Personalized Governance Strategy for Patient Data in a Digital One Health Surveillance System
Edoghogho Olaye, Imonikosaye Omafovbe, Williams O. Aigbe, Daniel Obuh · Procedia Computer Science · 2025
The integration of personal devices in health surveillance has introduced significant patient data risks. In this research, we developed a Patients’ Personal Data Sovereignty System (PPDSS) to intelligently mask the patient's personal and sensitive data that should not be part of the data for analysis, ensuring these sensitive records do not find its way into machine learning models or to the Local Storage of the Capture Device. The approach presented in this paper is to ensure a high level of privacy and confidentiality for patients’ private health information (such as name, address, age and phone number) from the process of data collection, transmission, and storage to data analysis. The PPDSS is an android application built using new Flutter-based Cross Platform Technology which allows us to target other devices in future with same code base is designed to handle the data masking and elimination of Personal Identifiable Patients Data captured using the device camera before sending to the Machine Learning Models as texts. Records were captured from paper records using the camera on a smartphone installed with PPDSS. The image captured by PPDSS was obfuscated and then converted to text using AI-powered optical character recognition (OCR). The result is a personalized governance strategy of patient data, which ensures personal data privacy, confidentiality, and ethical use while maximizing the benefits of data-driven insights. The paper contributes to data governance by proposing a way of solving the problems at the point of data collection, rather than after the data have been collected.