System Maintenance Notice

Please note that maintenance work is scheduled between 4 AM and 5 AM - CET. During this time, you may experience reduced performance. Thanks for your patience.

Publications

Journal Article Ahead of print

PubMed: 42873203 DOI: 10.1177/13524585261492525

Validation of generative artificial intelligence techniques for synthetic data generation in multiple sclerosis research: A comparison with real-world evidence from the Italian multiple sclerosis registry.

Mult Scler

Authors: Pietro Iaffaldano, Saverio D'Amico, Giuseppe Lucisano, Massimiliano Copetti, Tommaso Guerra, Maria A Rocca, Francesco Patti, Giovanna De Luca, Diana Ferraro, Rocco Totaro, Vincenzo Brescia Morra, Giuseppe Salemi, Emilio Portaccio, Matteo Foschi, Matilde Inglese, Maria G Coniglio, Clara G Chisari, Francesca Caputo, Damiano Paolicelli, Mario A Battaglia, Matteo G Della Porta, Victor Savevski, Mattia Delleani, Filippo E Colella, Elisabetta Sauta, Maria P Amato, Massimo Filippi, Maria Trojano

Affiliations

  • Department of Translational Biomedicine and Neurosciences (DiBraiN), Multiple Sclerosis Center, Policlinico of Bari, University of Bari Aldo Moro, Italy.
  • IRCCS Humanitas Research Hospital, Milan, Italy.
  • Train S.r.l. Milan, Italy.
  • Center for Outcomes Research and Clinical Epidemiology-CORESEARCH SRL, Pescara, Italy.
  • Unit of Biostatistics, Fondazione IRCCS "Casa Sollievo della Sofferenza", San Giovanni Rotondo, Italy.
  • Neuroimaging Research Unit, Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy.
  • Vita-Salute San Raffaele University, Milan, Italy.
  • Neurology Unit, IRCCS San Raffaele Scientific Institute, Milan, Italy.
  • Dipartimento di Scienze Mediche e Chirurgiche e Tecnologie Avanzate, GF Ingrassia, University of Catania, Italy.
  • UOS Sclerosi Multipla, AOU Policlinico "G Rodolico-San Marco", Università di Catania, Italy.
  • Centro Sclerosi Multipla, Clinica Neurologica, Policlinico SS Annunziata, Università "G. d'Annunzio", Chieti-Pescara, Italy.
  • Dipartimento di Neuroscienze, Ospedale Civile di Baggiovara, Azienda Ospedaliera-Università di Modena, Italy.
  • Centro Malattie Demielinizzanti, Ospedale San Salvatore, L'Aquila, Italy.
  • Department of Neurosciences, Reproductive and Odontostomatological Sciences, Multiple Sclerosis Clinical Care and Research Center, University of Naples Federico II, Italy.
  • Department of Biomedicine, Neurosciences and Advanced Diagnostics, University of Palermo, Italy.
  • Department of NEUROFARBA, University of Florence, Italy.
  • Neurology Unit, Department of Neuroscience, Multiple Sclerosis Center, Santa Maria delle Croci Hospital, Azienda USL Romagna, Ravenna, Italy.
  • Department of Biotechnological and Applied Clinical Sciences, University of L'Aquila, Italy.
  • Dipartimento Di Neuroscienze, Riabilitazione, Oftalmologia, Genetica E Scienze Materno-Infantili (DINOGMI), Università di Genova, Italy.
  • IRCCS, Ospedale Policlinico San Martino, Genova, Italy.
  • Center for Multiple Sclerosis, ASM P.O. "Madonna Delle Grazie", Matera, Italy.
  • Scientific Research Area, Italian Multiple Sclerosis Foundation (FISM), Genova, Italy.
  • Department of Biomedical Sciences, Humanitas University, Milan, Italy.
  • IRCCS Fondazione Don Carlo Gnocchi, Florence, Italy.

Abstract

BACKGROUND

The use of generative artificial intelligence to create synthetic data is an emerging strategy to enhance real-world evidence.

OBJECTIVE

To assess the validity of artificial intelligence-generated synthetic data in replicating data collected in the Italian Multiple Sclerosis and Related Disorders Register for the evaluation of progression independent of relapse activity risk under early intensive treatment and escalation treatment strategies.

METHODS

Artificial intelligence generative models were trained on a sub-cohort of 1666 Italian Multiple Sclerosis and Related Disorders Register patients to generate a synthetic dataset of 4878 patients. Synthetic vAlidation FramEwork, Clinical Synthetic Fidelity, and Nearest Neighbor Distance Ratio were applied. Comparisons between treatment strategies were conducted using both real and synthetic data, focusing on progression independent of relapse activity risk.

RESULTS

The synthetic data demonstrated fidelity and privacy preservation. Treatment-effect estimates for escalation treatment versus early intensive treatment were similar across the real and synthetic datasets. Cox proportional hazards models showed that synthetic data preserved the robustness of the estimates for the risk of a first progression independent of relapse activity event. Associations with radiological risk factors were broadly similar across the real and synthetic datasets.

CONCLUSION

Artificial intelligence-generated synthetic data reliably replicated treatment-effect outcomes of Italian Multiple Sclerosis and Related Disorders Register data, supporting their potential use in clinically defined research settings.

MeSH

Registries, Sclerosis, Multiple Sclerosis, Intelligence, Research, Therapeutics, Artificial Intelligence, Generative Artificial Intelligence