<![CDATA[Stunting is still a nutritional problem that exists in Indonesia and it needs immediate intervention in Jepara Regency. At the primary healthcare level, Batealit Public Health Center uses manual anthropometric recording for toddlers' growth assessment. This method can be prone to human recording errors and operational delays which hinder prompt clinical decision-making. To improve this condition, this study develops a web-based system for predicting stunting based on the K-Nearest Neighbor (KNN) algorithm. The research method was applied research with system development using the Waterfall model by processing main variables such as age, weight, and height. We tested the algorithm intensively by trying different neighbor values (k) to obtain the maximum value for accuracy, precision, and recall. From experiments, the KNN algorithm is best at k=3 with a 95.23% accuracy rate; this configuration is better compared to larger k values since they increase misclassification rates on normal and stunted categories. By porting this logic into a web interface, detection moves from being a manual task to an automated one occurring in real-time thus application becomes an essential part of decision support enabling health workers to bypass administrative delays and find stunting much faster more accurately within Batealit service area.]]>
Copyrights © 2025
