Por Helena Aidos (LASIGE/DI-FCUL).
Amyotrophic Lateral Sclerosis (ALS) is a rapidly progressive neurodegenerative disorder characterized by progressive loss of motor neurons in the brain and spinal cord, leading to muscular weakness and ultimately death. Life expectancy is 3 to 5 years after disease onset, there is no cure or known causes, and disease heterogeneity makes it difficult to understand its underlying mechanisms. ALS is also the most common neurodegenerative disease in young adults. Thus, finding a cure/ways to slow disease progression, improve patients’ prognosis, and promote patients’ quality of life are nowadays fundamental research challenges. In this context, it is crucial to exploit clinical data and machine learning techniques to learn patient profiles from heterogeneous sources of data, targeting patient stratification, and improve machine learning models for prognostic prediction. Hence, this talk will highlight recent developments in machine learning applications for ALS, focusing on patient profiling, identification of disease progression patterns, and advancements in prognostic prediction to support more personalized and effective approaches in ALS care and research.
Short Bio: Helena Aidos is an Assistant Professor at FCUL and a Senior Researcher at LASIGE. She participated and participates in national and international research projects in bioinformatics and data science topics. Her research focuses on the development and application of machine learning techniques in clinical settings, more specifically, supervised and unsupervised learning algorithms (such as clustering, clustering ensembles, and dimensionality reduction techniques), targeting diagnosis and prognosis of neurodegenerative diseases (such as amyotrophic lateral sclerosis).
