ML Based Health Prognosis: Forecasting Medical Conditions
Pratik Shrimant Bhange, Shubham Dilip Yadav , Vipul Suresh Raut , Mrs. Sarojini Naik
Electronics and Computer Engineering P. E. S’s Modern College Of
Engineering
Pune, India
Abstract - The increasing utilization of Big Data in biomedical and healthcare sectors underscores the critical need for accurate analysis to enhance patient care and healthcare systems. This study addresses the challenge of predicting chronic diseases, including diabetes, hypertension, cerebral infarction, and asthma, by harnessing machine learning algorithms. To overcome the accuracy limitations posed by fragmented medical data, a novel approach, the Convolutional Neural Network-based Multimodal Disease Risk Prediction (CNN-MDRP) model, is proposed. This advanced model integrates structured and unstructured data, leveraging Genetic Algorithm for data cleansing and Recurrent Neural Network (RNN) processing to transform unstructured data. Disease prediction is facilitated through classifiers like Naive Bayes (NB), Support Vector Machine (SVM), and logistic regression. Furthermore, upon successful prediction, the system recommends nearby medical facilities to users, enhancing accessibility to healthcare. This interdisciplinary approach amalgamates machine learning, neural networks, and natural language processing to predict diseases accurately. Through comprehensive data analysis and model selection, the system offers a valuable tool for early disease detection and personalized patient care. The proposed model's integration with user-friendly web interfaces facilitates seamless interaction and accessibility. With promising accuracy rates achieved for disease prediction, this study paves the way for future advancements in predictive healthcare technologies, ultimately improving patient outcomes and healthcare delivery systems. Key words: Machine learning algorithms
Machine learning algorithms, Convolutional Neural Network (CNN), Genetic Algorithm, Recurrent Neural Network (RNN), Disease prediction, Support Vector Machine (SVM), Medical facilities, Big Data, Biomedicine, Chronic diseases, Healthcare, Predictive modeling, Neural networks, Natural Language Processing (NLP), User interface, Accessibility.
