EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Clinical Prediction of Functional Decline in Multiple Sclerosis Using Volumetry-Based Synthetic Brain Networks

Alin Ciubotaru iD, Alexandra Maștaleru iD, Thomas Gabriel Schreiner iD, Cristiana Filip, Roxana Covali iD, Laura Riscanu iD, Robert-Valentin Bilcu, Laura-Elena Cucu iD, Sofia Alexandra Socolov-Mihaita, Diana Lăcătușu iD, Florina Crivoi, Albert Vamanu und 4 weitere

Life · 11.03.2026 · 16 (3) · 459

DOI: 10.3390/life16030459 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Life, online erschienen am 11.03.2026. Verfasst von Alin Ciubotaru und 15 weiteren Autor:innen. Beteiligte Einrichtung: Grigore T. Popa University of Medicine and Pharmacy, 700115 Iasi, Romania. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Disability progression in multiple sclerosis (MS) is increasingly recognized as a consequence of large-scale brain network disruption rather than isolated regional damage. Although diffusion tensor imaging (DTI) is the reference method for assessing structural connectivity, its limited availability restricts widespread clinical application. There is therefore a critical need for alternative approaches capable of capturing network-level alterations using routinely acquired MRI data.

Objective

This study aimed to determine whether synthetic structural connectivity matrices derived from standard regional volumetric MRI can capture clinically meaningful network alterations in MS and predict subsequent functional progression, particularly upper limb decline.

Methods

Regional brain volumetry was obtained from routine T1-weighted MRI using an automated, clinically approved volumetric pipeline. Synthetic structural connectivity matrices were generated by integrating principles of structural covariance, distance-dependent connectivity, and disease-specific vulnerability patterns. Graph-theoretical network metrics were extracted to characterize global and regional topology. Machine learning models including logistic regression, support vector machines, random forests, and gradient boosting were trained to predict clinical progression defined by worsening on the 9-Hole Peg Test. Dimensionality reduction was performed using principal component analysis, and model performance was evaluated using balanced accuracy, AUC-ROC, and resampling-based validation. Feature importance analyses were conducted to identify network vulnerability patterns.

Results

Synthetic connectivity networks exhibited biologically plausible properties, including preserved but attenuated small-world organization. Global efficiency showed a strong inverse correlation with disability severity (EDSS). Patients with clinical progression demonstrated marked reductions in network integration and segregation, alongside increased characteristic path length. Machine learning models achieved robust prediction of upper limb functional decline, with ensemble-based methods performing best (balanced accuracy > 80%, AUC-ROC up to 0.85). A limited subset of connections accounted for a disproportionate share of predictive power, predominantly involving frontoparietal associative networks, thalamocortical pathways, and inter-hemispheric connections. In a longitudinal subset, network-level alterations preceded measurable clinical deterioration by several months.

Conclusions

Synthetic structural connectivity derived from routine volumetric MRI captures clinically relevant network-level disruption in multiple sclerosis and enables accurate prediction of functional progression. By bridging network neuroscience with widely accessible imaging data, this framework provides a pragmatic alternative for connectomic analysis when diffusion imaging is unavailable and supports a network-based understanding of disease evolution in MS.

Schlagwörter

Stichwörter der Autor:innen

clinical progressiondisability severityinter-hemispheric connectionsmachine learning modelsnetwork vulnerability

Autor:innen und Institutionen

  • Grigore T. Popa University of Medicine and Pharmacy, 700115 Iasi, Romania.
  • Neurology Clinic, "N. Oblu" Clinical Emergency Hospital, 700309 Iasi, Romania.
  • Department of Radiology, Biomedical Engineering Faculty, Grigore T. Popa University of Medicine and Pharmacy, 700115 Iasi, Romania.
  • Department of Morphofunctional Sciences, Grigore T. Popa University of Medicine and Pharmacy, 700115 Iasi, Romania.
  • Doctoral School, Grigore T. Popa University of Medicine and Pharmacy, 700115 Iasi, Romania.
  • Doctoral School, Carol Davila University of Medicine and Pharmacy, 020021 Bucharest, Romania.

ORCID-Profile: Alin Ciubotaru, Alexandra Maștaleru, Thomas Gabriel Schreiner, Roxana Covali, Laura Riscanu, Laura-Elena Cucu, Diana Lăcătușu, Romica Sebastian Cozma

Zitieren

APA

Ciubotaru, A., Maștaleru, A., Schreiner, T. G., Filip, C., Covali, R., Riscanu, L., Bilcu, R. V., Cucu, L. E., Socolov-Mihaita, S. A., Lăcătușu, D., Crivoi, F., Vamanu, A., Martu, I., Dima-Cozma, L. C., Cozma, R. S., & Bitere-Popa, O. R. (2026). Clinical Prediction of Functional Decline in Multiple Sclerosis Using Volumetry-Based Synthetic Brain Networks. Life, 16(3), 459. https://doi.org/10.3390/life16030459

Vancouver

Ciubotaru A, Maștaleru A, Schreiner TG, Filip C, Covali R, Riscanu L, et al. Clinical Prediction of Functional Decline in Multiple Sclerosis Using Volumetry-Based Synthetic Brain Networks. Life. 2026;16(3):459. doi:10.3390/life16030459

BibTeX
@article{Ciubotaru2026,
  author = {Ciubotaru, Alin and Maștaleru, Alexandra and Schreiner, Thomas Gabriel and Filip, Cristiana and Covali, Roxana and Riscanu, Laura and Bilcu, Robert-Valentin and Cucu, Laura-Elena and Socolov-Mihaita, Sofia Alexandra and Lăcătușu, Diana and Crivoi, Florina and Vamanu, Albert and Martu, Ioana and Dima-Cozma, Lucia Corina and Cozma, Romica Sebastian and Bitere-Popa, Oana-Roxana},
  title = {Clinical Prediction of Functional Decline in Multiple Sclerosis Using Volumetry-Based Synthetic Brain Networks},
  journal = {Life},
  year = {2026},
  volume = {16},
  number = {3},
  pages = {459},
  doi = {10.3390/life16030459}
}
Kostenlos starten →