EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY 4.0

Development and internal validation of multimodal machine learning models for predicting eligibility for mechanical thrombectomy in suspected stroke patients using routinely collected clinical and imaging data

Arjun Agarwal, Nirman Bharti, Tamaghna Ghosh, Satish Golla, Navpreet K Bains, Rashi Chamadia, Dennis Robert iD, Preetham Putha, Adnan I Qureshi

PLOS One · 2025

DOI: 10.1371/journal.pone.0334242 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift PLOS One, 2025. Verfasst von Arjun Agarwal und 8 weiteren Autor:innen. Beteiligte Einrichtung: Qure.ai Technologies Private Limited, Mumbai, India. Hauptthemen laut MEDLINE: Machine Learning, Thrombectomy, Stroke, Ischemic Stroke. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Qure.ai Technologies Private Limited.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Mechanical thrombectomy (MT) eligibility for acute ischemic stroke (AIS) patients depends upon clinical and advanced imaging assessments like CT perfusion (CTP). Assessment complexities and limited access to advanced imaging investigations are known challenges. We developed machine-learning models using routinely collected clinical and imaging data to predict MT eligibility.

Methods

Age, National-Institutes-of-Health-Stroke-Scale-Score (NIHSS), last-known-well-time (LKWT), noncontrast-CT (NCCT) scan and CT-angiography (CTA) report from consecutive cohort of 260 AIS-suspected patients treated at a stroke centre during Apr’20 to Dec’23 were retrospectively collected. 160 underwent MT for anterior-circulation large vessel occlusion (LVO a ); rest were MT ineligible. MT eligibility was determined based on clinical and imaging investigations including CTP during routine-care. The dataset was split into train:test sets (50:50 split). A commercially available artificial-intelligence algorithm calculated infarct volume and ASPECT score (ASPECTS q ) from the NCCTs. We developed two supervised models using Gradient-Boosting-Machines. MODEL 1 utilized age, NIHSS, LKWT, ASPECTS q and infarct volume as inputs; MODEL 2 additionally included the presence/absence of LVO a as input. The target/response variable used for our supervised learning methods was whether the patients were MT eligible or not as determined during routine-care. Performance of the models were investigated using the test set.

Results

Among 130 patients (mean age ± standard-deviation: 67.4 ± 14.2 years; 61 males) in test set, 80 (61.5%) were MT eligible; rest were ineligible. The area-under-the-receiver-operating-characteristics-curve, sensitivity and specificity of MODEL 1 were 0.76 (95% CI: 0.67–0.85), 85% (75.6–91.2) and 60% (46.2–72.4), respectively. They were 0.92 (0.88–0.96), 82.5% (72.7–89.3) and 82% (69.2–90.2), respectively, for MODEL 2 .

Conclusions

The models showed promising results, demonstrating that NCCT, potentially with CTA, could be sufficient for MT eligibility determination. Such models can enable faster referrals of patients to higher centers.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningThrombectomyStrokeIschemic StrokeHumansMaleFemaleAgedMiddle AgedRetrospective StudiesComputed Tomography AngiographyAged, 80 and overTomography, X-Ray Computed

Autor:innen und Institutionen

  • Qure.ai Technologies Private Limited, Mumbai, India.
  • Qure.ai Technologies Private Limited, Bangalore, India.
  • Zeenat Qureshi Stroke Institute, St. Cloud, Minnesota, United States of America.
  • University of Missouri, Columbia, United States of America.

ORCID-Profile: Dennis Robert

Förderung

  • Qure.ai Technologies Private Limited

Zitieren

APA

Agarwal, A., Bharti, N., Ghosh, T., Golla, S., Bains, N. K., Chamadia, R., Robert, D., Putha, P., & Qureshi, A. I. (2025). Development and internal validation of multimodal machine learning models for predicting eligibility for mechanical thrombectomy in suspected stroke patients using routinely collected clinical and imaging data. PLOS One. https://doi.org/10.1371/journal.pone.0334242

Vancouver

Agarwal A, Bharti N, Ghosh T, Golla S, Bains NK, Chamadia R, et al. Development and internal validation of multimodal machine learning models for predicting eligibility for mechanical thrombectomy in suspected stroke patients using routinely collected clinical and imaging data. PLOS One. 2025. doi:10.1371/journal.pone.0334242

BibTeX
@article{Agarwal2025,
  author = {Agarwal, Arjun and Bharti, Nirman and Ghosh, Tamaghna and Golla, Satish and Bains, Navpreet K and Chamadia, Rashi and Robert, Dennis and Putha, Preetham and Qureshi, Adnan I},
  title = {Development and internal validation of multimodal machine learning models for predicting eligibility for mechanical thrombectomy in suspected stroke patients using routinely collected clinical and imaging data},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0334242}
}
Kostenlos starten →