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

Automated Prediction of Proximal Middle Cerebral Artery Occlusions in Noncontrast Brain Computed Tomography

Pyeong Eun Kim, Hyojung Yang, Dongmin Kim iD, Leonard Sunwoo iD, Chi Kyung Kim iD, Beom Joon Kim iD, Joon-Tae Kim iD, Wi-Sun Ryu iD, Ho Sung Kim iD

Stroke · 2024-06 · 55 (6) · 1609-1618

DOI: 10.1161/strokeaha.123.045772 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Stroke, 2024-06. Verfasst von Pyeong Eun Kim und 8 weiteren Autor:innen. Beteiligte Einrichtung: Artificial Intelligence Research Center, JLK Inc, Seoul, Republic of Korea (P.E.K., H.Y., D.K., W.-S.R.). Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Infarction, Middle Cerebral Artery, Computed Tomography Angiography. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Early identification of large vessel occlusion (LVO) in patients with ischemic stroke is crucial for timely interventions. We propose a machine learning–based algorithm (JLK-CTL) that uses handcrafted features from noncontrast computed tomography to predict LVO. METHODS: We included patients with ischemic stroke who underwent concurrent noncontrast computed tomography and computed tomography angiography in seven hospitals. Patients from 5 of these hospitals, admitted between May 2011 and March 2015, were randomly divided into training and internal validation (9:1 ratio). Those from the remaining 2 hospitals, admitted between March 2021 and September 2021, were designated for external validation. From each noncontrast computed tomography scan, we extracted differences in volume, tissue density, and Hounsfield unit distribution between bihemispheric regions (striatocapsular, insula, M1–M3, and M4–M6, modified from the Alberta Stroke Program Early Computed Tomography Score). A deep learning algorithm was used to incorporate clot signs as an additional feature. Machine learning models, including ExtraTrees, random forest, extreme gradient boosting, support vector machine, and multilayer perceptron, as well as a deep learning model, were trained and evaluated. Additionally, we assessed the models’ performance after incorporating the National Institutes of Health Stroke Scale scores as an additional feature. RESULTS: Among 2919 patients, 83 were excluded. Across the training (n=2463), internal validation (n=275), and external validation (n=95) datasets, the mean ages were 68.5±12.4, 67.6±13.8, and 67.9±13.6 years, respectively. The proportions of men were 57%, 53%, and 59%, with LVO prevalences of 17.0%, 16.4%, and 26.3%, respectively. In the external validation, the ExtraTrees model achieved a robust area under the curve of 0.888 (95% CI, 0.850–0.925), with a sensitivity of 80.1% (95% CI, 72.0–88.1) and a specificity of 88.6% (95% CI, 84.7–92.5). Adding the National Institutes of Health Stroke Scale score to the ExtraTrees model increased sensitivity (from 80.1% to 92.1%) while maintaining specificity. CONCLUSIONS: Our algorithm provides reliable predictions of LVO using noncontrast computed tomography. By enabling early LVO identification, our algorithm has the potential to expedite the stroke workflow.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, X-Ray ComputedInfarction, Middle Cerebral ArteryComputed Tomography AngiographyHumansMaleAgedFemaleMiddle AgedMachine LearningAged, 80 and overAlgorithmsIschemic StrokeDeep LearningPredictive Value of Tests

Stichwörter der Autor:innen

artificial intelligenceatrial fibrillationcomputed tomography angiographydeep learningischemic strokepredictive value of tests

Autor:innen und Institutionen

  • Artificial Intelligence Research Center, JLK Inc, Seoul, Republic of Korea (P.E.K., H.Y., D.K., W.-S.R.).
  • Department of Computer Science and Technology, University of Cambridge, United Kingdom (H.Y.).
  • Department of Radiology, Seoul National University College of Medicine, Republic of Korea (L.S.).
  • Department of Radiology (L.S.), Seoul National University Bundang Hospital, Seongnam, Republic of Korea.
  • Department of Neurology, Korea University Guro Hospital, Seoul, Republic of Korea (C.K.K.).
  • Department of Neurology (B.J.K.), Seoul National University Bundang Hospital, Seongnam, Republic of Korea.

ORCID-Profile: Dongmin Kim, Leonard Sunwoo, Chi Kyung Kim, Beom Joon Kim, Joon-Tae Kim, Wi-Sun Ryu, Ho Sung Kim

Zitieren

APA

Kim, P. E., Yang, H., Kim, D., Sunwoo, L., Kim, C. K., Kim, B. J., Kim, J. T., Ryu, W. S., & Kim, H. S. (2024). Automated Prediction of Proximal Middle Cerebral Artery Occlusions in Noncontrast Brain Computed Tomography. Stroke, 55(6), 1609-1618. https://doi.org/10.1161/strokeaha.123.045772

Vancouver

Kim PE, Yang H, Kim D, Sunwoo L, Kim CK, Kim BJ, et al. Automated Prediction of Proximal Middle Cerebral Artery Occlusions in Noncontrast Brain Computed Tomography. Stroke. 2024;55(6):1609-1618. doi:10.1161/strokeaha.123.045772

BibTeX
@article{Kim2024,
  author = {Kim, Pyeong Eun and Yang, Hyojung and Kim, Dongmin and Sunwoo, Leonard and Kim, Chi Kyung and Kim, Beom Joon and Kim, Joon-Tae and Ryu, Wi-Sun and Kim, Ho Sung},
  title = {Automated Prediction of Proximal Middle Cerebral Artery Occlusions in Noncontrast Brain Computed Tomography},
  journal = {Stroke},
  year = {2024},
  volume = {55},
  number = {6},
  pages = {1609--1618},
  doi = {10.1161/strokeaha.123.045772}
}
Kostenlos starten →