Artificial intelligence is being utilized in healthcare to support decision-making and achieve early disease detection. This article proposes an artificial intelligence-based disease prediction system that determines diseases based on symptoms input by the user. The Random Forest classifier was selected for the proposed system due to its speed and accuracy on medical data. The dataset is preprocessed by cleaning, encoding, and feature selection to increase the prediction accuracy. A basic interface is designed to let the user input the symptoms and receive the prediction result instantly. It should be noted that the system does not replace a medical practitioner but can provide early insight for the user to take appropriate action. The experimental results indicate that the model achieves high accuracy and generalizes well over other cases.-
Keywords
Crisis Detection, Social Media Analysis, Natural Language Processing, Multi-Layer Perceptron, TF-IDF, Geospatial visualization, Emergency Management.
Conclusion
The research presented here is an AI-based Disease Prediction System that employs machine learning techniques to predict diseases based on user symptoms.
The methodology used in this implementation consists of data preprocessing, feature selection, and using a Random Forest classifier to provide accurate and efficient predictions of diseases. Further, the proposed model can produce reliable predictions by analyzing the patterns of medical symptoms. Additionally, it is able to predict with a low level of computational complexity.
Through the experimental results of this project, it was found that the Random Forest classifier was superior to the other evaluated models (in terms of accuracy, precision, recall, and F1-score). In addition, the proposed implementation provided high prediction accuracy with low weight and thus could be deployed on standard hardware easily.
Furthermore, the implementation included a web-based user interface, which allowed users to submit their symptoms and receive their evaluated predictions almost instantaneously; therefore, making the system more accessible to the user. The implementation of this research demonstrates how machine learning can be effectively used to provide early detection of disease and subsequently provide assistance in the health care systems. The system works efficiently but there is a future scope for improvement. The existing model is highly dependent on symptom based input and does not take into account advanced medical information like laboratory reports or medical imaging.
In summary, the proposed system highlights the increasing ability of Artificial Intelligence to improve healthcare access, early diagnosis and decision-making support. The Random Forest classifier produced accurate and reliable results while maintaining low computational complexity. The system provides quick disease prediction through a simple web interface and can support early diagnosis in healthcare applications. Key contributions: Accurate disease prediction
Lightweight and low-cost implementation
Easy deployment on standard systems
Real-time prediction capability In conclusion, the proposed system demonstrates the potential of Artificial Intelligence in improving healthcare accessibility, early diagnosis, and decision-making support.
References
[1]T. Mitchell, Machine Learning, New York, NY, USA: McGraw-Hill, 1997.
[2]L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1,
pp. 5–32, 2001.
[3]F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
[4]I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, Cambridge, MA, USA: MIT Press, 2016.
[5]World Health Organization, “Artificial intelligence in healthcare,” WHO Report, 2021.
[6]D. Dua and C. Graff, “UCI Machine Learning Repository,” University of California, Irvine, 2019.
[7]S. Kotsiantis, “Supervised machine learning: A review of classification techniques,” Informatica, vol. 31, no. 3, pp. 249–
268, 2007.
[8]J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. Burlington, MA, USA: Morgan Kaufmann, 2011.
[9]A. Rajkomar, J. Dean, and I. Kohane, “Machine learning in medicine,” New England Journal of Medicine, vol. 380, no. 14,
pp. 1347–1358, 2019.
[10]K. Sharma and R. Gupta, “Disease prediction using machine learning algorithms,” International Journal of Advanced Research in Computer Science, vol. 10, no. 2, pp. 45–50, 2020.
How to Cite This Paper
Sachin Kumar, Kajal Singh, Harshita Sharma, Divyanshu Upadhyay, Rupendra Kaushik (2026). An AI-Based Disease Prediction System for Early Healthcare Diagnosis. International Journal of Computer Techniques, 13(3). ISSN: 2394-2231.
