Efficacy of Artificial Intelligence-based Screening for Diabetic Retinopathy in Type 2 Diabetes Mellitus Patients

IntroductionDespite advances in diabetic retinopathy (DR) medications, early identification is vitally important for DR administration and remains a major challenge. This study aims to develop a novel system of multidimensional network biomarkers (MDNBs) based on a widely targeted metabolomics approach to detect DR among patients with type 2 diabetes mellitus (T2DM) efficiently.Research design and methodsIn this propensity score matching-based case-control study, we used ultra-performance liquid chromatography-electrospray ionization-tandem mass spectrometry system for serum metabolites assessment of 69 pairs of patients with T2DM with DR (cases) and without DR (controls). Comprehensive analysis, including principal component analysis, orthogonal partial least squares discriminant analysis, generalized linear regression models and a 1000-times permutation test on metabolomics characteristics were conducted to detect candidate MDNBs depending on the discovery set. Receiver operating characteristic analysis was applied for the validation of capability and feasibility of MDNBs based on a separate validation set.ResultsWe detected 613 features (318 in positive and 295 in negative ESI modes) in which 63 metabolites were highly relevant to the presence of DR. A panel of MDNBs containing linoleic acid, nicotinuric acid, ornithine and phenylacetylglutamine was determined based on the discovery set. Depending on the separate validation set, the area under the curve (95% CI), sensitivity and specificity of this MDNBs system were 0.92 (0.84 to 1.0), 96% and 78%, respectively.ConclusionsThis study demonstrates that metabolomics-based MDNBs are associated with the presence of DR and capable of distinguishing DR from T2DM efficiently. Our data also provide new insights into the mechanisms of DR and the potential value for new treatment targets development. Additional studies are needed to confirm our findings.

Download Full-text

Incidence, Progression, and Associated Risk Factors of Posterior Vitreous Detachment in Type 2 Diabetes Mellitus: Sankara Nethralaya Diabetic Retinopathy Epidemiology and Molecular Genetic Study (SN-DREAMS II, Report No. 7)

Seminars in Ophthalmology ◽

10.3109/08820538.2015.1047959 ◽

2015 ◽

Vol 32 (2) ◽

pp. 191-197 ◽

Cited By ~ 4

Author(s):

Laxmi Gella ◽

Rajiv Raman ◽

Swakshyar Saumya Pal ◽

Suganeswari Ganesan ◽

Tarun Sharma

Keyword(s):

Diabetes Mellitus ◽

Risk Factors ◽

Type 2 Diabetes ◽

Type 2 Diabetes Mellitus ◽

Diabetic Retinopathy ◽

Molecular Genetic ◽

Posterior Vitreous Detachment ◽

Molecular Genetic Study ◽

Associated Risk Factors

Download Full-text

Adherence to medication among Tunisian adults with type 2 diabetes

European Journal of Public Health ◽

10.1093/eurpub/ckaa166.1151 ◽

2020 ◽

Vol 30 (Supplement_5) ◽

Author(s):

A Amara ◽

R Ghammem ◽

N Zammit ◽

S BenFredj ◽

J Maatoug ◽

...

Keyword(s):

Diabetes Mellitus ◽

Type 2 Diabetes ◽

Type 2 Diabetes Mellitus ◽

Diabetic Retinopathy ◽

University Hospital ◽

Health Concern ◽

Eligibility Criteria ◽

Cross Sectional ◽

Adherence To Medication

Abstract Introduction Diabetes mellitus is a growing public health concern. Despite compelling evidence about the effectiveness of medications, studies have indicated that less than 50% of patients achieved therapeutic targets. The aim of this study was to assess the adherence to type 2 diabetes mellitus treatment and its determinants. Methods A cross-sectional study was conducted between April and June 2017 in the Endocrinology and internal medicine departments of Farhat Hached University Hospital in Sousse, Tunisia. A convenient sample of patients who fulfilled the eligibility criteria was recruited. A pre-tested questionnaire was used to gather information. This was followed by assessing patients' adherence to diabetes medications using the eight-item Morisky Medication Adherence Scale (MMAS-8). Results A total of 330 patients with Type 2 Diabetes Mellitus participated in this study. The mean ±SD age of patients was 58.96±10.3 with female predominance (60.3%). More than half of participants were with high cardiovascular risk. In most cases (70.6 %), participants were moderate adherent. Results showed that patients become non-adherent as the disease gets older (p = 0.001). In addition patients with health insurance were significantly more adherent comparing to those who did not have it (p = 0.01). Regarding self-care practices and other metabolic risk factors' effects, our data revealed that exercising 30 minutes below than 5 times in week and poor self-management of diet were associated with low adherence (p < 10-3). On the other hand, patients who have started insulin therapy were less adherent than those who had not yet (0.01). Patients with diabetic retinopathy or maculopathy were significantly more prone to be non- adherent, with respective percentage of 39.1% and 37.5%. Conclusions This study provides insights into the determinants of non-adherence, ultimately guiding the effective interventions through development of structured long-term policies not yet implemented. Key messages In most cases (70.6 %), participants were moderate adherent. Patients with diabetic retinopathy or maculopathy were significantly more prone to be non- adherent.

Download Full-text