Epidemiology of renal involvement in Type II diabetics (NIDDM) in Catalonia

Esmatjes, Enric; Castell, Conxa; González, Teresa; Tresserras, Ricard; Lloveras, G

doi:10.1016/0168-8227(96)01256-9

Cited by 35 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Long duration of diabetes may affect the severity of diabetes that is associated with weight loss (low BMI) and history of insulin therapy [44,45]. Since diabetic nephropathy is also caused by microvascular damage, the biomarkers of kidney dysfunction, including elevated BUN and urine dipstick test positive, are closely related to DR [24,46,47]. We found that low diastolic blood pressure was a better predictor of DR in contrast with several previous studies [2].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Diabetic retinopathy risk prediction for fundus examination using sparse learning: a cross-sectional study

Yoo

Park

2013

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

BackgroundBlindness due to diabetic retinopathy (DR) is the major disability in diabetic patients. Although early management has shown to prevent vision loss, diabetic patients have a low rate of routine ophthalmologic examination. Hence, we developed and validated sparse learning models with the aim of identifying the risk of DR in diabetic patients.MethodsHealth records from the Korea National Health and Nutrition Examination Surveys (KNHANES) V-1 were used. The prediction models for DR were constructed using data from 327 diabetic patients, and were validated internally on 163 patients in the KNHANES V-1. External validation was performed using 562 diabetic patients in the KNHANES V-2. The learning models, including ridge, elastic net, and LASSO, were compared to the traditional indicators of DR.ResultsConsidering the Bayesian information criterion, LASSO predicted DR most efficiently. In the internal and external validation, LASSO was significantly superior to the traditional indicators by calculating the area under the curve (AUC) of the receiver operating characteristic. LASSO showed an AUC of 0.81 and an accuracy of 73.6% in the internal validation, and an AUC of 0.82 and an accuracy of 75.2% in the external validation.ConclusionThe sparse learning model using LASSO was effective in analyzing the epidemiological underlying patterns of DR. This is the first study to develop a machine learning model to predict DR risk using health records. LASSO can be an excellent choice when both discriminative power and variable selection are important in the analysis of high-dimensional electronic health records.

show abstract

Section: Discussionmentioning

confidence: 99%

“…It is important to identify the patients with diabetic complications among the first-visit patients with undiagnosed diabetes, especially for clinicians [24]. Therefore, we also evaluated the discriminative ability to predict DR in newly-diagnosed diabetic patients (participants with undiagnosed diabetes).…”

Section: Methodsmentioning

confidence: 99%

Diabetic retinopathy risk prediction for fundus examination using sparse learning: a cross-sectional study

Yoo

Park

2013

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…There are several reports on the prevalence of microalbuminuria in Spain. Most of them described the frequency of this problem in diabetic patients either type I [5][6][7][8][9][10][11] or type II [12][13][14]. Some more series in hypertensive patients [15,16] and ⁄ or high cardiovascular risk subjects (including hypertensive and diabetics ones) [17] have been published.…”

Section: Introductionmentioning

confidence: 99%

Prevalence of abnormal urinary albumin excretion in a population‐based study in Spain: results from the HERMEX Study

Robles

Félix²,

Fernández-Bergés³

et al. 2012

Eur J Clin Investigation

View full text Add to dashboard Cite

show abstract

“…Based on studies of >6,000 patients, ~70% of screened type 2 diabetic patients are normoalbuminuric (42,(59)(60)(61)(62)(63)(64)(65)(66)(67). It can then be estimated that ~40% of the dipstick-negative type 2 diabetic patients who are ultimately destined to develop proteinuria will be normoalbuminuric at initial screening, whereas ~60% will be microalbuminuric.…”

Section: Type 2 Diabetesmentioning

confidence: 99%

The need for early predictors of diabetic nephropathy risk: is albumin excretion rate sufficient?

2000

View full text Add to dashboard Cite

Initial studies showing an ~80% rate of progression from microalbuminuria (MA) to proteinuria in type 1 diabetic patients led to the broad acceptance of MA as a useful clinical predictor of increased diabetic nephropathy (DN) risk. Some MA patients, however, have quite advanced renal structural changes, and MA may, in these cases, be a marker rather than a predictor of DN. More recent studies have observed only about a 30-45% risk of progression of MA to proteinuria over 10 years, while about 30% of type 1 diabetic patients with MA became normoalbuminuric and the rest remained microalbuminuric. The finding that some MA patients have only mild diabetic renal lesions is consistent with the lower than originally estimated risk of progression from MA to proteinuria and with the notion that some MA patients revert to normoalbuminuria. To increase the complexity of the scenario, some normoalbuminuric long-standing type 1 diabetic patients have well-established DN lesions and ~40% of all patients destined to progress to proteinuria are normoalbuminuric at initial screening, despite many years of diabetes. A similar picture is emerging in type 2 diabetic patients, although fewer studies have been conducted. Thus, the predictive precision for MA to progress to overt nephropathy over the subsequent decade or so is considerably less than originally described. It is unclear whether this is due to changes in the natural history of DN resulting from improved glycemia and blood pressure control, or whether there were overestimates of risk in the original studies due to the small sample sizes, post hoc analyses, and variable MA definitions. Albumin excretion rate (AER) remains the best available noninvasive predictor of DN risk and should be regularly measured according to established guidelines. However, AER may be unable to define patients who are safe from or at risk of DN with an accuracy that is adequate for optimal clinical decision making or for the design of certain clinical trials. Investigations into new risk markers or into the combined use of several currently available predictive parameters are needed.

show abstract

Epidemiology of renal involvement in Type II diabetics (NIDDM) in Catalonia

Cited by 35 publications

References 26 publications

Diabetic retinopathy risk prediction for fundus examination using sparse learning: a cross-sectional study

Diabetic retinopathy risk prediction for fundus examination using sparse learning: a cross-sectional study

Prevalence of abnormal urinary albumin excretion in a population‐based study in Spain: results from the HERMEX Study

The need for early predictors of diabetic nephropathy risk: is albumin excretion rate sufficient?

Contact Info

Product

Resources

About