Modern Secure Electronic Health Framework (M-SEHF) for Collaborative Medical Data Analysis with Privacy-Preserving Techniques

Background: As healthcare data grows exponentially, cloud computing has emerged as a scalable solution for managing and storing electronic health records (EHRs). However, ensuring the confidentiality and integrity of such sensitive information in open and distributed environments remains a pressing concern. Classical Secure Electronic Health Frameworks (SEHFs) frequently use single-layer encryption and static rule-based systems, which are unable to handle huge, unstructured datasets efficiently and do not offer real-time data handling or semantic analysis. Objective: This study introduces a Modern Secure Electronic Health Framework (M-SEHF) that ensures end-to-end confidentiality, integrity, and accessibility of medical data in cloud environments. The framework integrates Natural Language Processing (NLP), Decision Tree (DT) algorithms, and hybrid cryptographic techniques to enable secure data classification, processing, and storage. Methods: M-SEHF employs NLP-based pre-processing to identify and sanitize Protected Health Information (PHI) from patient records. Decision Tree algorithms classify records by sensitivity level, while a hybrid encryption model Advanced Encryption Standard (AES-256) for data and RSA for secure key exchange ensures privacy during cloud storage and transmission. A custom mapping algorithm securely links encrypted data to its source for traceable access. Findings: Evaluated on a dataset of 100,000 anonymized patient records (~1 TB), M-SEHF achieved 94.6% accuracy in PHI detection and classification. It reduced average data retrieval latency to 2.3 seconds—30% faster than existing systems, while fully adhering to HIPAA privacy standards. Novelty and Contribution: M-SEHF is the first cloud security framework to integrate real-time semantic pre-processing (NLP-DT) with hybrid encryption AES and RSA in a scalable pipeline tailored for healthcare big data. By enabling dynamic sensitivity analysis and multi-layered encryption, it gets beyond the drawbacks of traditional SEHFs and provides better accuracy, speed, and privacy compliance. A strong, adaptable, and future-proof security solution is offered by M-SEHF to meet the changing needs of digital healthcare. Keywords: Big data, Natural Language Processing (NLP), Cloud Computing, Patients' history, Encryption