% CI: 81.9% to 84.6%) sensitivity and a 92.5% (95% CI: 92.1% to 92.9%) specificity to detect referable DR. The five-stage DR classification performance (concordance: 83.0%) is comparable to the interobserver variability of specialists (concordance: 84.3%). The estimated prevalence in patients with diabetes detected by DL algorithm for any DR, referable DR and vision-threatening DR were 28.8% (95% CI: 28.4% to 29.3%), 24.4% (95% CI: 24.0% to 24.8%) and 10.8% (95% CI: 10.5% to 11.1%), respectively. The prevalence was higher in female, elderly, longer diabetes duration and higher glycated hemoglobin groups.ConclusionThis study performed, a nationwide, multicenter, DL-based DR screening and the results indicated the importance and feasibility of DR screening in clinical practice with this system deployed at diabetes centers.Trial registration numberNCT04240652.
Type 2 diabetes [T2D] and thyroid dysfunction [TD] often co-occur, have overlapping pathologies, and their risk increases with age. Since 1995, universal salt iodization has been implemented in China to prevent disorders caused by iodine deficiency. However, after two decades of implementation of universal salt iodization, the prevalence of TD in elderly Chinese patients with T2D is not well described and may have been underestimated. We conducted a questionnaire-based survey across 24 endocrinology centers in China between December 2015 and July 2016. Demographic and clinical data from 1677 patients with T2D were obtained and analyzed to examine the prevalence of TD along with T2D in these patients. We assessed TD prevalence according to the four TD subtypes [subclinical hypothyroidism, clinical hypothyroidism, subclinical hyperthyroidism, and clinical hyperthyroidism], TD history, gender, and age. The diagnosis rates were calculated for TD and also for the TD subtype. The number of patients reaching treatment goals for T2D [hemoglobin A1c <7%] and TD [normal free thyroxine and thyroid-stimulating hormone [TSH]] and the incidences of complications and comorbidities were recorded. Among the enrolled patients with T2D [N = 1677], TD was diagnosed in 23.79% [399/1677] out of which 61% (245/399) were previously diagnosed and 38.59% (154/399) were newly diagnosed cases. Subclinical hypothyroidism, clinical hypothyroidism, subclinical hyperthyroidism, and clinical hyperthyroidism were reported in 4.89%, 9.3%, 1.13%, and 3.16% of the total population, respectively. Among patients previously diagnosed with TD, the incidence in women [166/795; 20.88%] was higher than in men [79/882; 8.96%]. The treatment goals for TD and T2D were attained in 39.6% [97/245] and 34.41% [577/1677] of the cases, respectively. Diabetic complications and comorbidities were reported in 99.7% of patients, with peripheral neuropathy being the most common [43.46%] followed by cataract [24.73%]. We had found that the incidences of dyslipidemia, elevated LDL levels, and osteoporosis were significantly higher in patients with TD than those without TD. TD is underdiagnosed in elderly Chinese patients with T2D.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.