EUVIMEDEUVIMED entdecken
Open Access

Association of deep learning-derived temporalis sarcopenia with mortality in acute ischemic stroke

Joshua Ron Onichino iD, Ding Yi Zhang, Miguel Trottier, Lorne Rosenbloom, Jonathan Afilalo iD

The Journals of Gerontology, Series A: Biological Sciences and Medical Sciences · 06.06.2026 · 81 (7)

DOI: 10.1093/gerona/glag149 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journals of Gerontology, Series A: Biological Sciences and Medical Sciences, online erschienen am 03.06.2026. Verfasst von Joshua Ron Onichino und 4 weiteren Autor:innen. Beteiligte Einrichtung: Center for Clinical Epidemiology, Lady Davis Institute for Medical Research, McGill University, Montreal, Quebec, Canada. Hauptthemen laut MEDLINE: Deep Learning, Sarcopenia, Ischemic Stroke, Predictive Learning Models. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: McGill University Faculty of Medicine and Health Sciences, CIHR, Canadian Institutes of Health Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Sarcopenia is associated with mortality following acute ischemic stroke (AIS), but diagnosis is time-consuming. Computed tomography (CT) measures of temporal muscle volume (TMV) and density (TMD) can be automatically extracted from existing scans using deep learning (DL). This study sought to demonstrate the incremental value of DL-derived TMV and TMD from CT scans on AIS mortality and length of stay (LOS).

Methods

In this retrospective, single-center cohort study, consecutive AIS patients admitted from 2014 to 2023 were included. TMV and TMD were quantified on admission CT scans by a novel DL model and represented as continuous or categorical variables. Patients were classified as non-sarcopenic, pre-sarcopenic (low TMV or TMD), or sarcopenic (low TMV and TMD) using 5th-percentile thresholds derived from 50 healthy adults. The primary outcome was 30-day all-cause mortality. Secondary outcomes were 365-day all-cause mortality and LOS. Multivariable logistic and linear regression were used.

Results

The cohort consisted of 2285 patients with 1151 (50%) females, and a mean (SD) age of 74.7 (13.7) years. There were 877 (38%) non-sarcopenic, 838 (37%) pre-sarcopenic, and 570 (25%) sarcopenic patients. Adjusted ORs (95% CIs) for 30-day mortality were 2.70 (1.64-4.46) and 2.91 (1.72-4.91) for pre-sarcopenia and sarcopenia. Findings were consistent across secondary outcomes. The association between sarcopenia and mortality was preserved after adding the Hospital Frailty Risk Score (HFRS) to the models. Findings were consistent in sensitivity analyses using cohort-derived threshold definitions.

Conclusions

TMV and TMD extracted using a novel DL model were incrementally predictive of AIS mortality.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSarcopeniaIschemic StrokePredictive Learning ModelsTemporal MuscleRetrospective StudiesHumansMaleFemaleMiddle AgedAgedAged, 80 and overFrailtyFrail ElderlyRisk AssessmentRisk FactorsTomography, X-Ray ComputedBiomarkers

Stichwörter der Autor:innen

Artificial intelligenceBiomarkersBody compositionFrailty

Substanzen

Biomarkers

Autor:innen und Institutionen

  • Center for Clinical Epidemiology, Lady Davis Institute for Medical Research, McGill University, Montreal, Quebec, Canada.
  • Department of Diagnostic Radiology, Faculty of Medicine and Health Sciences, McGill University, Montreal, Quebec, Canada.
  • Department of Medicine, Center hospitalier affilié universitaire régional de Trois-Rivières, CIUSSS de la Mauricie-et-du-Center-du-Quebec, Trois-Rivières, Quebec, Canada.
  • Faculté de Médecine, Université de Montréal, Trois-Rivières, Quebec, Canada.
  • Division of Cardiology, McGill University, Montreal, Quebec, Canada.

ORCID-Profile: Joshua Ron Onichino, Jonathan Afilalo

Förderung

  • McGill University Faculty of Medicine and Health Sciences
  • CIHR
  • Canadian Institutes of Health Research

Zitieren

APA

Onichino, J. R., Zhang, D. Y., Trottier, M., Rosenbloom, L., & Afilalo, J. (2026). Association of deep learning-derived temporalis sarcopenia with mortality in acute ischemic stroke. The Journals of Gerontology, Series A: Biological Sciences and Medical Sciences, 81(7). https://doi.org/10.1093/gerona/glag149

Vancouver

Onichino JR, Zhang DY, Trottier M, Rosenbloom L, Afilalo J. Association of deep learning-derived temporalis sarcopenia with mortality in acute ischemic stroke. The Journals of Gerontology, Series A: Biological Sciences and Medical Sciences. 2026;81(7). doi:10.1093/gerona/glag149

BibTeX
@article{Onichino2026,
  author = {Onichino, Joshua Ron and Zhang, Ding Yi and Trottier, Miguel and Rosenbloom, Lorne and Afilalo, Jonathan},
  title = {Association of deep learning-derived temporalis sarcopenia with mortality in acute ischemic stroke},
  journal = {The Journals of Gerontology, Series A: Biological Sciences and Medical Sciences},
  year = {2026},
  volume = {81},
  number = {7},
  doi = {10.1093/gerona/glag149}
}
Kostenlos starten →