scholarly journals Development of a Prediction Model for Colorectal Cancer among Patients with Type 2 Diabetes Mellitus Using a Deep Neural Network

2018 ◽  
Vol 7 (9) ◽  
pp. 277 ◽  
Author(s):  
Meng-Hsuen Hsieh ◽  
Li-Min Sun ◽  
Cheng-Li Lin ◽  
Meng-Ju Hsieh ◽  
Kyle Sun ◽  
...  
Keyword(s):  
Neural Network ◽  
Diabetes Mellitus ◽  
Colorectal Cancer ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Roc Curve ◽  
Deep Neural Network ◽  
Severity Index ◽  
Increased Risk

Objectives: Observational studies suggested that patients with type 2 diabetes mellitus (T2DM) presented a higher risk of developing colorectal cancer (CRC). The current study aims to create a deep neural network (DNN) to predict the onset of CRC for patients with T2DM. Methods: We employed the national health insurance database of Taiwan to create predictive models for detecting an increased risk of subsequent CRC development in T2DM patients in Taiwan. We identified a total of 1,349,640 patients between 2000 and 2012 with newly diagnosed T2DM. All the available possible risk factors for CRC were also included in the analyses. The data were split into training and test sets with 97.5% of the patients in the training set and 2.5% of the patients in the test set. The deep neural network (DNN) model was optimized using Adam with Nesterov’s accelerated gradient descent. The recall, precision, F1 values, and the area under the receiver operating characteristic (ROC) curve were used to evaluate predictor performance. Results: The F1, precision, and recall values of the DNN model across all data were 0.931, 0.982, and 0.889, respectively. The area under the ROC curve of the DNN model across all data was 0.738, compared to the ideal value of 1. The metrics indicate that the DNN model appropriately predicted CRC. In contrast, a single variable predictor using adapted the Diabetes Complication Severity Index showed poorer performance compared to the DNN model. Conclusions: Our results indicated that the DNN model is an appropriate tool to predict CRC risk in patients with T2DM in Taiwan.

scholarly journals A multi-class classification model for supporting the diagnosis of type II diabetes mellitus

PeerJ ◽  
2020 ◽  
Vol 8 ◽  
pp. e9920
Author(s):  
Kuang-Ming Kuo ◽  
Paul Talley ◽  
YuHsi Kao ◽  
Chi Hsien Huang
Keyword(s):  
Neural Network ◽  
Diabetes Mellitus ◽  
Machine Learning ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Deep Neural Network ◽  
Classification Model ◽  
Diagnosis Code ◽  
Ensemble Techniques

Background Numerous studies have utilized machine-learning techniques to predict the early onset of type 2 diabetes mellitus. However, fewer studies have been conducted to predict an appropriate diagnosis code for the type 2 diabetes mellitus condition. Further, ensemble techniques such as bagging and boosting have likewise been utilized to an even lesser extent. The present study aims to identify appropriate diagnosis codes for type 2 diabetes mellitus patients by means of building a multi-class prediction model which is both parsimonious and possessing minimum features. In addition, the importance of features for predicting diagnose code is provided. Methods This study included 149 patients who have contracted type 2 diabetes mellitus. The sample was collected from a large hospital in Taiwan from November, 2017 to May, 2018. Machine learning algorithms including instance-based, decision trees, deep neural network, and ensemble algorithms were all used to build the predictive models utilized in this study. Average accuracy, area under receiver operating characteristic curve, Matthew correlation coefficient, macro-precision, recall, weighted average of precision and recall, and model process time were subsequently used to assess the performance of the built models. Information gain and gain ratio were used in order to demonstrate feature importance. Results The results showed that most algorithms, except for deep neural network, performed well in terms of all performance indices regardless of either the training or testing dataset that were used. Ten features and their importance to determine the diagnosis code of type 2 diabetes mellitus were identified. Our proposed predictive model can be further developed into a clinical diagnosis support system or integrated into existing healthcare information systems. Both methods of application can effectively support physicians whenever they are diagnosing type 2 diabetes mellitus patients in order to foster better patient-care planning.

scholarly journals Obesity, Hyperinsulinemia, IGF-1, and Hyperglycemia as Risk Factors for Colorectal Cancer in Patients with Type 2 Diabetes mellitus

2020 ◽  
Vol 0 (1-2) ◽  
pp. 60-63
Author(s):  
Т. С. Вацеба
Keyword(s):  
Diabetes Mellitus ◽  
Colorectal Cancer ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Study Groups ◽  
The Body ◽  
Enzyme Linked Immunosorbent Assay ◽  
Control Group ◽  
Increased Risk

The latest studies prove an increased risk of colorectal cancer in patients with type 2 diabetes mellitus. The pathogenetic factors of type 2 diabetes have been recognized as mechanisms of association between these diseases. The objective: to investigate the effects of obesity, hyperinsulinemia, IGF-1 and hyperglycemia on the development of colorectal cancer in patients with type 2 diabetes. Materials and methods. 36 patients were divided into groups: I – healthy (control group), II – patients with type 2 diabetes mellitus, III – patients with colorectal cancer without diabetes, IV – patients with a combination of two diseases. Using the method of enzyme-linked immunosorbent assay were determined levels of insulin and insulin-like growth factor-1 (IGF-1). DM compensation was assessed by the level of glycosylated hemoglobin (HbA1c) that was determined by immuno-exchange chromatography. The data obtained were analyzed using Statistica 12.0 (StatSoft Inc.,USA). Differences between the values in the control and experimental groups were determined by the Student’s t-test. The differences were considered significant at р<0.05. Results. According to the data obtained, colorectal cancer was diagnosed in patients with the age of over 60 years old with obesity. The body mass index (BMI) in patients of all study groups was higher than 30 kg/m2. Patients of group IV with a combination of type 2 diabetes and a circle of rectal cancer had significantly higher BMI compared to the control group (р<0.05). Significant hyperinsulinemia and increased IGF-1 levels were detected in patients in all study groups (р<0.05). Most patients with diabetes in both groups had HbA1c levels higher than 7.5%. Conclusions. Obesity, hyperinsulinemia, increased bioavailability of IGF-1, and hyperglycemia are pathogenetic factors in the risk of colorectal cancer in patients with type 2 diabetes. Patients over the age of 55 with diabetes, obesity, and hyperinsulinemia are advised to be screened for colorectal cancer.

The GSTM1 and GSTT1 Null Genotypes Increase the Risk for Type 2 Diabetes Mellitus and the Subsequent Development of Diabetic Complications: A Meta-analysis

2018 ◽  
Vol 15 (1) ◽  
pp. 31-43 ◽  
Author(s):  
Sayantan Nath ◽  
Sambuddha Das ◽  
Aditi Bhowmik ◽  
Sankar Kumar Ghosh ◽  
Yashmin Choudhury
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Meta Analysis ◽  
Subsequent Development ◽  
Asian Population ◽  
Gstm1 Null Genotype ◽  
Increased Risk

Background:Studies pertaining to association of GSTM1 and GSTT1 null genotypes with risk of T2DM and its complications were often inconclusive, thus spurring the present study.Methods:Meta-analysis of 25 studies for evaluating the role of GSTM1/GSTT1 null polymorphisms in determining the risk for T2DM and 17 studies for evaluating the role of GSTM1/GSTT1 null polymorphisms in development of T2DM related complications were conducted.Results:Our study revealed an association between GSTM1 and GSTT1 null polymorphism with T2DM (GSTM1; OR=1.37;95% CI =1.10-1.70 and GSTT1; OR=1.29;95% CI =1.04-1.61) with an amplified risk of 2.02 fold for combined GSTM1-GSTT1 null genotypes. Furthermore, the GSTT1 null (OR=1.56;95%CI=1.38-1.77) and combined GSTM1-GSTT1 null genotypes (OR=1.91;95%CI=1.25- 2.94) increased the risk for development of T2DM related complications, but not the GSTM1 null genotype. Stratified analyses based on ethnicity revealed GSTM1 and GSTT1 null genotypes increase the risk for T2DM in both Caucasians and Asians, with Asians showing much higher risk of T2DM complications than Caucasians for the same. </P><P> Discussion: GSTM1, GSTT1 and combined GSTM1-GSTT1 null polymorphism may be associated with increased risk for T2DM; while GSTT1 and combined GSTM1-GSTT1 null polymorphism may increase the risk of subsequent development of T2DM complications with Asian population carrying an amplified risk for the polymorphism.Conclusion:Thus GSTM1 and GSTT1 null genotypes increases the risk for Type 2 diabetes mellitus alone, in combination or with regards to ethnicity.

Epidemiology of Hypertension and Diabetes Mellitus in Latin America

2020 ◽  
Vol 16 ◽  
Author(s):  
Patricio Lopez-Jaramillo ◽  
Jose Lopez-Lopez ◽  
Daniel Cohen ◽  
Natalia Alarcon-Ariza ◽  
Margarita Mogollon-Zehr
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Latin America ◽  
Cardiovascular Diseases ◽  
Latin American ◽  
Premature Mortality ◽  
Increased Risk ◽  
And Control

: Hypertension and type 2 diabetes mellitus are two important risk factors that contribute to cardiovascular diseases worldwide. In Latin America hypertension prevalence varies from 30 to 50%. Moreover, the proportion of awareness, treatment and control of hypertension is very low. The prevalence of type 2 diabetes mellitus varies from 8 to 13% and near to 40% are unaware of their condition. In addition, the prevalence of prediabetes varies from 6 to 14% and this condition has been also associated with increased risk of cardiovascular diseases. The principal factors linked to a higher risk of hypertension in Latin America are increased adiposity, low muscle strength, unhealthy diet, low physical activity and low education. Besides being chronic conditions, leading causes of cardiovascular mortality, both hypertension and type 2 diabetes mellitus represent a substantial cost for the weak health systems of Latin American countries. Therefore, is necessary to implement and reinforce public health programs to improve awareness, treatment and control of hypertension and type 2 diabetes mellitus, in order to reach the mandate of the Unit Nations of decrease the premature mortality for CVD.

scholarly journals Risk of Depression among Early Onset Type 2 Diabetes Mellitus Patients

2021 ◽  
pp. 1-11
Author(s):  
Baizid Khoorshid Riaz ◽  
Shahjada Selim ◽  
Megan Neo ◽  
Md Nazmul Karim ◽  
M. Mostafa Zaman
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Early Onset ◽  
Tertiary Care ◽  
Positive Family History ◽  
Depression Symptoms ◽  
Mixed Effect ◽  
Increased Risk

<b><i>Methodology:</i></b> Biochemically confirmed type 2 diabetes mellitus (T2DM) patients (<i>n</i> = 1,114) were recruited from the outpatient department of 2 tertiary care hospitals in Dhaka, Bangladesh. Face-to-face interview was conducted using a semi-structured questionnaire containing sociodemographic parameters and relevant information about depression and diabetes. Biochemical test results and treatment-related information were taken from patients’ records. The Hospital Anxiety and Depression Scale (HADS) was used to screen all patients for psychiatric manifestation. Those diagnosed by HADS were subsequently reassessed using structured clinical interview for DSM-5 Disorders – Clinician Version. T2DM diagnosed at age &#x3c;40 years were considered as early onset T2DM. Association between age of onset category and depression was assessed using multivariable mixed-effect logistic regression adjusting for random variation of the area of residence and plausible confounders. <b><i>Results:</i></b> Around a third of the participants (32.5%) were diagnosed with T2DM before the age of 40 years. Early onset T2DM patients were found to have 57% increase in the risk of developing depression (OR 1.57; 95% CI 1.13–2.28; <i>p</i> = 0.011) in comparison to those with usual onset T2DM (≥40 years). Among other factors a positive family history for diabetes (OR 1.33; 95% CI 1.03–1.78; <i>p</i> = 0.038), poor glycemic control (OR 1.31; 95% CI 1.03–1.68; <i>p</i> = 0.028), presence of 1, or more diabetic complications (OR 1.37; 95% CI 1.03–1.78; <i>p</i> = 0.011) also showed increased risk of depression. <b><i>Conclusion:</i></b> Early onset T2DM patients are at greater risk of developing depression. The finding is likely to help in setting preventive strategies aiming to reduce the presence of concomitant depression symptoms among diabetes.

scholarly journals Associations of markers of arterial stiffness and remodeling with new-onset type 2 diabetes mellitus

2021 ◽  
Vol 28 (Supplement_1) ◽  
Author(s):  
F Ahmadizar ◽  
K Wang ◽  
F Mattace Raso ◽  
MA Ikram ◽  
M Kavousi
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Blood Glucose ◽  
Arterial Stiffness ◽  
Wall Stress ◽  
Lipid Lowering ◽  
Circumferential Wall Stress ◽  
Increased Risk

Abstract Funding Acknowledgements Type of funding sources: None. Background. Arterial stiffness/remodeling results in impaired blood flow and, eventually, decreased glucose disposal in peripheral tissues and increased blood glucose. Besides, increased arterial stiffness/remodeling may lead to hypertension, as a potential reciprocal risk factor for type 2 diabetes mellitus (T2D). We, therefore, hypothesized that increased arterial stiffness/remodeling is associated with an increased risk of T2D. Purpose. To study the associations between arterial stiffness/remodeling and incident T2D. Methods. We used the prospective population-based Rotterdam Study. Common carotid arterial properties were ultrasonically determined in plaque-free areas. Aortic stiffness was estimated by carotid-femoral pulse wave velocity (cf_PWV), carotid stiffness was estimated by the carotid distensibility coefficient (carDC). Arterial remodeling was estimated by carotid artery lumen diameter (carDi), carotid intima-media thickness (cIMT), mean circumferential wall stress (CWSmean), and pulsatile circumferential wall stress (CWSpuls). Cox proportional hazard regression analysis was used to estimate the associations between arterial stiffness/remodeling and the risk of incident T2D, adjusted for age, sex, cohort, mean arterial pressure (MAP), antihypertensive medications, heart rate, non- high-density lipoprotein (HDL)-cholesterol, lipid-lowering medications, and smoking. We included interaction terms in the fully adjusted models to study whether any significant associations were modified by sex, age, blood glucose, or MAP. Spearman correlation analyses were applied to examine the correlations between measurements of arterial stiffness/remodeling and glycemic traits. Results. We included 3,055 individuals free of T2D at baseline (mean (SD) age, 67.2 (7.9) years). During a median follow-up of 14.0 years, 395 (12.9%) T2D occurred. After adjustments, higher cf_PWV (hazard ratio (HR),1.18; 95%CI:1.04-1.35), carDi (1.17; 1.04-1.32), cIMT (1.15; 1.01-1.32), and CWSpuls (1.28; 1.12-1.47) were associated with increased risk of incident T2D. After further adjustment for the baseline glucose, the associations attenuated but remained statistically significant. Sex, age, blood glucose, or MAP did not modify the associations between measurements of arterial stiffness/remodeling, and incident T2D. Among the population with prediabetes at baseline (n = 513) compared to the general population, larger cIMT was associated with a greater increase in the risk of T2D. Most measurements of arterial stiffness/remodeling significantly but weakly correlated with baseline glycemic traits, particularly with blood glucose.  Conclusions. Our study suggests that greater arterial stiffness/remodeling is independently associated with an increased risk of T2D development. Blood glucose and hypertension do not seem to play significant roles in these associations. Further studies should disentangle the underlying mechanism that links arterial stiffness/remodeling and T2D.

scholarly journals P-82 Impact of type 2 diabetes mellitus in overall survival and clinical features of Latin patients with colorectal cancer: A 15-year follow-up

2021 ◽  
Vol 32 ◽  
pp. S125-S126
Author(s):  
G. Calderillo-Ruiz ◽  
C. Diaz ◽  
H. Lopez Basave ◽  
E. Ruiz-Garcia ◽  
A. Apodaca ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Colorectal Cancer ◽  
Type 2 Diabetes ◽  
Overall Survival ◽  
Type 2 Diabetes Mellitus ◽  
Clinical Features

115 RISK OF POST-COLONOSCOPY COLORECTAL CANCER IN PATIENTS WITH TYPE 2 DIABETES MELLITUS: A DANISH POPULATION-BASED COHORT STUDY

2021 ◽  
Vol 160 (6) ◽  
pp. S-30
Author(s):  
Frederikke Sch⊘nfeldt Troelsen ◽  
Henrik Toft S⊘rensen ◽  
Lars Pedersen ◽  
Rune Erichsen
Keyword(s):  
Diabetes Mellitus ◽  
Colorectal Cancer ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Cohort Study ◽  
Population Based ◽  
Danish Population
Sign in / Sign up

Export Citation Format

Share Document