• Dr.Sanju S Anand
• Dhanya Damodar Naik
• Sakita Mahabaleshwar Gouda
• Sannidhi Vanakudari
• Harshita Annappa Naik

Artificial Intelligence (AI) and Natural Language Processing (NLP) have become useful technologies for developing intelligent healthcare-support applications. This paper presents the development of an AI-based Medical Symptom Checker that predicts a possible disease from a user's natural-language description of symptoms. The proposed system uses a Symptom2Disease dataset containing 1,200 symptom descriptions belonging to 24 disease categories. Data preprocessing is performed to remove missing, empty, and duplicate records. The cleaned data are converted into numerical representations using Term Frequency-Inverse Document Frequency (TF-IDF), and a Logistic Regression classifier is trained for multi-class disease classification. After preprocessing, 1,155 records were available for model development. The data were divided into training and testing sets, with 231 samples used for final testing. The trained model correctly classified 215 of the 231 test samples, achieving an accuracy of 93.07%. The model obtained a macro-average precision of 0.94, recall of 0.93, and F1-score of 0.93. A confusion matrix was used to analyze class-wise performance and misclassifications. Finally, the trained model was exported in ONNX format and integrated into a C# Windows Forms desktop application using ONNX Runtime. The developed application accepts natural-language symptom descriptions and produces a preliminary disease prediction. The system is intended for educational and preliminary decision-support purposes and is not a replacement for professional medical diagnosis.

Artificial Intelligence, Natural Language Processing, Machine Learning, Medical Symptom Checker, TF-IDF, Logistic Regression, ONNX, C#, Disease Classification.

"Development and Deployment of an AI-Based Medical Symptom Checker Using Natural Language Processing and Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 9, page no.b279-b289, September-2026, Available :http://www.jetir.org/papers/JETIR2609133.pdf

"Development and Deployment of an AI-Based Medical Symptom Checker Using Natural Language Processing and Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 9, page no. ppb279-b289, September-2026, Available at : http://www.jetir.org/papers/JETIR2609133.pdf