Rossella Tupler
Computational Models for new Patients Stratification Strategies of Neuromuscular Disorders: a new strategy to tackle hereditary neuromuscular disorders
Autori
- BENEDIKT SCHOSER (FRIEDRICH-BAUR-INSTITUT AN DER NEUROLOGISCHE KLINIK UND POLIKLINIK, KLINIKUM DER UNIVERSITÄT MÜNCHEN, LUDWIG-MAXIMILIANS-UNIVERSITÄT MÜNCHEN, GERMANY – NEUROLOGIST)
- JOANNA POLANSKA (DEPARTMENT OF DATA SCIENCE AND ENGINEERING, SILESIAN UNIVERSITY OF TECHNOLOGY, GLIWICE, POLAND – COMPUTATIONAL SCIENTIST)
- VOLKER STRAUB (JOHN WALTON MUSCULAR DYSTROPHY RESEARCH CENTRE, TRANSLATIONAL AND CLINICAL RESEARCH INSTITUTE, NEWCASTLE UNIVERSITY AND NEWCASTLE HOSPITALS NHSFOUNDATION TRUST, NEWCASTLE UPON TYNE, UK – NEUROLOGIST)
- MARCO SVARESE (FOLKHÄLSAN RESEARCH CENTER, HELSINKI, FINLAND – GENETICIST)
- FILIPPO SANTORELLI (MOLECULAR MEDICINE, IRCCS FONDAZIONE STELLA MARIS, PISA, ITALY – NEUROLOGIST)
- JOCELYN LAPORTE (IGBMC (INSTITUT DE GÉNÉTIQUE ET DE BIOLOGIE MOLÉCULAIRE ET CELLULAIRE), UNIVERSITÉ DE STRASBOURG, ILLKIRCH, FRANCE – MOLECULAR BIOLOGIST)
- MARCELLO SCIPIONI (FINCONS GROUP, LUGANO, SWITZERLAND – INFORMATICIAN)
- MICHAEL OBACH (TECNALIA, SAN SEBASTIAN, SPAIN – PHYSICIST)
- PETER STEENSGAARD (CEGAT GMBH, TÜBINGEN, GERMANY – MEDICAL DOCTOR)
- ANNALISA DE ANGELIS (DEEPBLUE, ROMA, ITALY – HUMAN SCIENTIST)
- ROSSELLA TUPLER (DIPARTIMENTO DI SCIENZE BIOMEDICHE, METABOLICHE E NEUROSCIENZE, UNIVERSITÀ DI MODENA E REGGIO EMILIA, MODENA, ITALY – MEDICAL GENETICIST)
Presentatore
ROSSELLA TUPLER
Modalità
Oral Communication
Abstract
Computational tools and Artificial Intelligence (AI) are an unprecedented opportunity to expand medical knowledge and make clinical decisions more precise. The CoMPaSS-NMD project aims at developing and testing novel AI-based stratification methods of hereditary neuromuscular disorders (HNMD) patients based on a huge base of multidimensional genomic, clinical, and MRI data provided by third-level Clinical Reference Centers in France, Germany, Finland, United Kingdom and Italy. Computational tools for high-dimensional clustering will be applied in an unsupervised learning approach using the internal structure of data to define groups of similar patients. Moreover, classification model averaging and integration techniques for federated learning-inspired model building and novel HNMD-specific descriptors of histopathological images will be applied. This approach allows for developing cost-effective AI-based applications – CoMPaSS-NMD Atlas – serving a precise clinical characterization and diagnosis of people living with HNMDs and to uncover new patterns present in data that can advance knowledge and response prediction. AI-guided Reframing Deep Disease Gestalt and Progression will provide clinical researchers with effective health data integration solutions for a more precise classification of the clinical phenotypes. Based on the developed and validated robust data-driven AI-guided Clinical Toolbox that will be used by researchers and health care professionals to successfully stratify patients, CoMPaSS-NMD will deliver evidence-based guidelines for stratification-based patient management to be adopted by health care professionals to offer superior standard-of-care for diagnosis and prognosis for HNMDs patients and assist in planning clinical trials.