Cloud computing and machine learning algorithms may drastically improve the efficiency and precision of medical diagnostics. But there’s still a huge obstacle to overcome: protecting patients’ personal information while it’s in the cloud, both during transmission and processing. This paper addresses the problem of data breaches and unauthorized access to patient information, which can lead to severe privacy violations and loss of trust in cloud-based medical systems. To tackle this issue, we propose a robust solution involving the implementation of a hybrid encryption scheme that combines advanced encryption standard (AES) and homomorphic encryption. In contrast to homomorphic encryption, which encrypts data without decrypting it, AES enables fast data encryption. With this combined method, even when data is processed on the cloud, patient information is protected all the way through the diagnostic process. Experimental results demonstrate that our proposed solution significantly enhances data security without compromising the performance and accuracy of the machine learning algorithms used for diagnosis. This advancement is a crucial step toward realizing the full potential of cloud-integrated machine learning in medical diagnosis, ensuring patient data privacy and fostering greater adoption of these technologies in healthcare.