ARTIFICIAL NEURAL NETWORK BASED EARLY DIAGNOSIS OF DIABETES MELLITUS

• Main Authors: Kumar, T. C. H. Anil, Ohmshankar, S, Ranjani, R, Srilalitha, Sapram, Haque, M. Akiful, S., Prathik, Sharma, Deepankar, Balachander, Bhuvaneswari, Jaiswal, Sushma, D., Maheswari
• Format: Patent
• Language: English
• Published: 03.06.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DIAGNOSIS; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; MEDICAL OR VETERINARY SCIENCE; PHYSICS; SURGERY

ARTIFICIAL NEURAL NETWORK BASED EARLY DIAGNOSIS OF DIABETES MELLITUS Diabetes Mellitus is a type of common chronic disease, which if can be treated at an early stage can provide improved results. Disease prediction can be done at an early stage by using data mining techniques. In this invention, significant attributes are utilized for prediction of diabetes with characterization of different attributes with the relationship between them. The selection of significant attributes is based on various tools required for the process of clustering, prediction and the associated data mining rule for diabetes. Principal Component Analysis method used for selection of significant attributes. Apriori method is used for extraction of blood glucose level and body mass index of the patient as these two parameters are associated strongly with diabetes. Prediction of diabetes is done by implementing the Artificial Neural Network (ANN) method. Best accuracy is achieved by the proposed Artificial Neural Network (ANN) method for early detection of diabetes for assisting medical officers in making decisions related to treatment. cOmpret oft" Figure 1. Framework of Proposed ANN based Early Diabetes Detection Wn( 9Wk Wk p Wim X100oo X2 Output HL1 HL2 HL3 HL4 Hidden layers Figure 2. Layers involved in ANN Algorithmfor Diabetes Detection