Automated detection of intracranial large vessel occlusions using Viz.ai software: Experience in a large, integrated stroke network
Abstract Background and purpose Endovascular thrombectomy is an evidence‐based treatment for large vessel occlusion (LVO) stroke. Commercially available artificial intelligence has been designed to detect the presence of an LVO on computed tomography angiogram (CTA). We compared Viz.ai‐LVO (San Fran...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-01-01
|
| Series: | Brain and Behavior |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/brb3.2808 |
| _version_ | 1797893707388682240 |
|---|---|
| author | Rahul R. Karamchandani Anna Maria Helms Sagar Satyanarayana Hongmei Yang Jonathan D. Clemente Gary Defilipp Dale Strong Jeremy B. Rhoten Andrew W. Asimos |
| author_facet | Rahul R. Karamchandani Anna Maria Helms Sagar Satyanarayana Hongmei Yang Jonathan D. Clemente Gary Defilipp Dale Strong Jeremy B. Rhoten Andrew W. Asimos |
| author_sort | Rahul R. Karamchandani |
| collection | DOAJ |
| description | Abstract Background and purpose Endovascular thrombectomy is an evidence‐based treatment for large vessel occlusion (LVO) stroke. Commercially available artificial intelligence has been designed to detect the presence of an LVO on computed tomography angiogram (CTA). We compared Viz.ai‐LVO (San Francisco, CA, USA) to CTA interpretation by board‐certified neuroradiologists (NRs) in a large, integrated stroke network. Methods From January 2021 to December 2021, we compared Viz.ai detection of an internal carotid artery (ICA) or middle cerebral artery first segment (MCA‐M1) occlusion to the gold standard of CTA interpretation by board‐certified NRs for all code stroke CTAs. On a monthly basis, sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) were calculated. Trend analyses were conducted to evaluate for any improvement of LVO detection by the software over time. Results 3851 patients met study inclusion criteria, of whom 220 (5.7%) had an ICA or MCA‐M1 occlusion per NR. Sensitivity and specificity were 78.2% (95% CI 72%–83%) and 97% (95% CI 96%–98%), respectively. PPV was 61% (95% CI 55%–67%), NPV 99% (95% CI 98%–99%), and accuracy was 95.9% (95% CI 95.3%–96.5%). Neither specificity or sensitivity improved over time in the trend analysis. Conclusions Viz.ai‐LVO has high specificity and moderately high sensitivity to detect an ICA or proximal MCA occlusion. The software has the potential to streamline code stroke workflows and may be particularly impactful when emergency access to NRs or vascular neurologists is limited. |
| first_indexed | 2024-04-10T06:57:10Z |
| format | Article |
| id | doaj.art-750856aee6504a62a71ef9f3b4c8be3d |
| institution | Directory Open Access Journal |
| issn | 2162-3279 |
| language | English |
| last_indexed | 2024-04-10T06:57:10Z |
| publishDate | 2023-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Brain and Behavior |
| spelling | doaj.art-750856aee6504a62a71ef9f3b4c8be3d2023-02-28T07:01:06ZengWileyBrain and Behavior2162-32792023-01-01131n/an/a10.1002/brb3.2808Automated detection of intracranial large vessel occlusions using Viz.ai software: Experience in a large, integrated stroke networkRahul R. Karamchandani0Anna Maria Helms1Sagar Satyanarayana2Hongmei Yang3Jonathan D. Clemente4Gary Defilipp5Dale Strong6Jeremy B. Rhoten7Andrew W. Asimos8Neurology, Neurosciences Institute Atrium Health Charlotte North Carolina USANeurosciences Institute Atrium Health Charlotte North Carolina USAInformation and Analytics Services Atrium Health Charlotte North Carolina USAInformation and Analytics Services Atrium Health Charlotte North Carolina USACharlotte Radiology, Neurosciences Institute Atrium Health Charlotte North Carolina USACharlotte Radiology, Neurosciences Institute Atrium Health Charlotte North Carolina USAInformation and Analytics Services Atrium Health Charlotte North Carolina USANeurosciences Institute Atrium Health Charlotte North Carolina USAEmergency Medicine, Neurosciences Institute Atrium Health Charlotte North Carolina USAAbstract Background and purpose Endovascular thrombectomy is an evidence‐based treatment for large vessel occlusion (LVO) stroke. Commercially available artificial intelligence has been designed to detect the presence of an LVO on computed tomography angiogram (CTA). We compared Viz.ai‐LVO (San Francisco, CA, USA) to CTA interpretation by board‐certified neuroradiologists (NRs) in a large, integrated stroke network. Methods From January 2021 to December 2021, we compared Viz.ai detection of an internal carotid artery (ICA) or middle cerebral artery first segment (MCA‐M1) occlusion to the gold standard of CTA interpretation by board‐certified NRs for all code stroke CTAs. On a monthly basis, sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) were calculated. Trend analyses were conducted to evaluate for any improvement of LVO detection by the software over time. Results 3851 patients met study inclusion criteria, of whom 220 (5.7%) had an ICA or MCA‐M1 occlusion per NR. Sensitivity and specificity were 78.2% (95% CI 72%–83%) and 97% (95% CI 96%–98%), respectively. PPV was 61% (95% CI 55%–67%), NPV 99% (95% CI 98%–99%), and accuracy was 95.9% (95% CI 95.3%–96.5%). Neither specificity or sensitivity improved over time in the trend analysis. Conclusions Viz.ai‐LVO has high specificity and moderately high sensitivity to detect an ICA or proximal MCA occlusion. The software has the potential to streamline code stroke workflows and may be particularly impactful when emergency access to NRs or vascular neurologists is limited.https://doi.org/10.1002/brb3.2808artificial intelligencelarge vessel occlusionViz.ai |
| spellingShingle | Rahul R. Karamchandani Anna Maria Helms Sagar Satyanarayana Hongmei Yang Jonathan D. Clemente Gary Defilipp Dale Strong Jeremy B. Rhoten Andrew W. Asimos Automated detection of intracranial large vessel occlusions using Viz.ai software: Experience in a large, integrated stroke network Brain and Behavior artificial intelligence large vessel occlusion Viz.ai |
| title | Automated detection of intracranial large vessel occlusions using Viz.ai software: Experience in a large, integrated stroke network |
| title_full | Automated detection of intracranial large vessel occlusions using Viz.ai software: Experience in a large, integrated stroke network |
| title_fullStr | Automated detection of intracranial large vessel occlusions using Viz.ai software: Experience in a large, integrated stroke network |
| title_full_unstemmed | Automated detection of intracranial large vessel occlusions using Viz.ai software: Experience in a large, integrated stroke network |
| title_short | Automated detection of intracranial large vessel occlusions using Viz.ai software: Experience in a large, integrated stroke network |
| title_sort | automated detection of intracranial large vessel occlusions using viz ai software experience in a large integrated stroke network |
| topic | artificial intelligence large vessel occlusion Viz.ai |
| url | https://doi.org/10.1002/brb3.2808 |
| work_keys_str_mv | AT rahulrkaramchandani automateddetectionofintracraniallargevesselocclusionsusingvizaisoftwareexperienceinalargeintegratedstrokenetwork AT annamariahelms automateddetectionofintracraniallargevesselocclusionsusingvizaisoftwareexperienceinalargeintegratedstrokenetwork AT sagarsatyanarayana automateddetectionofintracraniallargevesselocclusionsusingvizaisoftwareexperienceinalargeintegratedstrokenetwork AT hongmeiyang automateddetectionofintracraniallargevesselocclusionsusingvizaisoftwareexperienceinalargeintegratedstrokenetwork AT jonathandclemente automateddetectionofintracraniallargevesselocclusionsusingvizaisoftwareexperienceinalargeintegratedstrokenetwork AT garydefilipp automateddetectionofintracraniallargevesselocclusionsusingvizaisoftwareexperienceinalargeintegratedstrokenetwork AT dalestrong automateddetectionofintracraniallargevesselocclusionsusingvizaisoftwareexperienceinalargeintegratedstrokenetwork AT jeremybrhoten automateddetectionofintracraniallargevesselocclusionsusingvizaisoftwareexperienceinalargeintegratedstrokenetwork AT andrewwasimos automateddetectionofintracraniallargevesselocclusionsusingvizaisoftwareexperienceinalargeintegratedstrokenetwork |