Machine Learning–Based Classification of Active and Latent Phases of Inherited Retinal Dystrophies Using Synthetic Proteomic Data: A Pathway-Based Application Exercise
Healthcare Informatics Research · 31.07.2026 · 32 (3) · 285-292
DOI: 10.4258/hir.2026.32.3.285 ↗Kurz gefasst
Fachartikel in der Zeitschrift Healthcare Informatics Research, erschienen am 31.07.2026. Verfasst von Alessandro Macchia und 19 weiteren Autor:innen. Beteiligte Einrichtung: MAGI'S LAB, Rovereto (TN), Italy. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Provincia Autonoma di Trento in the scope of LP.
Abstract (Originalsprache)
Objectives
Inherited retinal dystrophies are characterized by high genetic and phenotypic heterogeneity, and their clinical progression may alternate between latent and active phases. Identifying the onset of the active phase may support earlier intervention for inflammatory retinal degeneration. Plasma proteomics has shown potential for characterizing predictive biomarkers in retinal diseases, but its application remains experimental. This study aimed to develop a methodological simulation exercise to evaluate the performance of machine learning (ML) models in distinguishing active and latent phases using an artificially generated dataset.
Methods
An artificial dataset of 500 samples was created, and plasma proteomic profiles were generated for each sample using arbitrary values. Sample classification was based on a pathway activation score. Four ML models were tested: support vector machine, random forest, logistic regression, and extreme gradient boosting. Each model was trained across a range of hyperparameters.
Results
Logistic regression achieved the best performance, with an accuracy of 0.73, precision of 0.73, and F1-score of 0.73.
Conclusions
This simulation study showed that synthetic proteomic datasets can be used to evaluate ML approaches for distinguishing active and latent phases of retinal dystrophies when real data are scarce. Synthetic data can support the creation of targeted datasets for proteins associated with retinal dystrophies, helping to address the limited availability of suitable open-source data.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- MAGI'S LAB, Rovereto (TN), Italy.
- MAGI'S LAB, Rovereto (TN), Italy. gabriele.bonetti@ assomagi.org.
- Department of Pharmaceutical Sciences, University of Perugia, Perugia, Italy. gabriele.bonetti@ assomagi.org.
- MAGI EUREGIO, Bolzano, Italy.
- Università Cattolica del Sacro Cuore, Fondazione Policlinico Universitario A. Gemelli-IRCCS, Roma, Italy.
- Università Cattolica del Sacro Cuore, Istituto di Medicina Genomica, Fondazione Policlinico Universitario A. Gemelli-IRCCS, UOC Genetica Medica, Roma, Italy.
Förderung
- Provincia Autonoma di Trento in the scope of LP
Zitieren
APA
Macchia, A., Medori, M. C., Abidin, A. J., Bonetti, G., Dhuli, K., Ferrari, L., Feizyab, S., Miertuš, J., Falsini, B., Placidi, G., Chiurazzi, P., Gordani, O., Dhamo, X., Kalluci, E., Vešelényiová, D., Miertuš, S., Luptáková, I. D., Pospíchal, J., Gregorini, M., & Bertelli, M. (2026). Machine Learning–Based Classification of Active and Latent Phases of Inherited Retinal Dystrophies Using Synthetic Proteomic Data: A Pathway-Based Application Exercise. Healthcare Informatics Research, 32(3), 285-292. https://doi.org/10.4258/hir.2026.32.3.285
Vancouver
Macchia A, Medori MC, Abidin AJ, Bonetti G, Dhuli K, Ferrari L, et al. Machine Learning–Based Classification of Active and Latent Phases of Inherited Retinal Dystrophies Using Synthetic Proteomic Data: A Pathway-Based Application Exercise. Healthcare Informatics Research. 2026;32(3):285-292. doi:10.4258/hir.2026.32.3.285
BibTeX
@article{Macchia2026,
author = {Macchia, Alessandro and Medori, Maria Chiara and Abidin, Ahmad Jainul and Bonetti, Gabriele and Dhuli, Kristjana and Ferrari, Luca and Feizyab, Sara and Miertuš, Jan and Falsini, Benedetto and Placidi, Giorgio and Chiurazzi, Pietro and Gordani, Ornela and Dhamo, Xhilda and Kalluci, Eglantina and Vešelényiová, Dominika and Miertuš, Stanislav and Luptáková, Iveta Dirgová and Pospíchal, Jiří and Gregorini, Matteo and Bertelli, Matteo},
title = {Machine Learning–Based Classification of Active and Latent Phases of Inherited Retinal Dystrophies Using Synthetic Proteomic Data: A Pathway-Based Application Exercise},
journal = {Healthcare Informatics Research},
year = {2026},
volume = {32},
number = {3},
pages = {285--292},
doi = {10.4258/hir.2026.32.3.285}
}
EUVIMED