Impact of an automated large vessel occlusion detection tool on clinical workflow and patient outcomes
PurposeAutomated large vessel occlusion (LVO) tools allow for prompt identification of positive LVO cases, but little is known about their role in acute stroke triage when implemented in a real-world setting. The purpose of this study was to evaluate the automated LVO detection tool’s impact on acut...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-05-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2023.1179250/full |
| _version_ | 1827941628348727296 |
|---|---|
| author | Jennifer E. Soun Anna Zolyan Joel McLouth Sebastian Elstrott Masaki Nagamine Conan Liang Farideh H. Dehkordi-Vakil Eleanor Chu David Floriolli Edward Kuoy John Joseph Nadine Abi-Jaoudeh Peter D. Chang Peter D. Chang Wengui Yu Daniel S. Chow Daniel S. Chow |
| author_facet | Jennifer E. Soun Anna Zolyan Joel McLouth Sebastian Elstrott Masaki Nagamine Conan Liang Farideh H. Dehkordi-Vakil Eleanor Chu David Floriolli Edward Kuoy John Joseph Nadine Abi-Jaoudeh Peter D. Chang Peter D. Chang Wengui Yu Daniel S. Chow Daniel S. Chow |
| author_sort | Jennifer E. Soun |
| collection | DOAJ |
| description | PurposeAutomated large vessel occlusion (LVO) tools allow for prompt identification of positive LVO cases, but little is known about their role in acute stroke triage when implemented in a real-world setting. The purpose of this study was to evaluate the automated LVO detection tool’s impact on acute stroke workflow and clinical outcomes.Materials and methodsConsecutive patients with a computed tomography angiography (CTA) presenting with suspected acute ischemic stroke were compared before and after the implementation of an AI tool, RAPID LVO (RAPID 4.9, iSchemaView, Menlo Park, CA). Radiology CTA report turnaround times (TAT), door-to-treatment times, and the NIH stroke scale (NIHSS) after treatment were evaluated.ResultsA total of 439 cases in the pre-AI group and 321 cases in the post-AI group were included, with 62 (14.12%) and 43 (13.40%) cases, respectively, receiving acute therapies. The AI tool demonstrated a sensitivity of 0.96, a specificity of 0.85, a negative predictive value of 0.99, and a positive predictive value of 0.53. Radiology CTA report TAT significantly improved post-AI (mean 30.58 min for pre-AI vs. 22 min for post-AI, p < 0.0005), notably at the resident level (p < 0.0003) but not at higher levels of expertise. There were no differences in door-to-treatment times, but the NIHSS at discharge was improved for the pre-AI group adjusted for confounders (parameter estimate = 3.97, p < 0.01).ConclusionImplementation of an automated LVO detection tool improved radiology TAT but did not translate to improved stroke metrics and outcomes in a real-world setting. |
| first_indexed | 2024-03-13T09:41:36Z |
| format | Article |
| id | doaj.art-7a1ab3e448cf4cf696da1ba9b5e8a8bf |
| institution | Directory Open Access Journal |
| issn | 1664-2295 |
| language | English |
| last_indexed | 2024-03-13T09:41:36Z |
| publishDate | 2023-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj.art-7a1ab3e448cf4cf696da1ba9b5e8a8bf2023-05-25T04:24:55ZengFrontiers Media S.A.Frontiers in Neurology1664-22952023-05-011410.3389/fneur.2023.11792501179250Impact of an automated large vessel occlusion detection tool on clinical workflow and patient outcomesJennifer E. Soun0Anna Zolyan1Joel McLouth2Sebastian Elstrott3Masaki Nagamine4Conan Liang5Farideh H. Dehkordi-Vakil6Eleanor Chu7David Floriolli8Edward Kuoy9John Joseph10Nadine Abi-Jaoudeh11Peter D. Chang12Peter D. Chang13Wengui Yu14Daniel S. Chow15Daniel S. Chow16Department of Radiological Sciences, University of California, Irvine, Orange, CA, United StatesDepartment of Neurology, University of California, Irvine, Orange, CA, United StatesDepartment of Radiological Sciences, University of California, Irvine, Orange, CA, United StatesDepartment of Radiological Sciences, University of California, Irvine, Orange, CA, United StatesDepartment of Neurology, University of California, Irvine, Orange, CA, United StatesDepartment of Radiological Sciences, University of California, Irvine, Orange, CA, United StatesCenter for Statistical Consulting, School of Medicine, University of California, Irvine, Irvine, CA, United StatesDepartment of Radiological Sciences, University of California, Irvine, Orange, CA, United StatesDepartment of Radiological Sciences, University of California, Irvine, Orange, CA, United StatesDepartment of Radiological Sciences, University of California, Irvine, Orange, CA, United StatesThe Paul Merage School of Business, School of Medicine, University of California, Irvine, Irvine, CA, United StatesDepartment of Radiological Sciences, University of California, Irvine, Orange, CA, United StatesDepartment of Radiological Sciences, University of California, Irvine, Orange, CA, United StatesCenter for Artificial Intelligence in Diagnostic Medicine, University of California, Irvine, Irvine, CA, United StatesDepartment of Neurology, University of California, Irvine, Orange, CA, United StatesDepartment of Radiological Sciences, University of California, Irvine, Orange, CA, United StatesCenter for Artificial Intelligence in Diagnostic Medicine, University of California, Irvine, Irvine, CA, United StatesPurposeAutomated large vessel occlusion (LVO) tools allow for prompt identification of positive LVO cases, but little is known about their role in acute stroke triage when implemented in a real-world setting. The purpose of this study was to evaluate the automated LVO detection tool’s impact on acute stroke workflow and clinical outcomes.Materials and methodsConsecutive patients with a computed tomography angiography (CTA) presenting with suspected acute ischemic stroke were compared before and after the implementation of an AI tool, RAPID LVO (RAPID 4.9, iSchemaView, Menlo Park, CA). Radiology CTA report turnaround times (TAT), door-to-treatment times, and the NIH stroke scale (NIHSS) after treatment were evaluated.ResultsA total of 439 cases in the pre-AI group and 321 cases in the post-AI group were included, with 62 (14.12%) and 43 (13.40%) cases, respectively, receiving acute therapies. The AI tool demonstrated a sensitivity of 0.96, a specificity of 0.85, a negative predictive value of 0.99, and a positive predictive value of 0.53. Radiology CTA report TAT significantly improved post-AI (mean 30.58 min for pre-AI vs. 22 min for post-AI, p < 0.0005), notably at the resident level (p < 0.0003) but not at higher levels of expertise. There were no differences in door-to-treatment times, but the NIHSS at discharge was improved for the pre-AI group adjusted for confounders (parameter estimate = 3.97, p < 0.01).ConclusionImplementation of an automated LVO detection tool improved radiology TAT but did not translate to improved stroke metrics and outcomes in a real-world setting.https://www.frontiersin.org/articles/10.3389/fneur.2023.1179250/fullartificial intelligencelarge vessel occlusionstrokemachine learningCT angiography |
| spellingShingle | Jennifer E. Soun Anna Zolyan Joel McLouth Sebastian Elstrott Masaki Nagamine Conan Liang Farideh H. Dehkordi-Vakil Eleanor Chu David Floriolli Edward Kuoy John Joseph Nadine Abi-Jaoudeh Peter D. Chang Peter D. Chang Wengui Yu Daniel S. Chow Daniel S. Chow Impact of an automated large vessel occlusion detection tool on clinical workflow and patient outcomes Frontiers in Neurology artificial intelligence large vessel occlusion stroke machine learning CT angiography |
| title | Impact of an automated large vessel occlusion detection tool on clinical workflow and patient outcomes |
| title_full | Impact of an automated large vessel occlusion detection tool on clinical workflow and patient outcomes |
| title_fullStr | Impact of an automated large vessel occlusion detection tool on clinical workflow and patient outcomes |
| title_full_unstemmed | Impact of an automated large vessel occlusion detection tool on clinical workflow and patient outcomes |
| title_short | Impact of an automated large vessel occlusion detection tool on clinical workflow and patient outcomes |
| title_sort | impact of an automated large vessel occlusion detection tool on clinical workflow and patient outcomes |
| topic | artificial intelligence large vessel occlusion stroke machine learning CT angiography |
| url | https://www.frontiersin.org/articles/10.3389/fneur.2023.1179250/full |
| work_keys_str_mv | AT jenniferesoun impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT annazolyan impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT joelmclouth impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT sebastianelstrott impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT masakinagamine impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT conanliang impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT faridehhdehkordivakil impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT eleanorchu impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT davidfloriolli impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT edwardkuoy impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT johnjoseph impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT nadineabijaoudeh impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT peterdchang impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT peterdchang impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT wenguiyu impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT danielschow impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes AT danielschow impactofanautomatedlargevesselocclusiondetectiontoolonclinicalworkflowandpatientoutcomes |