Heart disease prediction using machine learning algorithm

Research paper on heart disease prediction using machine learning algorithm

1. Heart disease prediction using machine learning algorithm INTRODUCTION Heart disease remains a leading cause of mortality worldwide, necessitating effective predictive methodologies for timely intervention. This research investigates the application of machine learning algorithms to predict heart disease based on patient data. Discover the power of machine learning in predicting heart disease. Explore the importance of accurate prediction and gain insights into various algorithms.

2. LITERATURE REVIEW Several studies explore machine learning algorithms for heart disease prediction, leveraging diverse datasets and methodologies. They commonly employ techniques like decision trees , random forest, and support vector machines, aiming to enhance accuracy and efficiency in identifying risk factors and predicting cardiovascular conditions. The review highlights the challenges of imbalanced data, overfitting, and model interpretability, while suggesting future directions to enhance predictive accuracy and clinical applicability in preventing heart diseases.

3. METHODOLOGY DATA SOURCE An Organized Dataset of individuals had been selected Keeping in mind their history of heart problems and in accordance with other medical conditions. We take a data source which is comprised of medical history of 304 different patient of different age groups. This dataset gives us the much-needed information i.e. the medical attributes such as age, resting blood pressure, fasting sugar level etc. of the patient that helps us in detecting the patient that is diagnosed with any heart disease or not. DATA PREPROCESSING In this research we have utilized the describe function and pandas profiling in Python to summarize the dataset and used various central tendency to handle the missing values and the outliers.

4. MACHINE LEARNING ALGORITIHMS Discover an overview of the most commonly used machine learning algorithms for heart disease prediction. Understand their strengths and weaknesses to choose the most suitable algorithm for your specific needs. Algorithm Pros Cons Logistic Regression Interpretability Assumes linearity Decision Trees Nonlinear relationships Can lead to overfitting Random Forest Highly accurate Difficult to interpret Support Vector Machines Effective with high-dimensional data Can be slow with large datasets K-Nearest Neighbors Simple to implement Sensitive to data scaling

5. RESULTS AND FINDINGS The algorithms that we used are more accurate, saves a lot of money i.e. it is cost efficient and faster than the algorithms that the previous researchers used Our objective was to think about various arrangement models and characterize the most productive one. The accuracy score achieved using Logistic Regression is: 85.25 % The accuracy score achieved using Naive Bayes is: 85.25 % The accuracy score achieved using Support Vector Machine is: 81.97 % The accuracy score achieved using K-Nearest Neighbors is: 67.21 % The accuracy score achieved using Decision Tree is: 81.97 % The accuracy score achieved using Random Forest is: 95.08 %

6. FUTURE SCOPE Advanced Feature Engineering: Exploring novel biological markers and imaging data integration for richer feature sets to enhance model accuracy. Interpretability and Explain ability: Developing interpretable models to bridge the gap between predictions and clinical decision-making, ensuring trust and adoption by healthcare professionals. Real-time Monitoring Systems: Creating scalable, real-time predictive systems integrated with wearable technology and IoT devices for continuous, personalized cardiac health monitoring, enabling early intervention and personalized care.

7. CONCLUSIONS The study demonstrates the potential of machine learning in heart disease prediction, showcasing its effectiveness in leveraging diverse algorithms for accurate prognosis. It underscores the significance of robust data preprocessing, feature selection, and model comparison for enhanced predictive performance. Despite notable achievements, challenges persist, including imbalanced datasets and interpretability issues. However, this research illuminates pathways for refining models, emphasizing the need for clinical validation and real-world implementation. Ultimately, this work establishes machine learning as a promising tool in preventive healthcare, offering avenues for early detection and personalized interventions, thereby contributing significantly to reducing the burden of heart diseases.

8. REFERENCES [1] Muktevi Srivenkatesh . "Prediction of Cardiovascular Disease using Machine Learning Algorithms" - International Journal of Engineering and Advanced Technology 2020 [2] Pronab Ghosh, Sami Azam, Mirjam Jonkman , Asif Karim, F. M. Javed Mehedi Shamrat , Eva Ignatious , Shahana Shultana , Abhijith Reddy Beeravolu,And Friso De Boer. "Efficient Prediction of Cardiovascular Disease Using Machine Learning Algorithms With Relief and LASSO Feature Selection Techniques" - College of Engineering, IT, and Environment, Charles Darwin University, Casuarina, NT 0810, Australia 2021 [3] V.Archana Reddy, K Venkatesh Sharma. "Heart Disease Classification And Risk Prediction By Using Convolutional Neural Network" - International Journal of Aquatic Science ISSN: 2008-8019 Vol 12, Issue 02, 2021 [4] Harshit Jindal. "Heart disease prediction using machine learning algorithms" - IOP Conference Series: Materials Science and Engineering 2021