EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Machine Learning Applied to Visual Fields of Dominant Optic Atrophy Patients

Catarina P Coutinho, Ferdinando Zanchetta, Michele Carbonelli, Marco Battista, Alice Galzignato, Chiara La Morgia, Giulia Amore, Martina Romagnoli, Giacomo Savini, Luigi Brotto, Paolo Nucci, Leonardo Caporali und 5 weitere

Translational Vision Science & Technology · 10.06.2025 · 14 (6) · 20

DOI: 10.1167/tvst.14.6.20 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Translational Vision Science & Technology, erschienen am 10.06.2025. Verfasst von Catarina P Coutinho und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pharmacy and Biotechnology, University of Bologna, Bologna, Italy. Hauptthemen laut MEDLINE: Visual Fields, Machine Learning, Optic Atrophy, Autosomal Dominant. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Identification and quantification of characteristic visual field (VF) patterns in patients with dominant optic atrophy (DOA) using the archetypal analysis (AA) machine learning algorithm.

Methods

In this retrospective study, we collected 30-2 or 24-2 VFs performed with Humphrey Visual Field analyzer from 144 patients (280 eyes) affected by molecularly confirmed DOA carrying OPA1 heterozygous mutation. The VFs were randomly separated into a training set (224 VFs, 80%) and test set (56 VFs, 20%). An AA model was developed by decomposing the VFs of the training set into archetypes (ATs). Spearman correlations were calculated between ATs' weights and mean deviation (MD) and visual acuity (VA). Statistical comparison was performed between ATs weights according to mutation subtype groups.

Results

The DOA-AA model was composed of eight ATs with a high performance in the test set (R2 = 0.88). According to the Ocular Hypertension Treatment Study (OHTS) classification, the central/ceco-central scotoma resembling ATs presented the highest weights (24%) followed by superior defects (13%). ATs with more abnormal VF resembling defects correlated most with MD (AT5-8), whereas only the total loss AT7 with VA (P value < 0.01). Subtype mutations linked with worse clinical features had statistically significantly higher weights for worse ATs (AT7, P < 0.001).

Conclusions

The developed AA model allowed the identification and quantification of VF patterns in DOA. Furthermore, a clinical genotype-phenotype association was supported by the comparison of severity at VF AA decomposition. Translational Relevance: AA enables an objective identification of quantifiable visual field defects intrinsic to DOA providing functional details based on genotype.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Visual FieldsMachine LearningOptic Atrophy, Autosomal DominantHumansMaleFemaleRetrospective StudiesAdultMiddle AgedVisual AcuityVisual Field TestsMutationYoung AdultGTP PhosphohydrolasesAged

Substanzen

OPA1 protein, humanGTP Phosphohydrolases

Autor:innen und Institutionen

  • Department of Pharmacy and Biotechnology, University of Bologna, Bologna, Italy.
  • Studio Oculistico d'Azeglio, Bologna, Italy.
  • Department of Biomedical and Neuromotor Sciences, University of Bologna, Bologna, Italy.
  • Department of Ophthalmology, University Vita-Salute, IRCCS Ospedale San Raffaele, Milan, Italy.
  • IRCCS, Istituto delle Scienze Neurologiche, Programma di Neurogenetica, Bologna, Italy.
  • G. B. Bietti Foundation IRCCS, Rome, Italy.

Zitieren

APA

Coutinho, C. P., Zanchetta, F., Carbonelli, M., Battista, M., Galzignato, A., La Morgia, C., Amore, G., Romagnoli, M., Savini, G., Brotto, L., Nucci, P., Caporali, L., Bandello, F., Carelli, V., Cascavilla, M. L., Fioresi, R., & Barboni, P. (2025). Machine Learning Applied to Visual Fields of Dominant Optic Atrophy Patients. Translational Vision Science & Technology, 14(6), 20. https://doi.org/10.1167/tvst.14.6.20

Vancouver

Coutinho CP, Zanchetta F, Carbonelli M, Battista M, Galzignato A, La Morgia C, et al. Machine Learning Applied to Visual Fields of Dominant Optic Atrophy Patients. Translational Vision Science & Technology. 2025;14(6):20. doi:10.1167/tvst.14.6.20

BibTeX
@article{Coutinho2025,
  author = {Coutinho, Catarina P and Zanchetta, Ferdinando and Carbonelli, Michele and Battista, Marco and Galzignato, Alice and La Morgia, Chiara and Amore, Giulia and Romagnoli, Martina and Savini, Giacomo and Brotto, Luigi and Nucci, Paolo and Caporali, Leonardo and Bandello, Francesco and Carelli, Valerio and Cascavilla, Maria Lucia and Fioresi, Rita and Barboni, Piero},
  title = {Machine Learning Applied to Visual Fields of Dominant Optic Atrophy Patients},
  journal = {Translational Vision Science & Technology},
  year = {2025},
  volume = {14},
  number = {6},
  pages = {20},
  doi = {10.1167/tvst.14.6.20}
}
Kostenlos starten →