DEVELOPMENT OF A SMART DIGITAL HEALTH ECOSYSTEM: ARTIFICIAL INTELLIGENCE DRIVEN HEALTH MONITORING AND TREATMENT ADHRENCE SYSTEM
Abstract
Sickle Cell Disease (SCD) is a difficult condition with its chronic progression, unpredictable pain crisis, and poor compliance with treatment, causing high morbidity and healthcare cost. The aim of this project is to develop an AI-driven health monitoring and treatment adherence system. The approach integrates machine learning models like Random Forest, Long Short-Term Memory (LSTM) networks, k-Means Clustering, and Naïve Bayes to predict vaso-occlusive crises from patient self-reported symptoms and vital signs. The system was implemented on Python, FastAPI, React Native, and SQLite with a web application for tracking symptoms, reminders for medication, educational material customized for the individual, and secure doctor-patient messaging via WebSocket. Pilot trials using simulated data were characterized by rapid response times and high user satisfaction, with the system being use in predicting crisiss. By addressing the limitations of existing digital interventions, such as weak integration and prediction capabilities, this system empowers patients, reduces emergency hospitalizations, and improves healthcare delivery to disadvantaged SCD patients. Future expansion involves integration with wearable sensors and multilingual delivery to further enhance availability and effectiveness.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.