AI-Based Pharyngitis Detection Expert System Using the Certainty Factor Method

Abstract

Pharyngitis, an inflammation of the pharynx commonly known as a sore throat, is one of the most frequent complaints in Indonesian primary health care, yet the uneven distribution of physicians, especially in remote regions, often delays timely triage. This study develops an Android-based expert system that provides an early-screening indication of two types of pharyngitis, acute and chronic, using the Certainty Factor (CF) method. Rather than treating the disease application itself as the main contribution, the novelty lies in the validation framework: a dual-source certainty model that keeps expert-elicited rule weights separate from user-reported symptom confidence, and a class-level accuracy evaluation, including a confusion matrix, sensitivity, specificity, precision, recall, and F1-score, that is rarely reported alongside comparable Certainty Factor systems. Knowledge was acquired from a general practitioner and clinical references and encoded as thirteen symptoms, two disease classes, and a rule base of IF-THEN rules with expert certainty weights. User certainty is captured through six linguistic terms and combined with the expert CF values using the single-evidence formula CF[H,E] = CFuser x CFexpert and the parallel combination formula. The application was built with Android Studio and a local SQLite knowledge base so that it operates entirely offline. A worked example involving five symptoms of acute pharyngitis produced a combined certainty of 0.9890, or 98.90%, illustrating a high-confidence screening output. The system's screening conclusions were compared with a general practitioner's diagnosis on 30 patient cases, agreeing in 28 cases for an overall agreement accuracy of 93.33% (class-level sensitivity of 94.12% for acute and 92.31% for chronic pharyngitis); because this figure reflects agreement with a single practitioner rather than a laboratory-confirmed reference standard, it is reported as an agreement accuracy rather than a universal clinical accuracy. Black-box testing confirmed that all functional features operated as intended. The results indicate that the Certainty Factor method can quantify screening uncertainty effectively and that the resulting offline mobile application can serve as an accessible early-screening aid for the public and a decision-support tool for paramedics, complementing rather than replacing a professional medical examination.

GS Cited Analysis