Publications by authors named "B Gulek"
Smartphone pupillometry with machine learning differentiates ischemic from hemorrhagic stroke: A pilot study.
J Stroke Cerebrovasc Dis
December 2024
Objectives: Similarities between acute ischemic and hemorrhagic stroke make diagnosis and triage challenging. We studied a smartphone-based quantitative pupillometer for differentiation of acute ischemic and hemorrhagic stroke.
Materials And Methods: Stroke patients were recruited prior to surgical or interventional treatment.
Article Synopsis
- The study assessed how well three radiologists agreed on MRI evaluations for staging and restaging rectal cancer in 239 patients, particularly after neoadjuvant therapy.
- The findings showed moderate to high interobserver agreement on various MRI parameters, with specific focus on tumor distance from the mesorectal fascia and lymph node involvement being significant predictors of locoregional recurrence.
- Ultimately, the analysis highlighted the importance of lymph node restaging and its correlation with locoregional recurrence rates, indicating that changes in lymph node status can influence patient outcomes.
Smartphone pupillometry predicts ischemic penumbra in acute ischemic stroke.
J Stroke Cerebrovasc Dis
January 2025
Background: Recent advances in time-sensitive treatment methods for large vessel occlusion (LVO), including medical and mechanical thrombectomy, have increased the importance of rapid recognition of acute ischemic stroke. The pupillary light reflex (PLR) is a biomarker for neurological status. We studied a portable smartphone-based quantitative pupillometry application that has been developed to quantify PLR metrics without requiring external hardware or extensive training to operate.
View Article and Find Full Text PDFArticle Synopsis
- - The study assessed the interobserver agreement and diagnostic accuracy of the ovarian-adnexal reporting and data system for MRI (O-RADS MRI) through the examination of 471 lesions by three radiologists.
- - The results showed varied agreement levels, specifically lower for O-RADS 4 (67% agreement) and better for O-RADS 5 (71% agreement), with predictive malignancy rates of 74% and 95%, respectively.
- - Machine learning models, particularly the artificial neural network, demonstrated high classification accuracy, suggesting that AI integration could enhance O-RADS MRI effectiveness in future diagnostic protocols.
Smartphone pupillometry for detection of cerebral vasospasm after aneurysmal subarachnoid hemorrhage.
J Stroke Cerebrovasc Dis
October 2024
Objectives: Vasospasm is a complication of aneurysmal subarachnoid hemorrhage (aSAH) that can change the trajectory of recovery and is associated with morbidity and mortality. Earlier detection of vasospasm could improve patient outcomes. Our objective is to evaluate the accuracy of smartphone-based quantitative pupillometry in the detection of radiographic vasospasm and delayed cerebral ischemia (DCI) after aSAH.
View Article and Find Full Text PDF