Artificial Neural Network-Based Pelvic Inflammatory Disease Diagnosis System

Abstract

Pelvic Inflammatory Disease (PID) is a reproductive health infective disease of feminine genital tract and high among minority adolescent girls and young adult women. Clinical manifestation of PID differs among patients and decision of medical experts are based on clinician experience instead of hidden data in the knowledge database. The diagnosis of PID based on heuristic lead to errors where ectopic pregnancy could be mistaken for PID. This paper presents an Artificial Neural Network model to diagnose pelvic inflammatory diseases based on a set of clinical data. The ANN model was trained with 259 clinical data as input to the neural network. The system can predict the presence or absence of PID based on the available symptoms. The system recorded an accuracy of 96.1% based on the confusion matrix. The obtain result is promising, an indication that the system can be effective in diagnosis of PID cases.