Definition of the line
Artificial intelligence (AI) has revolutionized the field of neuroengineering by helping to unveil and better understand the mechanisms of brain function and dysfunction. The study of brain dysfunction and the use of AI have contributed to a better comprehension of neurological disorders having a significant impact on diagnostic, evaluation, and rehabilitation procedures, and enhancing and complementing the existing clinical procedures.
The main research focus of the group is to use AI techniques for understanding the dysfunctional, motor and non-motor manifestations caused by pathological conditions such as Parkinson’s disease, Alzheimer’s, essential tremor, etc. This is achieved through the analysis of various biosignals, including sEMG, trajectory/ acceleration data recorded from MOCAP systems, speech, and oculometric recodings. Subsequently, AI methodologies are employed to extract novel biomarkers, and to uncover and comprehend the functional differences between pathological and normal conditions.
History/expertise of the group in this line
The group is composed of experts in different fields including signal processing, bioengineering, biomechanics and artificial intelligence. This expertise is complemented by active collaboration with hospitals and clinical centers in Spain, including Hospital General Universitario Gregorio Marañón, Hospital Nacional de Parapléjicos de Toledo and Hospital los Madroños, as well as with other multidisciplinary research groups around the world.
The group is currently involved in the AI4HealthyAging and Neuromark projects, in which we develop and use AI models to study motor-related manifestations of Parkinson’s disease using several biometric approaches. We are particularly interested in studying the progression of the disease with time , and to fuse the different recording modalities to improve the understanding of PD manifestations in a holistic way.
Pascual-Valdunciel, Alejandro, et al. “Classification of Kinematic and Electromyographic Signals Associated with Pathological Tremor Using Machine and Deep Learning.” Entropy 25.1 (2023): 114. https://doi.org/10.3390/e25010114
Pascual-Valdunciel, Alejandro, et al. “Prediction of Pathological Tremor Signals Using Long Short-Term Memory Neural Networks.” IEEE Journal of Biomedical and Health Informatics 26.12 (2022): 5930-5941. https://doi.org/10.1109/JBHI.2022.3209316.
Cermeno-Silveira, C., et al. “Detecting Parkinson’s Disease from body limb acceleration using machine learning and a frequency-domain analysis.” MOVEMENT DISORDERS. Vol. 37. 111 RIVER ST, HOBOKEN 07030-5774, NJ USA: WILEY, 2022. (link)
Perez Sanchez, J. R., et al. “IMU-based study on Gait and Balance in Parkinson’s disease and healthy subjects.” MOVEMENT DISORDERS. Vol. 35. 111 RIVER ST, HOBOKEN 07030-5774, NJ USA: WILEY, 2020.
Caramia, Carlotta, et al. “IMU-based classification of Parkinson’s disease from gait: A sensitivity analysis on sensor location and feature selection.” IEEE journal of biomedical and health informatics 22.6 (2018): 1765-1774. https://doi.org/10.1109/JBHI.2018.2865218
Dr. Jorge García
Dr. Diego Torricelli