Enhancing healthcare diagnostics with artificial intelligence: A hybrid machine learning model for early disease detection

Introduction: Artificial intelligence (AI) is transforming healthcare by enabling early and precise detection of chronic diseases, which is crucial for improving patient outcomes and reducing healthcare costs. Material and Methods: This paper presents a hybrid machine learning model that combines convolutional neural networks (CNNs) for advanced feature extraction with random forests for robust classification to diagnose chronic diseases such as diabetes, cardiovascular conditions and hypertension using electronic health records. The model was rigorously evaluated on a comprehensive dataset comprising 10,000 anonymised patient records from a public health repository. Results: The model achieved an impressive accuracy of 92.5%, sensitivity of 90.1%, specificity of 93.4% and F1-score of 90.8%. Conclusion: By integrating the strengths of CNNs in handling complex patterns in structured data and random forests in providing interpretable and efficient decision-making, the model not only balances high accuracy with computational efficiency but also demonstrates superior performance compared to standalone models. This study contributes significantly to the field of AI-driven healthcare solutions by offering a scalable, practical framework for early diagnosis, which can be seamlessly integrated into clinical workflows to enhance patient outcomes and support precision medicine initiatives.