Health-Aware Path Planning Using Environmental Data and Sequential Prediction Models for Asthma Management

Asthma patients are more prone to environmental elements like the quality of air, weather, humidity, and air pollution, which directly affect their respiratory health in relation to day-to-day activities. Deterioration in negative environmental conditions may cause severe asthma attacks, thereby resulting in emergency situations and a decline in the quality of life. In spite of the existence of conventional navigation apps, there is still a widespread shortage of systems with dynamic incorporation of health risk into route planning, especially among vulnerable populations. This work introduces a novel health-aware and personalized route planning system, which cleverly employs real-time environmental data such as air quality indexes, temperature, and humidity levels obtained through public APIs such as OpenWeatherMap and AirVisual (IQAir), together with patient health profiles. These profiles were synthetically generated to reflect variations in asthma severity, allergen sensitivity, age, and gender. The system highlights the integration of a heuristic-based A* pathfinding algorithm and sequential prediction models, specifically Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) architecture, in an attempt to predict the optimal steps next along a patient’s trajectory. Continuous real-time environmental inputs are incorporated to enable dynamic adjustment of walking trajectories to prevent exposure to unfavorable conditions. Testing on real environmental datasets and simulated urban mobility traces has shown that the Long Short-Term Memory (LSTM) model had a prediction accuracy of 78% and an F1-Score of 0.73, outperforming baseline methods. Moreover, sequential modeling coupled with heuristic search has significantly enhanced adaptability and health sensitivity of route suggestions. No real patient data was used in this study, and all health information was simulated to preserve privacy and ensure ethical compliance. The system described is intended to promote greater safety, minimize environmental exposure threats, and facilitate smart, health-aware urban mobility, in the end protecting the well-being of vulnerable citizens amidst evolving urban environments.