Stroke, Ischemic
Conditions
Keywords
Artificial Intelligence, Large Vessel Occlusion
Brief summary
The objective of this study is to evaluate the impact of Viz LVO in hospital systems with non-interventional and interventional (spoke and hub) stroke centers on the timing and outcomes of patients with suspected acute ischemic stroke indicated for mechanical thrombectomy.
Detailed description
This is a multi-center, non-randomized observational study of acute ischemic stroke patients whose CTA scans are analyzed by Viz LVO to support clinicians in making stroke triage decisions,. The study results will be compared to a cohort from enrolling centers prior to Viz LVO implementation that will serve as a historical control. Data will be collected retrospectively from the time of presentation through 90 days post discharge. The study will include patients undergoing imaging for a suspected LVO acute ischemic stroke. The post-Viz LVO intervention group will consist of patients who either presented to or underwent transfer to an interventional center, from a non-interventional center, following image analysis by Viz LVO. Data will be collected retrospectively on consecutive patients meeting eligibility criteria from the date of implementation up to 5 years post implementation. The control group will consist of patients who either presented to or underwent transfer to an interventional center, from a non-interventional center, for evaluation prior to the implementation of Viz LVO. Data will be collected on consecutive patients from one day prior to implementation, back as far as 2 years prior to implementation
Interventions
DEVICEViz LVO (De Novo Number DEN170073)
Viz LVO is a notification-only, parallel workflow tool for use by hospital networks and trained clinicians to identify and communicate images of specific patients to a specialist, independent of standard of care workflow. Viz LVO uses an artificial intelligence algorithm to analyze images for findings suggestive of a pre-specified clinical condition and to notify an appropriate medical specialist of these findings in parallel to standard of care image interpretation. Identification of suspected findings is not for diagnostic use beyond notification. Specifically, the device analyzes CT angiogram images of the brain acquired in the acute setting and sends notifications to a neurovascular specialist that a suspected large vessel occlusion has been identified and recommends review of those images. Images can be previewed through a mobile application.
No Intervention was performed for the pre-Viz group. Record review to establish operational metrics only occurred.
Sponsors
Viz.ai, Inc.
Study design
Observational model
CASE_CONTROL
Time perspective
RETROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* Age of 18 years or greater * Signs and symptoms consistent with the diagnosis of a large vessel occlusive stroke * Pre-treatment National Institutes of Health Stroke Scale (NIHSS) ≥ 6 * Aspects Score ≥6 * Patient must have a suspected LVO in M1. * Patient with an intention to treat with mechanical thrombectomy with confirmation of LVO by the CT/CTA radiographic report with the reading diagnosis.
Exclusion criteria
* Unable to undergo a brain imaging (i.e. severe contrast medium allergy, claustrophobia)
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Transfer patients: Time from spoke CT/CTA to door-out | up to 1 day (1440 minutes) | Time in minutes from CT/CTA imaging to time leaving the spoke center |
| Non-transfer patients: Time from Hub door to groin puncture | up to 1 day (1440 minutes) | Time in minutes from arrival a hub center to start time of treatment |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Time from Spoke CT/CTA to Groin Puncture | up to 1 day (1440 minutes) | Time in minutes from CT/CTA imaging to start time of treatment |
| Time from Spoke Door to Groin Puncture | up to 1 day (1440 minutes) | Time in minutes from departure to hub hospital to start time of treatment |
| Length of ICU Stay/Total Length of Stay | Hospital admit to discharge, up to 30 days | Number of days in hospital in the ICU and the total number of days in hospital |
| Time from Spoke Door-In to Door-Out (DIDO) | up to 1 day (1440 minutes) | Time in minutes from arrival at spoke hospital to departure to hub hospital |
| National Institutes of Health Stroke Scale (NIHSS) at Discharge | On date of discharge, up to 30 days | The National Institutes of Health Stroke Scale (NIHSS) is a 15-item neurologic examination stroke scale used to evaluate the effect of acute cerebral infarction on the levels of consciousness, language, neglect, visual-field loss, extraocular movement, motor strength, ataxia, dysarthria, and sensory loss. A trained observer rates the patent's ability to answer questions and perform activities. Ratings for each item are scored on a 3- to 5-point scale, with 0 as normal, and there is an allowance for untestable items. Scores range from 0 to 42, with higher scores indicating greater severity. |
| Patient Disposition at Discharge and 90 Days | 90 days | Data will be collected on whether or not the patient was discharged to their home or another type of care facility, and where they are located 90 days post hospital discharge |
| Modified Rankin Scale (mRS) at Discharge and 90 Days | 90 days | The Modified Rankin Score (mRS) is a 6 point disability scale with possible scores ranging from 0 to 5. A separate category of 6 is usually added for patients who expire. A score of 0 is a patient with no residual symptoms. Scores increase with severity to 5 which equals severe disability. |
| Time from Spoke CT/CTA to Specialist Notification | up to 1 day (1440 minutes) | Time in minutes from CT/CTA imaging to time an interventionalist was notified |
Countries
United States
Outcome results
None listed