Real-World Gait Speed Estimation: an AI-based Approach for Adaptive Wearable Devices Integration

Real-world gait speed assessment, has recently gained recognition as an important health indicator particularly in patients with chronic conditions such as Chronic Obstructive Pulmonary Disease (COPD). This study proposes an AI-based method for estimating gait speed in the real-world context in COPD patients using different combinations of three wearable devices: a smartphone, a smartwatch, and a pair of sensorized shoes. An analysis pipeline is developed and trained using laboratory datasets, then validated on an independent dataset acquired under free-walking conditions, demonstrating strong performance in both walking detection and gait speed estimation with mean accuracies across different device combinations of 0.81, 0.93, and 0.90 for resting, walking, and stair climbing activities, respectively, as well as a mean RMSE of 0.118 m/s and an ICC of 0.80. The estimated speed, obtained by applying the developed pipeline to daily life data of COPD patients, showed a strong and significant correlation with the clinical standard of functional capacity, the six-minutes walking distance (6MWD) across 34 patients (Spearman coefficient = 0.854, p-value = 1.38e-10). These findings highlight the feasibility of unobtrusive, continuous gait speed monitoring in real-life conditions, offering a promising integrative tool to traditional clinical assessments. The results suggest that wearable-based mobility monitoring could enhance remote patient management and personalized care strategies for COPD and other chronic conditions.