Artificial intelligence of imaging and clinical neurological data for predictive, preventive and personalized (P3) medicine for Parkinson Disease: The NeuroArtP3 protocol for a multi-center research study

• DOI: 10.1371/journal.pone.0300127
• Publication Date: 2024-03-14T17:34:21Z
• Authors: Maria Chiara Mala...; Lorenzo Gios; Bruno Giometto; Chiara Longo; Marianna Riello; Donatella Ottaviani; Maria Pellegrini; Raffaella Di Giacopo; Davide Donner; Umberto Rozzanigo; Marco Chierici; Monica Moroni; Giuseppe Jurman; Giorgia Bincoletto; Matteo Pardini; Ruggero Bacchin; Flavio Nobili; Francesca Di Biasio; Laura Avanzino; Roberta Marchese; Paola Mandich; Sara Garbarino; Mattia Pagano; Cristina Campi; Michele Piana; Manuela Marenco; Antonio Uccelli; Venet Osmani
• Keywords: Study Protocol; 03 medical and health sciences; 0302 clinical medicine

Background The burden of Parkinson Disease (PD) represents a key public health issue and it is essential to develop innovative cost-effective approaches promote sustainable diagnostic therapeutic interventions. In this perspective the adoption P3 (predictive, preventive personalized) medicine approach seems be pivotal. NeuroArtP3 (NET-2018-12366666) four-year multi-site project co-funded by Italian Ministry Health, bringing together clinical computational centers operating in field neurology, including PD. Objective core objectives are: i) harmonize collection data across participating centers, ii) structure standardized disease-specific datasets iii) advance knowledge on disease’s trajectories through machine learning analysis. Methods 4-years study combines two consecutive research components: multi-center retrospective observational phase; prospective phase. phase aims at collecting patients admitted centers. Whereas same variables newly diagnosed who will enrolled Results are Provincial Health Services (APSS) Trento (Italy) as center responsible for PD IRCCS San Martino Hospital Genoa promoter NeuroartP3 project. analysis Bruno Kessler Foundation with TrentinoSalute4.0 –Competence Center Digital Province LISCOMPlab University (Italy). Conclusions work behind protocol shows how possible viable systematize procedures order feed implementation into practice use AI models.