Study Data Show Accuracy of Viz.ai Algorithm for Intracranial Hemorrhage Volume Measurements

Viz.ai is sharing new clinical data validating the accuracy and clinical utility of its artificial intelligence (AI)-powered hyperdensity measurement solution for intracranial hemorrhage (ICH) management. Two independent studies highlight the ability of Viz ICH Plus to accurately and efficiently measure hemorrhage volume, quantify lateral ventricular volume, and estimate midline shift.

“Patients with ICH often require multiple scans in a short timeframe to guide treatment decisions,” said Peter Kan, M.D., professor and chair, Department of Neurosurgery, University of Texas Medical Branch. “Manual measurements can be time-consuming and vary between providers. Viz ICH Plus enables us to assess patients more quickly, identify the most urgent cases, and determine whether intervention is needed—with greater consistency and efficiency.”

The first study, published in Neurosurgery, “Estimation of Ventricular and Intracranial Hemorrhage Volumes and Midline Shift on an External Validation Data Set Using a Convolutional Neural Network Algorithm,”¹ assessed the performance of Viz ICH Plus in quantifying ICH volume, bilateral lateral ventricle (BLV) volume, and midline shift (MLS). The algorithm performed well with low median absolute error in segmenting and quantifying ICH volume, BLV volume, and MLS. Viz ICH Plus achieved up to 92.3% accuracy in identifying clinically meaningful findings on scans.

The second study, published in the Journal of NeuroInterventional Surgery, “Real-World Evaluation of Viz.ai’s Automated Intracranial Hemorrhage Volume Calculation Tool,”² evaluated 139 patients presenting with spontaneous ICH and compared Viz.ai’s automated measurements with traditional mABC/2 estimation. The study indicated Viz.ai was significantly more accurate than mABC/2 (mean volume difference of 4.77±4.06 mL vs. 8.36±9.48 mL, p<0.01) and delivered results nearly three times faster than manual methods.

“Accurate and timely volume estimation is critical for managing patients with ICH, especially in acute and intensive care settings,” Viz.ai Global Clinical Affairs Vice President Molly Madziva Taitt, Ph.D., stated. “These studies reinforce the precision, speed, and reliability of Viz ICH Plus, empowering clinicians with real-time information that can enhance decision-making and contribute to improved patient outcomes.”

Viz.ai is pioneering the use of AI algorithms and machine learning to increase the speed of diagnosis and care across 1,700 U.S. and European hospitals and health systems. The AI-powered Viz.ai One is an intelligent care coordination solution that identifies more patients with a suspected disease, informs critical decisions at the point of care, and optimizes care pathways and helps improve outcomes. Backed by real-world clinical evidence, Viz.ai One delivers significant value to patients, providers, and pharmaceutical and medical device companies.

References
¹ Colasurdo, Marco MD*; Amran, Dor MSc, EE‡; Chen, Huanwen MD§; Ziv, Keren BSc, BE‡; Geron, Michal MD‡; Love, Christopher J. PhD‡; Robledo, Ariadna MD‖; O’Leary, Sean MS‖; Husain, Adam MS‖; Von Waaden, Nicholas MS‖; Garcia, Roberto MD‖; Edhayan, Gautam MD¶; Shaltoni, Hashem MD#; Memon, Muhammad Zeeshan MD#; Kan, Peter MD, MPH‖. Estimation of Ventricular and Intracranial Hemorrhage Volumes and Midline Shift on an External Validation Data Set Using a Convolutional Neural Network Algorithm. Neurosurgery ():10.1227/neu.0000000000003455, April 14, 2025.
² Odland I, Liu KJ, Wu D, Yaeger KA, Ascanio LC, Smith C, Schuldt BR, Young T, Rossitto CP, Downes M, Vasan V, Ali M, Hardigan T, Shigematsu T, Fifi JT, Mocco J, Kellner CP. Real-world evaluation of the accuracy of the Viz.AI automated intracranial hemorrhage volume calculation tool. J Neurointerv Surg. 2025 Jan 19:jnis-2024-022564.