Diagnosis Of Diabetic Disease Research Articles

Rates of Eye Care and Diabetic Eye Disease among Insured Patients with Newly Diagnosed Type 2 Diabetes

To determine rates of eye examinations and diabetic eye disease in the first 5 years after diagnosis of type 2 diabetes (DM2) among continuously insured adults. Retrospective, longitudinal cohort study. Insured patients aged 40 years or older with newly diagnosed DM2 (n = 42 684), and control patients without diabetes matched on age, sex, and race were identified from a nationwide commercial claims database containing data from 2007 to2015. All patients were tracked for 6 years: 1 year before and 5 years after the index diabetes diagnosis. Receipt of eye care for individual patients was identified using International Classification of Diseases 9th edition (ICD-9) procedure codes or Current Procedural Terminology (CPT) codes indicating an eye examination, as well as encounters indicating the patient was seen by an ophthalmologist. A diagnosis of diabetic eye disease was determined by using ICD-9 codes. Outcome measures included annual receipt of eye care and development of diabetic eye disease, namely, diabetic retinopathy (DR). Associations between these outcomes and demographic factors were tested with multivariable logistic regression. Diabetic patients received more eye examinations than controls in each year, but no more than 40.4% of diabetic patients received an examination in any given year. Patients with Medicare Advantage received fewer eye examinations at 5 years (odds ratio [OR], 0.79; P < 0.01) than those with private insurance but were less likely to develop DR (OR, 0.71; P < 0.01). Hispanic patients had higher rates of DR (OR, 1.60; P < 0.01) and received fewer eye examinations (OR, 0.75; P < 0.01) at 5 years compared with White patients. Men received fewer eye examinations (OR, 0.84; P < 0.01) and were more likely to develop DR at 5 years (OR, 1.17; P < 0.01) than women. Patients with higher education were more likely to receive an eye examination and less likely to develop DR. The majority of diabetic patients do not receive adequate eye care within the 5 years after initial diabetes diagnosis despite having insurance. Efforts should be made to improve adherence to screening guidelines, especially for vulnerable populations.

Assessment of urinary NGAL for differential diagnosis and progression of diabetic kidney disease

ObjectiveChronic kidney disease (CKD) related to diabetes has become more common than glomerulonephritis in recent years. Given the inefficient and difficult identification of diabetic kidney disease (DKD) from non-diabetic kidney disease (NDKD) as well as a result of emerging evidence supporting a role for tubular involvement in DKD, we aimed to investigate the utility of urinary neutrophil gelatinase-associated lipocalin (uNGAL) in the differential diagnosis and predictive value of DKD from NDKD. MethodsData for 100 type 2 diabetic patients with CKD at our center from June 2016 to August 2019 were reviewed. All the patients were categorized into 2 groups by the renal biopsy results: DKD and NDKD. Urinary NGAL levels were normalized by urinary creatinine and calculated as uNGAL/creatinine ratios (uNCR). The independent factors of the occurrence of DKD and the diagnostic implications of uNCR were explored by logistic regression and receiver-operating characteristic (ROC) curve analysis. In addition, we analyzed the relationship between uNCR and proteinuria in patients with DKD by Pearson test and linear regression. Kaplan-Meier survival analysis was performed to assess the prospective association of uNCR with the renal outcome. ResultsSignificantly higher levels of uNCR were observed in patients with DKD when compared to those with NDKD (28.65 ng/mg vs 27.47 ng/mg, p< .001). uNCR was identified as an independent risk factor for the occurrence of DKD in diabetic patients with CKD (odds ratio [OR] = 1.020; 95%CI = [1.001–1.399], p = .042). The optimal cutoff value of uNCR for predicting DKD was 60.685 ng/mg with high specificity (90.5%) but relatively low sensitivity (55.7%). In Pearson test, uNCR was positively correlated with proteinuria, serum creatine, blood urea nitrogen, duration of diabetes, interstitial inflammation score and global sclerosis, whereas it was inversely correlated with eGFR, hemoglobin, serum albumin and 25-hydroxy vitamin D. Furthermore, in a fully adjusted model including eGFR, serum albumin and total cholesterol, the group with uNCR>60.685 ng/mg was associated with 7.595 times higher likelihood of nephrotic-range proteinuria compared to the group with uNCR≤60.685 ng/mg. In the Kaplan-Meier survival analysis, the event-free survival probability in patients with uNCR>60.685 ng/mg was significantly lower than those with uNCR≤60.685 ng/mg (p = .048). ConclusionsuNCR might serve as a potential tool for identifying cases in which there was a high clinical suspicion of DKD and that in whom confirmatory biopsy could be considered, and the best predictive cutoff value of normalized uNCR for DKD diagnosis was 60.685 ng/mg. Type 2 diabetic patients with increased level of uNCR had higher risk to nephrotic-range proteinuria and worse renal outcome.

Abstract PR16: Association of renal cell carcinoma subtypes with race/ethnicity and comorbid medical conditions

Abstract Background: Renal cell carcinomas (RCC) comprise distinct subtypes that differ in molecular characteristics and prognosis. The distribution of these subtypes varies by race/ethnicity. Hypertension, obesity, chronic kidney disease, and diabetes have been associated with increased risk of RCC, and emerging evidence suggests that the risk may be subtype specific. We assessed whether race/ethnicity and comorbidities were independently associated with RCC subtypes. Methods: Using population-based data from the California Cancer Registry linked to the Office of Statewide Health Planning and Development, we identified non-Latino White, non-Latino Black, Latino, and Asian/ Pacific Islander adults diagnosed with their first microscopically confirmed RCC between 2005 and 2015. Diagnosis of hypertension, diabetes, and kidney disease was defined by ICD-9 and ICD-10 codes present prior to RCC diagnosis. We used multivariable logistic regression to model the association of the three main RCC subtypes (clear cell, papillary, and chromophobe) with race/ethnicity adjusting for comorbidity, sex, neighborhood socioeconomic status, age, and year of diagnosis. Results: Of the 40,016 cases of RCC included, 62.6% were clear cell, 10.9% papillary, and 6.0% chromophobe. There were striking differences in the proportion of clear cell and papillary subtypes by race/ethnicity, ranging from 40.4% clear cell and 30.4% papillary in non-Latino Black adults to 70.7% clear cell and 4.5% papillary in Latino adults. The prevalence of comorbid conditions also varied by race/ethnicity—most notably the greater prevalence of kidney disease in the non-Latino Black group. In multivariable analysis, non-Latino Black individuals had a higher likelihood of presenting with papillary (odds ratio (OR) 3.35, 95% confidence interval (CI) 3.05-3.68) and chromophobe (OR 1.23, 95% CI 1.06-1.44) subtype compared to those identified as non-Latino White. In contrast, both Latino and Asian/Pacific Islander individuals were more likely than those of non-Latino White race/ethnicity to present with clear-cell subtype (OR 1.48, 95% CI 1.41-1.56 and OR 1.30, 95% CI 1.20-1.40, respectively). Clear-cell subtype was associated with diabetic renal disease (OR 1.39, 95%CI 1.23-1.58) and uncomplicated diabetes (OR 1.29, 95% CI 1.22-1.37), while papillary subtype was associated with hypertension (OR 1.22, 95% CI 1.13-1.32), hypertensive renal disease (OR 1.53, 95% CI 1.34-1.75), and end-stage renal disease (OR 1.55, 95% CI 1.31-1.84). Conclusion: In addition to race/ethnicity, specific comorbidities are associated with RCC subtype. The association of diabetes, hypertension, and end-stage renal disease with RCC subtype may provide clues to disease etiology as well as avenues for disease prevention. This abstract is also being presented as Poster D119. Citation Format: Daphne Y. Lichtensztajn, Brenda M. Hofer, John T. Leppert, James D. Brooks, Benjamin I. Chung, Sumit A. Shah, Mindy C. DeRouen, Scarlett L. Gomez, Iona Cheng. Association of renal cell carcinoma subtypes with race/ethnicity and comorbid medical conditions [abstract]. In: Proceedings of the Twelfth AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2019 Sep 20-23; San Francisco, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2020;29(6 Suppl_2):Abstract nr PR16.

Correlation of Serum Urea and Serum Creatinine in Diabetics patients and normal individuals

Diabetic Nephropathy in the long run leads to end Stage Renal Disease (ESRD). Serum Creatinine and Serum Urea are recognised as ideal markers to co-relate the progression of diabetic nephropathy. Diabetic Nephropathy is clinically diagnosed with decrease in Glomerular function rate (GFR), probability of hypertension, cardiovascular diseases and morbidity or mortality caused due to it. The early detection of an imbalance in the level of Urea and Creatinine levels can assist in the diagnosis and prevention of Diabetic Renal diseases and its progression. In this study, the period of the commencement of Diabetes and its severity is intensely correlated with an abnormal level of Urea but not so with that of Creatinine. While Creatinine is regarded as greater sensitive index of kidney function than Urea and hence this justifies as the requirement for a perfect filtration marker.

SAT-621 Framingham Cardiovascular Disease 10-Year-Risk Score Is Associated with Myocardial Perfusion in Asymptomatic Diabetic Patients

Background: Even without atherosclerosis, diabetes increases the risk of death from coronary heart disease and heart failure. Myocardial perfusion dysfunction may occur in the early stage of diabetic cardiomyopathy, but its examination method is relatively complex. It is very important to carry out targeted cardiac screening to find the factors related to diabetic myocardial perfusion in the early stage.Methods: We enrolled 77 patients with diabetes and 30 controls, performed anthropometric and laboratory tests such as blood glucose and lipids, and calculated Framingham Cardiovascular Disease 10-year-risk Score (FRS). All participants underwent cardiac magnetic resonance examinations and recorded their cardiac structure, functional indicators (such as ejection fraction (EF), end-diastolic volume (EDV), end-systolic volume (ESV), stroke volume(SV), peak filling rate (PFR),myocardial perfusion index (maximum upslope (Slope), half time to maximum signal intensity (Time50Max (s)), time to maximum signal intensity (TimeMax (s)), the maximum signal intensity (MaxSI),, basic signal intensity (Baseline),the ratio of MaxSI and Baseline ((MaxSI (BL) %), the difference value between MaxSI and Baseline (MaxSI (BL))).Results: Compared with normal group, no cardiovascular symptoms of left ventricular and right ventricular systolic function in patients with diabetes and end-diastolic and end systolic volume had no obvious difference, left ventricular PFR is lower than normal (279.65 + 57.62 vs. 322.57 + / - 78.29, p = 0.02), in the subgroup analysis we found that the FRS high-risk groups, ventricular septal thickening tend to, and Slope, MaxSI, MaxSI BL (%), MaxSI (BL) were significantly lower than the high risk group, Time50Max and TimeMax were significantly longer than the non-high-risk group, and FRS was negatively correlated with Slope, MaxSI(%BL) and positively correlated with TimeMax(s) and Time50Max(s), with statistical significance.Conclusion: Systolic function remains and diastolic function decreases in asymptomatic diabetic patients. Moreover, the patients with high risk of FRS had significant decreased perfusion function, and the quantitative indexes of perfusion function were closely related to FRS. It is of great value to pay attention to the changes of FRS score for early screening and diagnosis of diabetic heart disease.

Comparison of performance of k-nearest neighbor algorithm using smote and k-nearest neighbor algorithm without smote in diagnosis of diabetes disease in balanced data

According to the Indonesian Health Profile in 2017, diabetes is one of the causes of death for almost 70% in the world. The high mortality rate induces the need for making the effort to reduce the number of people with diabetes by conducting studies that lead to making a diagnosis so that can detect a person with diabetes accurately. This study tries to compare the performance of the K-Nearest Neighbors algorithm using Synthetic Minority Over-sampling Technique and the K-Nearest Neighbors algorithm without Synthetic Minority Over-sampling Technique in diagnosing diabetes on imbalanced datasets. The parameters tested are the k value of the K-Nearest Neighbors and Synthetic Minority Over-sampling Technique. The testing is carried out using the K-Fold Cross Validation strategy. The data used in this study were 3876 data from Pertamina Central Hospital. Based on the results of tests conducted, it shows that the value of accuracy produced in diagnosing diabetes by using Synthetic Minority Over-sampling Technique is better than the accuracy produced without using Synthetic Minority Over-sampling Technique with the highest accuracy increase of 8.25%. The highest average accuracy is obtained when the value of k = 3 in the K-Nearest Neighbors, k = 5 in the Synthetic Minority Over-sampling Technique, and fold = 10, which reaches 78.06%.

Artificial Neural Networks Based Decision Support System for the Detection of Diabetic Retinopathy

Machine learning methods have been frequently used for the diagnosis of several diseases recently because of its reliability and convenience. In this paper, a comprehensive overview of the literature related to diabetes and diabetic retinopathy has been done and diagnosis of diabetic retinopathy disease is investigated. Artificial Neural Networks (ANN) method has been applied to the problem using Rapid Miner, a data mining tool. Some other methods have also adapted to the problem, but ANN based detection approach gave the best results. 88.52% sensitivity has been obtained using the features of Messidor dataset. Besides showing the success of ANN in diabetic retinopathy detection, this study also proved that Rapid Miner can be used effectively for the analysis of diabetic retinopathy.

The Role of Podocytes and Podocyte-Associated Biomarkers in Diagnosis and Treatment of Diabetic Kidney Disease.

Diabetic kidney disease (DKD) is an important public health problem. Podocyte injury is a central event in the mechanism of DKD development. Podocytes are terminally differentiated, highly specialized glomerular visceral epithelial cells critical for the maintenance of the glomerular filtration barrier. Although potential mechanisms by which diabetic milieu contributes to irreversible loss of podocytes have been described, identification of markers that prognosticate either the development of DKD or the progression to end-stage kidney disease (ESKD) have only recently made it to the forefront. Currently, the most common marker of early DKD is microalbuminuria; however, this marker has significant limitations: not all diabetic patients with microalbuminuria will progress to ESKD and as many as 30% of patients with DKD have normal urine albumin levels. Several novel biomarkers indicating glomerular or tubular damage precede microalbuminuria, suggesting that the latter develops when significant kidney injury has already occurred. Because podocyte injury plays a key role in DKD pathogenesis, identification of markers of early podocyte injury or loss may play an important role in the early diagnosis of DKD. Such biomarkers in the urine include podocyte-released microparticles as well as expression of podocyte-specific markers. Here, we review the mechanisms by which podocyte injury contributes to DKD as well as key markers that have been recently implicated in the development and/or progression of DKD and might serve to identify individuals that require earlier preventative care and treatment in order to slow the progression to ESKD.

Use of urinary proteomics in diagnosis and monitoring of diabetic kidney disease

Use of urinary proteomics in diagnosis and monitoring of diabetic kidney disease

Glomerular Diseases in Patients with Diabetes Mellitus: An Underappreciated Epidemic.

The prevalence of nondiabetic kidney disease (NDKD) in patients with diabetes reflects the rising incidence of diabetes in the general population. The most current national prevalence of diabetes in United States adults is at a high of 12.2%. A contributing factor is the obesity epidemic, as 87.5% of diabetic adults are overweight or obese. It is well known that CKD and ESKD cause significant morbidity and mortality in obese and diabetic populations, with an estimated 36.5% of diabetics experiencing CKD (1). The relative risk of ESKD is higher in diabetics, ranging from 6.2 in white populations to 62.0 in Native Americans; of patients who start RRT, 51% are estimated to have diabetes (2). The diagnosis of diabetic kidney disease (DKD) is most often made clinically. However, there is growing awareness of the prevalence of NDKD with or without concomitant diabetic nephropathy (DN) in patients with diabetes. In turn, a large proportion of NDKD found on kidney biopsies is glomerular diseases. This knowledge draws attention to the possibility of undiagnosed, potentially reversible lesions in this population. Here, we review the prevalence and presentation of NDKD in diabetic patients, with a focus on glomerular lesions, and discuss the ways in which diabetes can affect the diagnosis and management of these conditions. A review of native kidney biopsies for evidence of NDKD in diabetics performed at the Columbia Renal Pathology Laboratory in 2011 estimated that 23.5% of patients with native kidney biopsies carry a diagnosis of diabetes, roughly double the prevalence of diabetes in United States adults. Of those patients, 37% had DN alone, 36% had NDKD alone, and 27% had concomitant DN and NDKD (3). A retrospective examination of renal biopsies at the Southern California Permanente Medical Group between 1995 and 2005 found larger proportions of patients with NDKD alone (53.2%) …

SAT-158 Early Diagnosis of Diabetic Kidney Disease through Histopathology Biomarkers

Background: Diabetic kidney disease (DKD) is universally spotted on the standards of persistent albuminuria. However, numerous diabetic patients may remain normoalbuminuric upon reaching a persistent glomerular filtration rate (GFR) of <60 mL/min. The objective of the present research study was to examine the occurrence and grouping of DKD renal microstructure insults in patients with diabetes mellitus (DM). Material and Methods: In this prospective study, we performed kidney biopsy of 29 patients; DM type 1 (3, 10.3%) and type 2 (26, 89.7%) with DM history >5 years and HbA1c above 6.5%. Serum creatinine, eGFR, albuminuria (>30mg/dL) and serum cholesterol were included as part of laboratory and clinical parameters. The mean age of the subjects was 52.3 ± 7.9 years. The creatinine (1.00 ± 0.15) and proteinuria (10.6 ± 4.6) of the patients were well within normal range and eGFR was >60mL/min/1.73m2. Overall, 79.3% of the subjects had hypertensive history, while 65.5% demonstrated dyslipidemia. CKD Class II was found to be the major Class affecting the studied subjects; 75.9%. Coronary Artery Disease (CAD) was the predominant etiology of death (34.5%). Out of 29 patients with DM history >5 years and HbA1c greater than 6.5%, 24 (82.8%) patients had renal histopathological insults proving DKD in the absence of proteinuria and eGFR <60mL/min/1.732. The kidney size was found to be normal for both right (11.4 ± 1.0) and left (11.3 ± 0.9) kidneys through Ultrasonography investigation. Class IIa (48.3%) was found to be the leading DKD Class in our patients. Overall, the mean GBM thickness was demonstrated to be 248.7 ± 114.3 nm. The mean percentage of global glomerulosclerosis was 12.4 ± 7.8 In the absence of proteinuria and early stages of CKD (Class I and II, eGFR >60mL/min/1.73m2) in DM patients, renal histopathological evidence confirms DKD in 82.8% of our study population. The kidney biopsy would not only be helpful in identifying silent DKD, but would also allow risk stratification and treatment of DM patients with early stages of CKD who otherwise might progress to ESRD.

Comparative Study of Machine Learning Algorithms on Prediction of Diabetes Mellitus Disease

Diabetes Mellitus disease is said to occur when there is not proper generation of insulin in the body which is needed for proper regulation of glucose in the body. This health disorder leads to whole degradation of several organs including the heart, kidneys, eyes, nerves. Hence diabetes disease diagnosis by means of accurate prediction is vital. When such disease related data is given as input to several machine learning techniques it becomes an important classification problem. The purpose of the work done in this paper is to compare several classic machine learning algorithms including decision tree, logistic regression and ensemble methods to identify the more accurate classification algorithm for better prediction of the diabetes mellitus disease. This in turn would help for better and effective treatment.

CORRELATIONS OF CARDIOVASCULAR INDICATORS IN INSULIN-DEPENDENT DIABETES IN CHILDREN

In the study we examined children with type 1 diabetes, aged 8 to 17 years, divided into groups depending on the duration of the disease (up to 5 years and over 5 years) in order to study the electrocardiographic changes by daily Holter ECG monitoring depending on the duration of the disease, glycaemia and insulin therapy. Holter ECG monitoring was performed by ECG monitoring complex “DiaCard” ("SOLVAIG" JSC, Kyiv, Ukraine). During the monitoring, the subjects kept a diary of activity with a record of the symptoms, time and dose of insulin and other drugs, as well as indicators of glycaemia, time and quality of sleep. In addition to arrhythmias and conduction parameters, standard parameters of the whole ECG were determined, including ST segment analysis, as well as QT and QT corrected intervals and their dispersion. All ECG parameters per day were evaluated in comparison with the normative values of heart rate in healthy children according to sex and age. The results indicate that regardless of the duration of the disease, there are cardiac dysrhythmias, mainly associated with changes in the automatism of the sinus node and increased activity of ectopic foci of rhythm, which weakens the parasympathetic effects on the heart. Correlation analysis of the detected ECG changes in patients confirmed the progressive effect of the sympathetic part of the autonomic nervous system on heart rate, the relationship of glycaemia with repolarization of ventricles and heart rate, cardiac arrhythmias with changes in sleep structure and awakening according to heart rate. These data can be used to optimize the diagnosis of diabetic heart disease in children and to identify patients who need close attention from cardiologists.

Predictive Power of Gut Microbiome in the Clinical or Pathological Diagnosis of Diabetic Kidney Disease

Background: Diabetic kidney disease (DKD) is characterized by increasing incidence, deficient diagnostic methods and poor prognosis. Methods: Using 16S ribosomal RNA (rRNA) technique, we characterized the microbial community in patients with clinically or pathologically diagnosed DKD. Findings: Differences among groups included expanded opportunistic pathogens, sulfate-reducing bacteria and mucin-degrading bacteria and depleted bacteria producing short-chain fatty acids (SCFA) levels. Eleven microbiota-targeted markers could separate the DKD group (clinically diagnosed; n =120) from the HCDM group (DM =92, HC = 140) with an area under the curve (AUC) of 88.12% . We analyzed an independent cohort of 60 DKDs and 116 HCDMs (DM = 46, Con = 70) to assess the diagnostic efficiency, with an AUC of 79.75%. The predicted functional category referring lipid metabolism was increased in DKD, and metabolism of tyrosine, phenylalanine and tryptophan was increased in DM. DKD-enriched microbial markers were positively correlated with serum creatinine and 24h-proteinuria. We performed the same analysis on 22 biopsy-proved DKD (also named diabetic nephropathy, DN) and 22 membranous nephropathy (MN). Differences in gut microbiome were identified by linear discriminant analysis, and the relative abundance of nine genera could be used to differentiate DN from MN (AUC = 77.69%). Interpretation: The gut microbiome was associated with DKD/DN. Microbiota-associated biomarkers represent a new diagnostic test for DKD that distinguishes it from MN. Funding: The National Natural Science Foundation of China; Science and Technology Innovation Team of Henan; Foundation for Leading Personnel of Central Plains of China; National Key Research and Development Program of China. Declaration of Interests: The authors have declared that no competing interest exists. Ethics Approval Statement: Our study followed the Helsinki declaration. The Institutional Review Board of the First Affiliated Hospital of Zhengzhou University approved all protocols (2019-KY-361). All participants had the right to information about the study and signed a written informed consent before sample collection.

The gut microbiome in differential diagnosis of diabetic kidney disease and membranous nephropathy

Background Diabetic kidney disease (DKD) and membranous nephropathy (MN) are the two major causes of end-stage renal disease (ESRD). Increasing evidence has shown that intestinal dysbiosis is associated with many diseases. The aim of this study was to explore the composition of the gut microbiome in DKD and MN patients. Methods 16S rRNA gene sequencing was performed on 271 fecal samples (DKD = 129 and MN = 142), and taxonomic annotation of microbial composition and function was completed. Results We observed distinct microbial communities between the two groups, with MN samples exhibiting more severe dysbiosis than DKD samples. Relative increases in genera producing short-chain fatty acids (SCFAs) in DKD and a higher proportion of potential pathogens in MN were the main contributors to the microbiome alterations in the two groups. Five-fold cross-validation was performed on a random forest model, and four operational taxonomic unit (OTU)-based microbial markers were selected to distinguish DKD from MN. The results showed 92.42% accuracy in the training set and 94.52% accuracy in the testing set, indicating high potential for these microbiome-based markers in separating MN from DKD. Overexpression of several amino acid metabolic pathways, carbohydrate metabolism and lipid metabolism was found in DKD, while interconversion of pentose/glucoronate and membrane transport in relation to ABC transporters and the phosphotransferase system were increased in MN. Conclusion The composition of the gut microbiome appears to differ considerably between patients with DKD and those with MN. Thus, microbiome-based markers could be used as an alternative tool to distinguish DKD and MN.

Paper Clinical Value of Color Doppler Ultrasonography in Diagnosis of Lower Extremity Arterial Disease of Diabetes Patients

Objective: To evaluate the diagnostic value of color Doppler ultrasound in the diagnosis of diabetic lower extremity vascular diseases. Methods: 48 patients with diabetic lower extremity vascular disease admitted in our hos-pital from September 2018 to September 2019 were included in the study and divided into the observation group, and another 48 patients with the same period of health examination in our hospital were included in the study and divided into the control group. Both groups used color Doppler ultrasound to detect the blood flow of lower extremity vessels. The incidence of blood flow, vascular diameter and stenosis, occlusion and arteriosclerosis of the lower extremity were observed. Results: The blood flow and vascular di-ameter of the lower extremity in the observation group were significantly lower than those in the control group (p

A Comparative Analysis on Diabetes Datasets Using Data Mining Techniques

In past, many researchers have been worked on the early diagnosis of diabetes disease. They used different diabetes datasets for the prediction of diabetes disease. Diabetes disease is one of the chronic diseases and becoming a cause of death among peoples. So many factors involved which cause diabetes disease and in this way a huge amount of data increasing about diabetes disease.In this paper, we compared different cases of diabetes disease based on two different Pima Indian diabetes datasets. From previous studies we found that different deep learning and machine learning methods had been applied to these two datasets but achieved very efficient methods used to diagnose diabetes. Also, determine the research gap in the application of different methods in the biomedical field.

Glomerular podocytes in diabetic renal disease.

Diabetic nephropathy (DN) is the most common cause of end-stage renal disease (ESRD), both in the USA and in Europe; moreover, its incidence is rising worldwide. The main laboratory markers of DN progression are albuminuria and a reduction in glomerular filtration rates, although progression of the disease has been observed even in the absence of these biomarkers. Renal impairment, associated with diabetes, results from damage to the glomerular filtration barrier, at the level of highly differentiated glomerular epithelial cells: podocytes. These cells regulate glomerular filtration and many immunological processes occurring at this level. The earliest possible diagnosis of diabetic kidney disease (DKD) and implementation of intensive treatment offers the possibility of preventing or substantially delaying the onset of ESRD. In this article, we review various urinary biomarkers linked with glomerular podocyte cytophysiology as potentially sensitive diagnostic tools for the early detection of DKD. These biomarkers have predictive potential for assessing the progression toward end-stage nephropathy.

System to assist in the Diagnosis of Diabetes using Ontology and Machine Learning

Diabetes mellitus has become a public health problem in both developed and developing countries. If it is not treated early, diabetes-related complications in many vital organs of the body can become fatal. Its early detection is very important for early treatment that can prevent the disease from progressing to such complications. This article focuses on designing a system to assist in the diagnosis of diabetes disease based on medical ontology and automatic learning. The proposed method uses automatic learning algorithms as a classifier for the diagnosis of diabetes based on a medical data set. The ontology suggests a pre-processing of a coherent, consistent, interoperable and shareable knowledge basis of data and the machine learning method focuses on classification based on symptoms and medical tests. Based on the experimental results, DDAS not only offers better performance in predicting and diagnosing diabetes in individuals, but also has better accuracy in recommending useful treatment to patients.

Serum Human Epididymis Protein 4 is Associated with Renal Function and Diabetic Kidney Disease in Patients with Type 2 Diabetes Mellitus.

Human epididymis protein 4 (HE4) is an available tumor biomarker mainly for detecting ovarian cancer. However, it is unknown whether it can be a novel indicator for diagnosis of diabetic kidney disease (DKD). The aim of this study was to investigate the possibility of serum HE4 as a novel biomarker for DKD in patients with type 2 diabetes mellitus (T2DM). We enrolled 236 patients with T2DM and 82 healthy individuals. Serum HE4 was detected by ARCHITECT i2000 and compared between T2DM patients and healthy controls. The relationships between various variables and HE4 were analyzed by univariate or multivariate linear regression analyses. The receiver operating characteristic (ROC) curve was constructed to assess the diagnostic performance of HE4 for DKD. The association between HE4 and DKD was analyzed by logistic regression analysis. The serum HE4 level was significantly increased in T2DM patients (median, interquartile range (IQR), 69.7, 46.5–153.9, pM) compared with healthy control (median, IQR, 40.3 33.2–46.3, pM) (P < 0.001). Furthermore, it was higher in those with DKD (median, IQR, 211.1, 141.6–367.4, pM) than those without DKD (median, IQR, 55.5, 42.7–79.6, pM) (P < 0.001). The multivariable analysis showed that age, eGFR, HDL, CRP, and urea significantly independently correlated with HE4 level, while other variables did not. The ROC curve showed that the diagnostic performance of serum HE4 for DKD with 82.9 pM as the optimal cutoff value was good (AUC = 0.917, 95% CI: 0.872–0.961, P < 0.001, with a sensitivity and specificity of 92.1% and 76.9%, respectively) in T2DM patients. Multivariable logistic regression analysis showed that increased HE4 level was a significant, independent risk factor for DKD (OR, 95% CI, 57.7, 3.0–1112.9, P < 0.001) after adjusting for factors associated with HE4. Increased serum HE4 level is associated with decreased renal function and increased risks of DKD in patients with DM. It displays a good diagnostic value for DKD.