Metodología de detección de anomalías en personas con esclerosis múltiple

Resumen

Personalized therapies have proven to be effective in slowing the progression of multiple sclerosis, thereby improving the quality of life of those people suffering from it. However, the design of such therapies requires knowledge of the patient’s functional state and early detection of changes that may occur. Given the drawbacks of traditional assessment techniques, recent studies have proposed monitoring patients’ gait in order to extract relevant indicators and assist specialists in this task. Given this situation, this study proposes a machine learning-based methodology, which aims to detect changes in the functional state of people with multiple sclerosis based on the data provided by a sensorized tip. Taking into account the variability that exists among patients, the proposed design focuses on an individualized approach, which characterizes the state of each individual using only his/her own data. The proposed methodology has been validated in three people with multiple sclerosis, obtaining an average accuracy of 88.9 %.