From raw data to actionable insights: preprocessing real-world data for machine learning in diabetes care
ML models' performance and their explanation did not vary substantially across experimental conditions, with worse baseline values being predictors of HbA1c decrease at three years. Insights such as this, extracted by ML application to RWD, enable clinical discussion and may foster improvements in patient management.
Authors
- Emanuela Setola
- Carlo Tacchetti (ORCID: https://orcid.org/0000-0003-4602-000X)
- Simone Barbieri (ORCID: https://orcid.org/0000-0002-3404-8921)
- Edoardo Draetta
- Patrizia Rovere‐Querini (ORCID: https://orcid.org/0000-0003-2615-3649)
- Alessio Dimonte
- Bruno Fabiani
- Antonio Esposito
- Lorenzo Piemonti
- Alberto Traverso
- Marco Montagna
- Aleksandar Svilenov Rabadzhiev
Institutions
- Vita-Salute San Raffaele University (IT)
- Istituti di Ricovero e Cura a Carattere Scientifico (IT)
- Imaging Center (US)
- Istituto di Ricovero e Cura a Carattere Scientifico San Raffaele (IT)
Publication Details
- Journal
- Frontiers in Digital Health
- Published
- 2026-02-25
- DOI
- https://doi.org/10.3389/fdgth.2026.1685842
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00