Modelling the prevalence of diabetes mellitus risk factors based on artificial neural network and multiple regression

Gholipour, Kamal; Asghari‐Jafarabadi, Mohammad; Iezadi, Shabnam; Jannati, Ali; Keshavarz, Sina

doi:10.26719/emhj.18.012

Cited by 19 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After four prediction models were established, we compared the risk assessment models' performance through accuracy, sensitivity, specificity, and receiver operating characteristic curve (ROC) to select the optimal prediction model. ROC curve is a visualized optimal model, which shows the performance of binary classifiers by considering the sensitivity, specificity, and accuracy of the model [16,17]. Unless specified, we used the significance level of 0.05 for all analyses.…”

Section: Discussionmentioning

confidence: 99%

Prediction model for the risk of osteoporosis incorporating factors of disease history and living habits in physical examination of population in Chongqing, Southwest China: based on artificial neural network

Wang

Sun

et al. 2021

BMC Public Health

View full text Add to dashboard Cite

Background Osteoporosis is a gradually recognized health problem with risks related to disease history and living habits. This study aims to establish the optimal prediction model by comparing the performance of four prediction models that incorporated disease history and living habits in predicting the risk of Osteoporosis in Chongqing adults. Methods We conduct a cross-sectional survey with convenience sampling in this study. We use a questionnaire From January 2019 to December 2019 to collect data on disease history and adults’ living habits who got dual-energy X-ray absorptiometry. We established the prediction models of osteoporosis in three steps. Firstly, we performed feature selection to identify risk factors related to osteoporosis. Secondly, the qualified participants were randomly divided into a training set and a test set in the ratio of 7:3. Then the prediction models of osteoporosis were established based on Artificial Neural Network (ANN), Deep Belief Network (DBN), Support Vector Machine (SVM) and combinatorial heuristic method (Genetic Algorithm - Decision Tree (GA-DT)). Finally, we compared the prediction models’ performance through accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC) to select the optimal prediction model. Results The univariate logistic model found that taking calcium tablet (odds ratio [OR] = 0.431), SBP (OR = 1.010), fracture (OR = 1.796), coronary heart disease (OR = 4.299), drinking alcohol (OR = 1.835), physical exercise (OR = 0.747) and other factors were related to the risk of osteoporosis. The AUCs of the training set and test set of the prediction models based on ANN, DBN, SVM and GA-DT were 0.901, 0.762; 0.622, 0.618; 0.698, 0.627; 0.744, 0.724, respectively. After evaluating four prediction models’ performance, we selected a three-layer back propagation neural network (BPNN) with 18, 4, and 1 neuron in the input layer, hidden and output layers respectively, as the optimal prediction model. When the probability was greater than 0.330, osteoporosis would occur. Conclusions Compared with DBN, SVM and GA-DT, the established ANN model had the best prediction ability and can be used to predict the risk of osteoporosis in physical examination of the Chongqing population. The model needs to be further improved through large sample research.

show abstract

Section: Discussionmentioning

confidence: 99%

Prediction model for the risk of osteoporosis incorporating factors of disease history and living habits in physical examination of population in Chongqing, Southwest China: based on artificial neural network

Wang

Sun

et al. 2021

BMC Public Health

View full text Add to dashboard Cite

show abstract

“…Extracted data from STEPs and NASBOD will be used to predict the MI mortality rate using ANN (25)(26)(27)(28)(29)(30). The modeling will be repeated 100 times to enhance the accuracy of the ANN model and eventually, the mean value of repeated results will be used to predict the future.…”

Section: Discussionmentioning

confidence: 99%

A A Scenario-based Modelling Study of the Prevention of Myocardial Infarction in Iran : A Scenario-based and Modeling Study on the Prevention of Heart Attack in Iran

Alizadeh

Gholipour

Dehnavieh

et al. 2020

ircmj

View full text Add to dashboard Cite

Background and Objectives: Globally, cardiovascular disease (CVD) is the number one cause of mortality. In this regard, this study aimed to provide policies for the management of CVD by focusing on the reduction of myocardial infarction (MI) mortality rate in Iran. Materials and Methods: The sequential mixed methods design will be employed to foresight the prevalence of MI in Iran in the next 10 years. This study consists of five phases and in the first phase, the risk factors of cardiovascular disease will be investigated using a systematic review. In the second phase, the uncertainty and impact of those factors will be demonstrated by the experts. Moreover, the impact/uncertainty grid will be used to identify the drivers that are less important and critical uncertainties. In the third phase, the cross-impact matrix will be developed by Scenario wizard, and the scenario logic and the scenarios will be developed. Once the scenario logic is established, details can be added to the scenarios. The next phase consists of statistical estimations of the rate of mortality due to heart attack using artificial neural networks. Finally, the policies will be developed based on the opinions of the panel of experts. The initial results will be published in mid-2020. Results: This future study will develop policies to prevent from MI with scenario-based and modeling approaches. The findings can be useful for healthcare professionals and it can improve our understanding of the future of MI to enhance the management of MI patients. Conclusion: The obtained policies will help policymakers to make evidence-based decisions, re-design structures, and processes of healthcare interventions, and also plan to decrease MI mortality rate.

show abstract

“…Different factors should be taken into consideration when dealing with patients with DM who are at higher risk of developing diabetes complications. A recent study in the Islamic Republic of Iran has emphasised the role of positive family history of T2DM, controlled hypertension and residence area and their relation with DM and its control [35].…”

Section: Discussionmentioning

confidence: 99%

Attitudes and perceptions towards hypoglycaemia in patients with diabetes mellitus: A multinational cross-sectional study

Naser

Wong

Whittlesea³

et al. 2019

PLoS ONE

View full text Add to dashboard Cite

BackgroundPreventing hypoglycaemia is an essential component of diabetes self-management that is affected by patients’ attitudes and perceptions. This study aimed to explore the hypoglycaemia problem-solving ability of patients who have diabetes mellitus and factors that determine their attitudes and perceptions towards their previous events.MethodologyA cross-sectional study was conducted between October 2017 and May 2018 in three Arab countries (Jordan, Saudi Arabia and Kuwait) in patients with diabetes mellitus, who were prescribed antidiabetic therapy and had experienced hypoglycaemic events in the past six months. The Hypoglycaemia Problem-Solving Scale was used in this study. This scale contains two subscales, problem orientation (six questions) and problem-solving skills (eighteen questions), using a five-point Likert scale (range 0–4). Multiple linear regression analysis was used to identify predictors of hypoglycaemia problem-solving abilities.ResultsA total of 895 patients participated in this study from the three countries (300 in Jordan, 302 in Saudi Arabia, and 293 in Kuwait). The average age of the patients was 53.5 years (standard deviation = 13.7) and 52.4% (n = 469) were males. Patients had moderate overall problem-solving ability with a median score of 63.00 (interquartile range = 13.00). Patients’ problem-solving skills score (68.1%) was better than their problem-orientation skills score (58.3%). The highest sub-scale scores were for detection control, setting problem-solving goals, and evaluating strategies, 75.0%. The lowest sub-scale score was for problem-solving perception and immediate management, 50.0%. Older age, being educated, being married, having T2DM, prescribed insulin therapy, and not having been admitted to hospital for hypoglycaemia were important predictors of patients’ problem-solving ability (p < 0.05).ConclusionsHealthcare professionals are advised to provide more education to patients on how to self-manage hypoglycaemic events. Specifically, they should focus on the overall problem-solving perception of hypoglycaemia and its immediate management.

show abstract

Modelling the prevalence of diabetes mellitus risk factors based on artificial neural network and multiple regression

Cited by 19 publications

References 18 publications

Prediction model for the risk of osteoporosis incorporating factors of disease history and living habits in physical examination of population in Chongqing, Southwest China: based on artificial neural network

Prediction model for the risk of osteoporosis incorporating factors of disease history and living habits in physical examination of population in Chongqing, Southwest China: based on artificial neural network

A A Scenario-based Modelling Study of the Prevention of Myocardial Infarction in Iran : A Scenario-based and Modeling Study on the Prevention of Heart Attack in Iran

Attitudes and perceptions towards hypoglycaemia in patients with diabetes mellitus: A multinational cross-sectional study

Contact Info

Product

Resources

About