Diabetes Mellitus Forecast Using Artificial Neural Network (ANN)

Jaafar, Salmah; Ali, Darmawaty Mohd

doi:10.1109/asense.2005.1564523

Cited by 24 publications

(7 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, since it applies the steepest descent method to update the weights, it suffers from a slow convergence rate, and often yields suboptimal solutions [30,31]. Jaafar et al used the back propagation neural network algorithm for diagnosing diabetes [32]. The inputs to the system were glucose tolerance test, diastolic blood pressure, triceps skin fold thickness, serum insulin, body mass index, diabetes pedigree function, number of times pregnant, and age.…”

Section: Back-propagation Neural Networkmentioning

confidence: 99%

Computational Intelligence in Early Diabetes Diagnosis: A Review

Shankaracharya¹,

Odedra²,

Samanta³

et al. 2010

Rev Diabet Stud

View full text Add to dashboard Cite

The development of an effective diabetes diagnosis system by taking advantage of computational intelligence is regarded as a primary goal nowadays. Many approaches based on artificial network and machine learning algorithms have been developed and tested against diabetes datasets, which were mostly related to individuals of Pima Indian origin. Yet, despite high accuracies of up to 99% in predicting the correct diabetes diagnosis, none of these approaches have reached clinical application so far. One reason for this failure may be that diabetologists or clinical investigators are sparsely informed about, or trained in the use of, computational diagnosis tools. Therefore, this article aims at sketching out an outline of the wide range of options, recent developments, and potentials in machine learning algorithms as diabetes diagnosis tools. One focus is on supervised and unsupervised methods, which have made significant impacts in the detection and diagnosis of diabetes at primary and advanced stages. Particular attention is paid to algorithms that show promise in improving diabetes diagnosis. A key advance has been the development of a more in-depth understanding and theoretical analysis of critical issues related to algorithmic construction and learning theory. These include trade-offs for maximizing generalization performance, use of physically realistic constraints, and incorporation of prior knowledge and uncertainty. The review presents and explains the most accurate algorithms, and discusses advantages and pitfalls of methodologies. This should provide a good resource for researchers from all backgrounds interested in computational intelligence-based diabetes diagnosis methods, and allows them to extend their knowledge into this kind of research.

show abstract

Section: Back-propagation Neural Networkmentioning

confidence: 99%

Computational Intelligence in Early Diabetes Diagnosis: A Review

Shankaracharya¹,

Odedra²,

Samanta³

et al. 2010

Rev Diabet Stud

View full text Add to dashboard Cite

show abstract

“…Numerous techniques are being used for Diabetes Prediction [13]. An Adaptive Neuro Fuzzy Inference System (ANFIS) is being used for the diagnosis of Diabetes and prediction of Cancer [1].…”

Section: Related Workmentioning

confidence: 99%

Performance analysis of training algorithms of multilayer perceptrons in diabetes prediction

Saji

Balachandran

2015

2015 International Conference on Advances in Computer Engineering and Applications

View full text Add to dashboard Cite

Artificial Intelligence plays a vital role in developing machines or software that can create intelligence. Artificial Neural Networks is a field of neuroscience which contributes tremendous developments in Artificial Intelligence. This paper focuses on the study of performance of various training algorithms of Multilayer Perceptrons in Diabetes Prediction. In this study, we have used Pima Indian Diabetes data set from UCI Machine Learning Repository as input dataset. The system is implemented in MatlabR2013. The Pima Indian Diabetes dataset consists of about 768 instances. The input data is the patient history and the target output is the prediction result as tested positive or tested negative. From the performance analysis, it was observed that out of all the training algorithms, Levenberg-Marquardt Algorithm has given optimal training results.

show abstract

“…There are a variety of uses of CDSS in primary care such as depression, hypertension and medication reviews [ 14 – 16 ]. In addition, various rule based and artificial intelligence based decision support systems have been developed for diabetes diagnosis [ 17 , 18 ].…”

Section: Introductionmentioning

confidence: 99%

A mobile and web-based clinical decision support and monitoring system for diabetes mellitus patients in primary care: a study protocol for a randomized controlled trial

Mevsim

Kut

Yürek

et al. 2017

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

BackgroundPhysicians’ guideline use rates for diagnosis, treatment and monitoring of diabetes mellitus (DM) is very low. Time constraints, patient overpopulation, and complex guidelines require alternative solutions for real time patient monitoring. Rapidly evolving e-health technology combined with clinical decision support and monitoring systems (CDSMS) provides an effective solution to these problems. The purpose of the study is to develop a user-friendly, comprehensive, fully integrated web and mobile-based Clinical Decision Support and Monitoring System (CDSMS) for the screening, diagnosis, treatment, and monitoring of DM diseases which is used by physicians and patients in primary care and to determine the effectiveness of the system.MethodsThe CDSMS will be based on evidence-based guidelines for DM disease. A web and mobile-based application will be developed in which the physician will remotely monitor patient data through mobile applications in real time.The developed CDSMS will be tested in two stages. In the first stage, the usability, understandability, and adequacy of the application will be determined. Five primary care physicians will use the developed application for at least 16 DM patients. Necessary improvements will be made according to physician feedback. In the second phase, a parallel, single-blind, randomized controlled trial will be implemented. DM diagnosed patients will be recruited for the CDSMS trial by their primary care physicians. Ten physicians and their 439 patients will be involved in the study. Eligible participants will be assigned to intervention and control groups with simple randomization. The significance level will be accepted as p < 0.05. In the intervention group, the system will make recommendations on patient monitoring, diagnosis, and treatment. These recommendations will be implemented at the physician’s discretion. Patients in the control group will be treated by physicians according to current DM treatment standards. Patients in both groups will be monitored for 6 months. Patient data will be compared between 0th and 6th month of the study. . Clinical and laboratory outcomes will be assessed in person while others will be self-assessed online.DiscussionThe developed system will be the first of its kind to utilize evidence based guidelines to provide health services to DM patients.Trial registrationClinicalTrials.gov NCT02917226. 28 September 2016.

show abstract

Diabetes Mellitus Forecast Using Artificial Neural Network (ANN)

Cited by 24 publications

References 1 publication

Computational Intelligence in Early Diabetes Diagnosis: A Review

Computational Intelligence in Early Diabetes Diagnosis: A Review

Performance analysis of training algorithms of multilayer perceptrons in diabetes prediction

A mobile and web-based clinical decision support and monitoring system for diabetes mellitus patients in primary care: a study protocol for a randomized controlled trial

Contact Info

Product

Resources

About