Decision Support System For Diabetes Diagnosis Using Simple Additive Weighting Method

Diabetes is a chronic metabolic condition marked by elevated blood glucose levels, necessitating early identification to avert long-term consequences, including cardiovascular diseases and organ impairment. The main obstacles in conventional diagnosis include time-consuming processes and limited medical experts, particularly in remote areas. This research aims to develop a web-based decision support system (DSS) to assist in the early diagnosis of diabetes by applying the Simple Additive Weighting (SAW) method. The developed system analyzes eight patient medical criteria: pregnancy count, level of sugar in the bloodstream, lower arterial pressure value, measurement of the triceps subcutaneous layer, amount of insulin present in the serum, and the body weight-to-height ratio index, genetic predisposition to diabetes, and age of the individual. Implementation and validation results show that the system successfully classified diabetes risk into three categories (low, medium, high) with 100% accuracy based on the comparison between system calculations and manual calculations. The system also features risk visualization based on a progress bar and automatic notifications triggered after medical personnel confirmation. In conclusion, this SAW-based DSS proves effective as an accurate and efficient screening tool for medical personnel in conducting early diabetes diagnosis, while potentially reducing healthcare service disparities in remote areas.