Healthcare in the country is grappling with medical data exchange fragmentation, doctor-to-doctor referral process, secure information transfer between hospitals, and patient-convenient portals to personal records being termed as critical points of vulnerability. Concerns are the isolation of health records within hospitals, risks of information abuse of revealed information, and the absence of adequate security protocols. To address these, the Electronic Health Record (EHR) Architecture based on Blockchain was created in collaboration with the hospital, physician, payer, and patient ecosystem. This paper evaluates the feasibility of applying the architecture to store clinical data in a manner that preserves privacy, provides controlled availability and reconciles competing demands for sharing and confidentiality, and promotes compatibility among disparate clinical and administrative system domains. Privacy, in this context, means detailsis accessible only to particular parties and is inviolate in any way—visible, modified, transmitted, or deleted—while being kept, transported, or processed without authorization by a patient. Availability requires that, despite unforeseen sabotage, malfunction, equipment obsolescence, or malicious behavior, patients and legitimate caregivers have access to required information without impeding workflows. Both practice and literature point out that the creation of this double horizon of privacy and resilience require the active participation of all stakeholders, corporate or individual. Interoperability in legacy practice valleys has centered mainly on plugs between information systems. The patient-care community has been busy in now with enabling patients to enter their healthdetails, with the passing being at their discretion. Our system offers privacy and data integrity through the acquisition of medical data first and then encrypting the data through Attribute-Based Encryption, where the best to sharpen the key is the DES algorithm. After encryption, the information is kept in a permissioned blockchain, provides layered access control and protection against compromised information. To further support the patient, we have integrated a predictive analytics module in our patient interface that utilizes machine-learning classifiers i.e. Random Forest, Logistic Regression, and Decision Tree to make near disease detection
C M SheelaRani (Mon,) studied this question.