ADVANCED DIABETES PREDICTION SYSTEM WITH MULTILINGUAL AND VOICE-ENABLED INTERFACE

The Advanced Diabetes Prediction System with Multilingual and Voice-Enabled Interface was successfully designed and implemented to provide an intelligent, accessible, and user-friendly solution for early diabetes risk assessment. The system combines machine learning techniques with speech recognition and multilingual communication technologies to enhance healthcare accessibility and improve user experience. The developed application enables users to enter medical information through both manual and voice-based methods, making the system convenient for individuals with limited technical knowledge, elderly users, and visually challenged people. By supporting multiple languages such as English, Hindi, and Telugu, the system eliminates language barriers and allows users to interact with the application in their preferred language. The machine learning model effectively analyzes important health parameters, including glucose level, insulin level, BMI, age, and diabetes pedigree function, to predict the likelihood of diabetes. The prediction results are presented through an interactive dashboard that displays risk scores, confidence levels, and clinical interpretations in a clear and understandable format. The integration of voice input and multilingual reporting further improves accessibility and usability. Experimental results demonstrate that the system provides accurate diabetes risk predictions while maintaining efficient performance and seamless user interaction. The application successfully bridges the gap between advanced healthcare technologies and everyday users by offering an inclusive platform for preliminary diabetes screening and awareness. Overall, the project achieves its objective of developing a smart healthcare application that leverages Artificial Intelligence, Machine Learning, Speech Processing, and Multilingual Computing to support early diabetes detection. The proposed system can serve as a valuable tool for healthcare awareness and preventive care.

·        Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, 2016. ·        Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, O'Reilly Media, 2022. ·        Scikit-Learn Documentation ·        Python Documentation ·        World Health Organization (WHO) Diabetes Fact Sheets ·        American Diabetes Association (ADA) Standards of Care ·        Trevor Hastie, Robert Tibshirani, and Jerome Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer, 2017. ·        Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006. ·        NumPy Documentation ·        Pandas Documentation ·        SpeechRecognition Library Documentation ·        Google Text-to-Speech (gTTS) Documentation ·        Tom M. Mitchell, Machine Learning, McGraw-Hill Education, 1997. ·        Ethem Alpaydin, Introduction to Machine Learning, MIT Press, 2021. ·        Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach, Pearson Education, 2021.