Optimizing Cyber Risk Prediction for Clinical Wearables with Dijkstra's Algorithm and Fuzzy Cognitive Mapping

The development of wearable biosensors marks a transformative era in healthcare, offering personalized medicine and continuous disease monitoring. This article explores advancements in sensor technology, miniaturization, and data analytics that enable diverse wearable devices like smartwatches, e-textiles, and chest-mounted sensors. A critical focus is on the security challenges posed by these devices, particularly through the lens of cyber-attack trees. By modeling potential vulnerabilities, we use graph theory to identify the shortest path an attacker might exploit and emphasize strengthening security along this path. This paper suggests that while Dijkstra's algorithm identifies key communication links that need to be secured, a fuzzy cognitive map can analyze vulnerability impacts and propagation in a cyberinfrastructure, which is reflected through cyber-attack graph analysis. Additionally, the paper addresses challenges using wearable technology and analyze them through the cyber-attack graph (tree) based approaches that enhance biosensor sensitivity and reliability, ensuring their secure and impactful role in future healthcare.