 A Machine Learning Approach for Disease Prediction Based on Age, Lifestyle Habits, and Symptom Analysis

Abstract: This project is about making a smart web system that helps people know if they are at risk of getting five common diseases. These diseases are heart disease, cancer, liver disease, diabetes, and chronic bronchitis. The system uses artificial intelligence (AI) to look at personal health information like age, smoking and drinking habits, sleep routine, how much exercise a person does, and what symptoms they have. Before training the models, the data was cleaned and changed using encoding and scaling so the AI could understand it better. Two machine learning models, Random Forest and Support Vector Machine (SVM), were trained to predict the risk of these diseases. The Random Forest model gave a very high accuracy of 96.8%, while SVM gave 95.3%. These models were added into a Flask-based web app, and MongoDB was used to save real-time user data and predictions. This system helps people take care of their health early. In the future, more diseases will be added, and it will be tested with real users.

Machine Learning, Random Forest, Support Vector Machine, Preventive Healthcare, Symptom Analysis, Artificial Intelligence.

1. Md Manjurul Ahsan, Shahana Akter Luna, Zahed Siddique. “Machine-Learning-Based Disease Diagnosis: A Comprehensive Review.” Healthcare (Basel). 10(3):541, 2022. [PMCID: PMC8950225]1 [Google Scholar] [Crossref]

2. Farzaneh Sogandi, et al. “Identifying diseases symptoms and general rules using supervised and unsupervised machine learning.” Sci Rep, 2024.2 [Google Scholar] [Crossref]

3. Yogendra Kumar, Rinkle Rani, Chhavi Rana. “Artificial Intelligence in Disease Diagnosis: A Systematic Literature Review.” Comput Biol Med, 2022.3 [Google Scholar] [Crossref]

4. Fuster-Palà, et al. “Optimized Machine Learning Classifiers for Symptom-Based Disease Detection,” Computers, 2024.4 [Google Scholar] [Crossref]

5. “Disease Predictor Based on Symptoms Using Machine Learning.” IJRASET, [Online]5 [Google Scholar] [Crossref]

6. “Disease Predictor Based on Symptoms Using Machine Learning.” J Neonatal Surg. 2025.6 [Google Scholar] [Crossref]

7. Jabir Al Nahian, et al. “Common Human Diseases Prediction Using ML Based on Survey Data.” arXiv:2209.10750, 2022.7 [Google Scholar] [Crossref]

8. E.F. Dinsa, et al. “AI-based disease category prediction model using supervised machine learning.” Sci Rep, 2024.8 [Google Scholar] [Crossref]

9. “Disease Prediction Based on Symptoms Using Machine Learning,” PSG TECH Project Report, 2023.9 [Google Scholar] [Crossref]

10. Rayan Alanazi. “Identification and Prediction of Chronic Diseases Using Machine Learning Approach.” Comput Math Methods Med, 2022.10 [Google Scholar] [Crossref]

11. K. Gaurav, A. Kumar, et al. “Human Disease Prediction using ML Techniques and Real-life Parameters.” Int J Eng, 36(6), 2023, 1092-1098.12 [Google Scholar] [Crossref]

12. Zhou Z., Zeng Y., et al. “Machine Learning for Online Automatic Prediction of Common Diseases.” Front Public Health, 2022.14 [Google Scholar] [Crossref]

13. “Predicting Disease from Several Symptoms Using Machine Learning.” IRJET V10I7116.pdf, 2023.15 [Google Scholar] [Crossref]

14. “Early-Stage Disease Prediction from Various Symptoms Using Machine Learning." EAI Endorsed Trans Internet of Things. 2023.16 [Google Scholar] [Crossref]

15. Anamika Sharma, Jatin Nain. “The role of machine learning in infectious disease early detection: A systematic review.” Informatics Med Unlocked, 2025.17 [Google Scholar] [Crossref]

• Advanced Techniques for Fake News Detection on Twitter Using NLP and AI: A Comprehensive Review
• Review of Self Compacting Geopolymer Concrete Using Slag Sand as Fine Aggregate
• Performance of Local Construction Contractors – Case Study of Registered Contractors in Monrovia, Liberia
• Cross-Cultural Perspectives on Innovation Management in Multinational Organizations
• Modeling of Reaction Between Dissolved Oxygen (DO) And Biological Oxygen Demand (BOD) in Degradation River