Gynaecological Disease Diagnosis Expert System (GDDES) Based on Machine Learning Algorithm and Natural Language Processing

• Published in: IEEE access Vol. 12; pp. 84204 - 84215
• Main Authors: de, Sumana, Goswami, Paromita, Faujdar, Neetu, Singh, Ghanshyam
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Classifiers; Diagnosis; Disease diagnosis; Diseases; Expert systems; Graphical user interface; Graphical user interfaces; gynaecological disease diagnosis expert system (GDDES); Gynecology; Knowledge engineering; Language; Machine learning; Medical diagnosis; Natural language processing; Predictive models; Recording; Signs and symptoms; support vector classifier; Support vector machine classification; Tongue
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2024.3406162

In this paper, the Gynaecological Disease Diagnosis Expert System (GDDES) is a Graphical User Interface, developed with the Support Vector Classifier (Machine Learning Algorithm) and Natural Language Processing. It is language-independent, allowing women from any state in India to use the system in their own native tongue and have their disorders diagnosed in that language. The diagnosis process is divided into two steps: At first, the user selects their regional language and the system asks some queries in their selected language and submits the reply for each query, then the system uses the Support Vector Classifier (SVC) Model to predict the disease name; and secondly, the user is prompted to record their symptoms in their native tongue and GDDES uses Natural Language Processing to calculate cosine similarities and play the most similar voice recording of disease diagnosis, and displays the sentences of the recording in the user's native language. The system with the SVC Model provides 93% accuracy and precision and 92% recall and f1 score.