Cesare Furlanello

FBK

Cesare Furlanello is head of Data Science at the Kessler Foundation (FBK Trento, Italy), where he also leads the MPBA Lab (https://mpbalab.fbk.eu). After graduating with honours in Mathematics at the University of Padua, he joined IRST, the first Artificial Intelligence research centre in Italy. He is a data scientist and an expert in machine learning applied to complex data with a focus on predictive models for human and environmental health. He has been PI of more than 60 projects funded by competitive grants or industry, including the first national project on industrial and health applications of neural networks in 1993, EU projects, including 4 projects of the European Institute of Technology, and grants from the Italian Ministry of Health linking geoinformatics to machine learning (Cancer mapping, predictive models for mitigation of road accident risk). Many of MPBA algorithms have been translated in data-driven infrastructures for industry and public administrations. He is a founder of three startups. He has published in machine learning and bioinformatics on Nature, Nature Biotech, Nature Genetics, Bioinformatics, IEEE J. Sign Proc., IEEE Trans Nano Biosc, Brief. Bioinformatics and others. CF has been Scientific secretary of the first GNCB-CNR school on Neural Networks for Signal Processing (Trento 1989), Conference Chair of the MGED11 Workshop of the MGED Society, organizer of many other workshops on applied Machine Learning, including the Deep Learning for Precision Medicine worskshops (2016 and 2017). He is adjoint research faculty of The Wistar Institute cancer research centre in Philadelphia. He has a national habilitation as full professor in Bioengineering; he is a founder of the Laboratory of Biomolecular Sequence and Structure Analysis for Health (FBK-Univ. of Trento-CNR) and a member of the PhD Board of the Centre for Integrative Biology of the University of Trento. Since 2001, he is Scientific Director of WebValley, the first summer school in Data Science for interdisciplinary research dedicated to talented high school students. His research currently aims at developing reproducible Deep Learning methods for Precision Medicine, with a focus on the integration of multi-modal omics and imaging data. He is President Elect of the MAQC international society for analysis and quality control of massive healthcare data.


Speeches di Cesare Furlanello

Deep Learning per Healthcare: le sfide della riproducibilità e della privacy-by-design

Gli algoritmi predittivi come servizio per ricercatori medici e clinici, ma anche per analizzare in tempo reale i dati dai dispositivi personali, sono al centro della sfida per un cambiamento epocale dei processi di Healthcare. Quanto possiamo davvero affidarci agli agli algoritmi di AI - sia in termini di accuratezza che di rispetto della privacy? Sarà introdotto il tema della riproducibilità nello sviluppo di modelli di machine learning da "massive data", partendo da horror story recenti nello sviluppo di biomarker predittivi che sembrano destinate a ripetersi in un contesto di diagnosi e predizione da dati medici complessi, multimodali, e spesso incompleti. Per garantire soluzioni accurate di deep learning per la ricerca medica e farmacogenomica su database sempre più complessi, discuteremo di strumenti sviluppati in collaborazione con la FDA per migliorare riproducibilità e generalizzazione. Saranno inoltre discussi aspetti di sicurezza e contromisure nell'uso del machine learning in dati di salute, cercando di identificare gli elementi indispensabili per le applicazioni in medicina di precisione.

Lingua speech: Italian

Topics

Genomics & Health


All Speakers

Promosso e organizzato da

Roma Tre
Maker Faire

Con il contributo scientifico di


Con il Patrocinio di
Autorità Garante della Concorrenza e del Mercato

Main Partner
Eni
Bnl
Acea
Google


Diamond Partner
Hpe

Silver Partner
Data ReplyCerved
Official Taxi
My Taxi

Technical Partner
Iaml Tecnopolo di Roma

Ecosystem Partner
Talent Garden

Community Partner
Machine Learning

Si ringrazia
Car

Media Partner
Il Messaggero

Follow us

   #DataDriven2018