Medicine Information and Advice System Using NLP and Decision Tree Algorithm

Abstract

The \"Medicine Information and Advice System\" is an application based on machine learning that aims to give reliable medicine information and individualized healthcare advice, enabling users to make better, informed choices more securely. It can handle both symptom-oriented and medicine-oriented questions through a simple interface, suiting all types of users. Using artificial intelligence, the system performs operations on user input either symptoms or medicine names to provide crucial health information. For medical questions, it provides comprehensive information such as, composition , product information, possible side effects, therapeutic class, uses. For symptom-based search, predictive modeling suggests possible diseases and recommends suitable medicines, diets, exercises, and precautions required. The system features voice command for hands-free use and is backed by a performance-tuned backend for rapid, reliable data access with ongoing learning from user behavior to enhance precision. Coupled with a simple, intuitive frontend and a large, robust medical database, the system improves health decision-making for patients and clinicians alike, enabling better, safer, and more tailored health outcomes.

Introduction

The Medicine Information and Advice System is an AI- and Machine Learning-based healthcare application designed to provide accurate medicine information and personalized medical advice. It enables users to search for medicines or describe their symptoms using text or voice input, and then delivers detailed medicine information, disease predictions, and healthcare recommendations through a simple, user-friendly interface.

The system provides comprehensive medicine details, including composition, dosage, side effects, manufacturer, price, and alternative medicines. For symptom-based queries, it predicts likely diseases using a Decision Tree classification algorithm and recommends suitable medications, dietary plans, exercises, and preventive precautions. Natural Language Processing (NLP) allows the application to understand natural language queries, recognize variations in medical terms, and improve search accuracy. Voice command functionality further enhances accessibility, especially for elderly and visually impaired users.

Existing medicine information systems are generally limited to displaying basic drug information and rely on manual keyword searches. They lack intelligent symptom analysis, personalized recommendations, voice interaction, alternative medicine suggestions, and integrated advice on diet, exercise, and preventive care. They also face challenges related to outdated databases, poor scalability, limited NLP capabilities, data privacy, and the inability to continuously improve recommendations.

The proposed system addresses these limitations by combining Machine Learning, NLP, and a comprehensive medicine database. Data preprocessing includes handling missing values, removing duplicates, text normalization, tokenization, TF-IDF vectorization, and categorical encoding. The dataset is divided into training and testing sets (80:20), and the Decision Tree model is trained to predict diseases and retrieve medicine information. Performance is evaluated using Accuracy, Precision, Recall, F1-score, and confusion matrix analysis, while user feedback supports continuous model improvement.

The methodology integrates medicine and symptom datasets, machine learning, NLP, and a recommendation engine into a unified platform. Users can search by medicine name or symptoms, and the system quickly generates detailed medicine information, disease predictions, and personalized healthcare guidance. By combining AI, machine learning, NLP, and voice interaction, the Medicine Information and Advice System provides a fast, accurate, secure, and intelligent healthcare assistant that supports informed medical decision-making while reducing medication errors and improving access to reliable medical information.

Conclusion

The AI-Powered Student Placement Prediction System Using Machine Learning is an intelligent web-based application developed to simplify and improve the student placement process. The system uses the Logistic Regression Machine Learning algorithm to analyze important student attributes such as CGPA, academic percentages, aptitude score, communication skills, technical skills, certifications, internship experience, and project details to predict placement opportunities accurately. By automating the prediction process, the system reduces manual effort, minimizes human errors, and supports data-driven decision-making for educational institutions. The application provides a secure and user-friendly platform where students can register, manage their profiles, generate placement predictions, and download detailed PDF reports. In addition to predicting placement status, the system also provides placement probability, confidence score, and personalized recommendations that help students identify areas for improvement and enhance their employability. These recommendations encourage students to strengthen their technical knowledge, communication skills, and practical experience before participating in campus recruitment. The integration of Python, Flask, Scikit-Learn, SQLite, HTML, CSS, and Bootstrap ensures efficient system performance, secure data management, and an interactive user interface. The proposed system can assist placement officers in monitoring student performance, identifying students who require additional training, and improving overall placement management. Overall, the project demonstrates the practical application of Artificial Intelligence and Machine Learning in the education sector by providing an accurate, reliable, and scalable solution for predicting student placement outcomes and supporting better career planning for students.

References

[1] Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. https://www.deeplearningbook.org [2] Mitchell, T. M. (1997). Machine Learning. McGraw-Hill Education. https://www.cs.cmu.edu/~tom/mlbook.html [3] Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer. https://link.springer.com/book/10.1007/978-0-387-45528-0 [4] Pedregosa, F., et al. (2011). Scikit-Learn: Machine Learning in Python. Journal of Machine Learning Research. https://scikit-learn.org [5] Python Software Foundation. (2024). Python Documentation. https://docs.python.org/3/ [6] Flask Development Team. (2024). Flask Documentation. https://flask.palletsprojects.com [7] SQLite Consortium. (2024). SQLite Documentation. https://www.sqlite.org/docs.html [8] McKinney, W. (2022). Pandas Documentation. https://pandas.pydata.org/docs/ [9] Harris, C. R., et al. (2020). NumPy Documentation. https://numpy.org/doc/ [10] Bootstrap Team. (2024). Bootstrap Documentation. https://getbootstrap.com/docs/ [11] Chollet, F. (2021). Deep Learning with Python (2nd ed.). Manning Publications. https://www.manning.com/books/deep-learning-with-python-second-edition [12] Géron, A. (2022). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (3rd ed.). O\'Reilly Media. https://www.oreilly.com/library/view/hands-on-machine-learning/ [13] Brownlee, J. (2019). Machine Learning Algorithms for Classification. Machine Learning Mastery. https://machinelearningmastery.com [14] IEEE Xplore Digital Library. (2024). Research Papers on Student Placement Prediction Using Machine Learning. https://ieeexplore.ieee.org [15] Springer Nature. (2024). Research Publications on Artificial Intelligence and Machine Learning. https://link.springer.com [16] Elsevier. (2024). ScienceDirect: Machine Learning and Educational Data Mining Research. https://www.sciencedirect.com

Copyright

Copyright © 2026 Bondada Sravani, G Manoj Kumar . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.