An Intelligent Appointment Scheduling System for Healthcare using Android and Machine Learning

Abstract

The project in many cases “ An Intelligent Appointment Scheduling System for Healthcare using Android and Machine Learning ” nowadays an integrated Mobile healthcare solution that combine intelligent disease anticipation with automated assignment scheduling. This finding appears to suggests, the organization is plan to assistance patient in place potential wellness conditions at an early level while simultaneously enable efficient consultation direction. It is Worth note that, the application arguably allows user to enter symptoms through an humanoid port. In light of this, a machine learning classification model process the symptom and predicts the most probable disease. This finding suggests, based on the prognosticate disease and associated symptom patterns, the system provides medicine recommendations include dosage and duration item. Additionally, it suggests relevant lab tests with priority level and estimated requirement to reinforcement exact diagnosis. The system potentially further recommends specialist doctors base on the predicted disease and the user ’ s geographic locating. Building upon this, patient can directly book appointment by take usable time slots, thereby trim manual intervention and waiting time. Edifice upon this, the integration of disease prediction, medicine proffer, lab test recommendation,. Location-based doctor filter into a single humanoid platform raise healthcare accessibility, better decision-making, and supports digital healthcare translation. Building upon this, this finding potentially suggest, the organization is designed with scalability, security, Modular architecture to ensure reliableness and hereafter enlargement.

Introduction

The text discusses the growing strain on global healthcare systems due to aging populations, limited medical professionals, and delayed access to care. Many individuals experience symptoms but postpone medical consultation ???? uncertainty, time constraints, or lack of specialist access, which can worsen health outcomes. Early guidance and timely intervention are therefore crucial for improving wellness and slowing disease progression.

To address this, the work introduces MediAssist AI, an integrated healthcare assistance system that goes beyond simple disease prediction. Unlike existing tools that only forecast diseases, MediAssist AI combines multiple functions into one platform, including:

• Symptom-based disease prediction
• Severity and urgency assessment
• Medicine recommendations
• Lab test suggestions
• Specialist recommendation and appointment booking

The system processes user-input symptoms using text vectorization (TF-IDF) and machine learning models (notably Random Forest) to predict possible diseases. It then generates structured recommendations and enables users to book appointments with appropriate doctors. The platform is built on a three-tier architecture (presentation, application, and data layers) to ensure scalability, modularity, and security.

The literature review highlights the evolution of healthcare AI—from rule-based systems to machine learning and deep learning approaches. While modern models improve diagnostic accuracy, challenges remain in handling complex cases, managing unstructured text data, ensuring privacy, and integrating multiple healthcare services into a unified system.

MediAssist AI addresses these gaps by combining predictive analytics with healthcare workflow automation in a single platform. Its goal is to improve healthcare accessibility, reduce consultation delays, and promote early health awareness, while ensuring that final diagnoses remain under professional medical supervision.

Conclusion

This paper presented MediAssist AI, an integrated AI-driven healthcare assistance platform that combines symptom-based disease prediction, severity assessment, medicine recommendation, specialist ranking, and appointment scheduling within a unified framework. The use of TF-IDF feature extraction and Random Forest classification achieved approximately 92% prediction accuracy while maintaining low computational overhead and rapid inference time. The modular three-tier architecture ensures: 1) Scalability 2) Maintainability 3) Secure data handling 4) Multi-role access control By bridging intelligent disease prediction with real-world specialist consultation, MediAssist AI enhances healthcare accessibility and supports early medical intervention.

References

[1] Al-Nafjan, A. Aljuhani, A. Alshebel, A. Alharbi, and A. Alshehri, “Artificial Intelligence in Predictive Healthcare: A Systematic Review,” J. Clin. Med., vol. 14, no. 19, p. 6752, Sep. 2025, doi:10.3390/jcm14196752. [2] J. Wei, H. Yan, X. Shao, L. Zhao, L. Han, P. Yan, and S. Wang, “A machine learning-based hybrid recommender framework for smart medical systems,” PeerJ Comput. Sci., vol. 10, p. e1880, Feb. 2024, doi:10.7717/peerj-cs.1880. [3] N. Nasution, M. A. Hasan, and F. B. Nasution, “Predicting Heart Disease Using Machine Learning: An Evaluation of Logistic Regression, Random Forest, SVM, and KNN Models on the UCI Heart Disease Dataset,” IT J. Res. Dev., vol. 9, no. 2, pp. 140–150, 2025, doi:10.25299/itjrd.2025.17941. [4] R. Aldora Rayadhani and M. Rahardi, “Comparative Analysis of Random Forest, SVM, and Naive Bayes for Cardiovascular Disease Prediction,” J. Appl. Informatics Comput., vol. 9, no. 6, 2025, doi:10.30871/jaic.v9i6.11451. [5] R. Islam, S. Tanweer, M. T. Nafis, I. Hussain, and M. O. Ahmad, “Enhancing Accuracy and Analyzing Performance of Machine Learning Models Using Random Forest for Heart Disease Prediction,” J. Electr. Syst., vol. 20, no. 3, 2024. [6] H. Chaurasia and A. Pal, “Early Prediction of Heart Disease Using Machine Learning Techniques,” IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), Dec. 2017, pp. 88–92, doi:10.1109/ICCIC.2017.8524361. [7] J. Jiang, G. Tang, and Y. Xiao, “A Diagnosis Approach Based on Symptom Text Mining and Machine Learning in Healthcare,” IEEE Access, vol. 7, pp. 159884–159893, 2019, doi:10.1109/ACCESS.2019.2952315. [8] S. K. Dash, P. Mishra, and A. Behera, “An Ensemble Approach for Predicting Breast Cancer Survival by Integrating Multiple Machine Learning Models,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 18, no. 2, pp. 570–580, 2021, doi:10.1109/TCBB.2019.2958953. [9] S. Ayyasamy and N. Subashini, “Predictive Modeling for Diabetes Mellitus Using Random Forests and Support Vector Machine,” 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS), 2021, pp. 1231–1235, doi:10.1109/ICICCS51141.2021.9432250. [10] M. Mehmood, M. Sajjad, S. Khan, A. Hussain, and J. Pan, “Symptom-Based Disease Prediction Using Text Classification Techniques,” IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2020, pp. 1580–1585, doi:10.1109/SMC42975.2020.9282919.

Copyright

Copyright © 2026 Dr. Sk. Syed Basha, Dr. Deevi Hari Krishna, Mr. Talluri Lokesh Sai, Mr. Pinapati Manoj Babu, Mr. Rajana Maheshwar Rao, Mr. Vepuri Nanda Rakesh. 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.