A Natural Language Processing-Based Turkish Diagnosis Recommendation System

Authors : Servet BADEM, Özlem ÖZCAN KILIÇSAYMAZ

Pages : 8-18

Doi:10.54047/bibted.1227017

View : 215 | Download : 128

Publication Date : 2023-08-09

Article Type : Other Papers

Abstract :MD-Advisor is the abbreviation of “medical doctor – advisor” which is an artificial intelligence-based recommendation system in healthcare. Moreover, the health-based recommender system is a decision-making tool that makes recommendations for appropriate healthcare information to patients and clinicians. MD-Advisor project was developed in order to speed up the procedures that doctors follow when diagnosing patients and to present all possible conditions to the doctor in a short time. With this project, the processes of diagnosing the patient and then recommending the examination are completed very quickly. Thus, the patient is directly transferred to the treatment phase. Based on the data obtained from patient complaints which indicates the current health status of the patient; data preprocessing, labeling and deep learning modeling techniques are used. The diagnostic codes used as labels for the diagnosis recommendation were obtained as output from the Recurrent Neural Networks model. As a result of the study, the diagnosis proposal for the patient\`s complaints was successfully predicted with the applied recurrent neural networks insert ignore into journalissuearticles values(RNN); model approach.
Keywords : AI based Recommendation System, Machine Learning, Deep Learning, Turkish Natural Language Processing, LSTM Long Short Term Memory, Recurrent Neural Network RNN, Hea