Real-World Experience with Artificial Intelligence-Based Triage in Transferred Large Vessel Occlusion Stroke Patients

Background and Purpose: Randomized controlled trials have demonstrated the importance of time to endovascular therapy (EVT) in clinical outcomes in large vessel occlusion (LVO) acute ischemic stroke. Delays to treatment are particularly prevalent when patients require a transfer from hospitals without EVT capability onsite. A computer-aided triage system, Viz LVO, has the potential to streamline workflows. This platform includes an image viewer, a communication system, and an artificial intelligence (AI) algorithm that automatically identifies suspected LVO strokes on CTA imaging and rapidly triggers alerts. We hypothesize that the Viz application will decrease time-to-treatment, leading to improved clinical outcomes. Methods: A retrospective analysis of a prospectively maintained database was assessed for patients who presented to a stroke center currently utilizing Viz LVO and underwent EVT following transfer for LVO stroke between July 2018 and March 2020. Time intervals and clinical outcomes were compared for 55 patients divided into pre- and post-Viz cohorts. Results: The median initial door-to-neuroendovascular team (NT) notification time interval was significantly faster (25.0 min [IQR = 12.0] vs. 40.0 min [IQR = 61.0]; p = 0.01) with less variation (p < 0.05) following Viz LVO implementation. The median initial door-to-skin puncture time interval was 25 min shorter in the post-Viz cohort, although this was not statistically significant (p = 0.15). Conclusions: Preliminary results have shown that Viz LVO implementation is associated with earlier, more consistent NT notification times. This application can serve as an early warning system and a failsafe to ensure that no LVO is left behind.

Download Full-text

Abstract P129: Initial Real-World Experience With Viz LVO in Transferred Large Vessel Occlusion Stroke Patients

Stroke ◽

10.1161/str.52.suppl_1.p129 ◽

2021 ◽

Vol 52 (Suppl_1) ◽

Author(s):

Jacob Morey ◽

Xiangnan Zhang ◽

Kurt Yaeger ◽

Emily Fiano ◽

Naoum Fares Marayati ◽

...

Keyword(s):

New York ◽

Warning System ◽

Large Vessel ◽

Time Interval ◽

Large Vessel Occlusion ◽

Time Intervals ◽

Vessel Occlusion ◽

Left Behind ◽

Time Period ◽

Stroke Center

Background and Purpose: Randomized controlled trials have demonstrated the importance of time to endovascular therapy (EVT) on clinical outcomes in large vessel occlusion (LVO) acute ischemic stroke. Delays to treatment are particularly prevalent when patients require a transfer from hospitals without EVT capability onsite. A novel computer aided triage system, Viz LVO, has the potential to streamline workflows. This platform includes an image viewer, communication system, and an artificial intelligence (AI) algorithm that automatically identifies suspected LVO strokes on CTA imaging and rapidly triggers alerts. We hypothesize that the Viz application will decrease time-to-treatment. Methods: A prospective database was assessed for patients who presented to a stroke center utilizing Viz LVO in the Mount Sinai Health System in New York and underwent EVT following transfer for LVO stroke between July 2018 and March 2020. This time period was chosen due to the COVID-19 pandemic affecting stroke workflow after March 2020. Time intervals were compared for 55 patients divided into Pre- and Post-Viz cohorts. Results: The median initial door-to-neuroendovascular team (NT) notification time interval was significantly faster (25.0 minutes [IQR=12.0] vs 40.0 minutes [IQR=61.0]; p=0.01) with significantly less variation (p<0.05). The median initial door-to-skin puncture time interval was 25 minutes shorter in the Post-Viz cohort, although not statistically significant (p=0.15). Post Viz LVO implementation, the Viz notification was the first NT notification 38% (10/26) of the time. Conclusions: Our preliminary results have shown that Viz LVO implementation is associated with earlier, more consistent NT notification times and potentially treatment times. This platform presents a novel application of AI that can serve as an early warning system and a failsafe to ensure that no LVO is left behind. Further studies are warranted.

Download Full-text

Impact of Viz LVO on Time-to-Treatment and Clinical Outcomes in Large Vessel Occlusion Stroke Patients Presenting to Primary Stroke Centers

10.1101/2020.07.02.20143834 ◽

2020 ◽

Author(s):

Jacob R. Morey ◽

Emily Fiano ◽

Kurt A. Yaeger ◽

Xiangnan Zhang ◽

Johanna T. Fifi

Keyword(s):

New York ◽

Clinical Outcomes ◽

Large Vessel ◽

Similar Proportion ◽

Time Interval ◽

Large Vessel Occlusion ◽

Vessel Occlusion ◽

Time To Treatment ◽

Comprehensive Stroke Center ◽

Stroke Center

AbstractIntroductionRandomized controlled trials have demonstrated the importance of time-to-treatment on clinical outcomes in large vessel occlusion (LVO) stroke. Delays in interventional radiology (INR) consultation are associated with a significant delay in overall time to endovascular treatment (EVT). Delays in EVT are particularly prevalent in Primary Stroke Centers (PSC), hospitals without thrombectomy capability onsite, where the patient requires transfer to a Thrombectomy Capable or Comprehensive Stroke Center for EVT. A novel computer aided triage system, Viz LVO, assists in early notification of the PSC stroke team and affiliated INR team. This platform includes an image viewer, communication system, and an artificial intelligence algorithm that automatically identifies suspected LVO strokes on CTA imaging and rapidly triggers alerts.HypothesisViz LVO will decrease time-to-treatment and improve clinical outcomes.MethodsA prospectively maintained database was assessed for all patients who presented to a PSC currently utilizing Viz LVO in the Mount Sinai Health System in New York and underwent EVT following transfer for LVO stroke between October 1, 2018 and March 15, 2020. There were 42 patients who fit the inclusion criteria and divided into pre- and post-Viz ContaCT implementation by comparing the periods of October 1, 2018, to March 15, 2019, “Pre-Viz”, and October 1, 2019, to March 15, 2020, “Post-Viz.” Time intervals and clinical outcomes were collected and compared.ResultsThe Pre- and Post-Viz cohorts were similar in terms of gender, age, proportion receiving IV-tPA, and proportion with revascularization of TICI > 2B. The presenting NIHSS and pre-stroke mRS scores were not statistically different.The median initial door-to-INR notification was significantly faster in the post-Viz cohort (21.5 minutes vs 36 minutes; p=0.02). The median initial door-to-puncture time interval was 20 minutes shorter in the Post-Viz cohort, but this was not statistically significant (p=0.20).The 5-day NIHSS and discharge mRS were both significantly lower in the Post-Viz cohort (p=0.02 and p=0.03, respectively). The median 90-day mRS scores were also significantly lower post-Viz implementation, although a similar proportion received a good outcome (mRS score ≤ 2) (p=0.02 and p=0.42, respectively).ConclusionsEVT is a time-sensitive intervention that is only available at select stroke centers. Significant delays in time-to-treatment are present when patients require transfer from PSCs to a EVT capable stroke center. In a large health care system, we have shown that Viz LVO implementation is associated with improved time to INR notification and clinical outcomes. Viz LVO has the potential for wide-spread improvement in clinical outcomes with implementation across large hub and stroke systems across the country.

Download Full-text

Progression of cerebral infarction before and after thrombectomy is modified by prehospital pathways

Journal of NeuroInterventional Surgery ◽

10.1136/neurintsurg-2020-017155 ◽

2021 ◽

pp. neurintsurg-2020-017155

Author(s):

Alexander M Kollikowski ◽

Franziska Cattus ◽

Julia Haag ◽

Jörn Feick ◽

Alexander G März ◽

...

Keyword(s):

Patient Characteristics ◽

Large Vessel ◽

Stroke Severity ◽

Large Vessel Occlusion ◽

Time Intervals ◽

Vessel Occlusion ◽

Before And After ◽

Transferred Patients ◽

Stroke Center

BackgroundEvidence of the consequences of different prehospital pathways before mechanical thrombectomy (MT) in large vessel occlusion stroke is inconclusive. The aim of this study was to investigate the infarct extent and progression before and after MT in directly admitted (mothership) versus transferred (drip and ship) patients using the Alberta Stroke Program Early CT Score (ASPECTS).MethodsASPECTS of 535 consecutive large vessel occlusion stroke patients eligible for MT between 2015 to 2019 were retrospectively analyzed for differences in the extent of baseline, post-referral, and post-recanalization infarction between the mothership and drip and ship pathways. Time intervals and transport distances of both pathways were analyzed. Multiple linear regression was used to examine the association between infarct progression (baseline to post-recanalization ASPECTS decline), patient characteristics, and logistic key figures.ResultsASPECTS declined during transfer (9 (8–10) vs 7 (6-9), p<0.0001), resulting in lower ASPECTS at stroke center presentation (mothership 9 (7–10) vs drip and ship 7 (6–9), p<0.0001) and on follow-up imaging (mothership 7 (4–8) vs drip and ship 6 (3–7), p=0.001) compared with mothership patients. Infarct progression was significantly higher in transferred patients (points lost, mothership 2 (0–3) vs drip and ship 3 (2–6), p<0.0001). After multivariable adjustment, only interfacility transfer, preinterventional clinical stroke severity, the degree of angiographic recanalization, and the duration of the thrombectomy procedure remained predictors of infarct progression (R2=0.209, p<0.0001).ConclusionsInfarct progression and postinterventional infarct extent, as assessed by ASPECTS, varied between the drip and ship and mothership pathway, leading to more pronounced infarction in transferred patients. ASPECTS may serve as a radiological measure to monitor the benefit or harm of different prehospital pathways for MT.

Download Full-text

Abstract WP61: Artificial Intelligence for Automated Detection of Large Vessel Occlusion Strokes

Stroke ◽

10.1161/str.51.suppl_1.wp61 ◽

2020 ◽

Vol 51 (Suppl_1) ◽

Author(s):

Catarina Perry da Câmara ◽

Gabriel M Rodrigues ◽

Clara Barreira ◽

Mehdi Bouslama ◽

Leonardo Pisani ◽

...

Keyword(s):

Artificial Intelligence ◽

Detrimental Effect ◽

Poor Quality ◽

Automated Detection ◽

Large Vessel ◽

Large Vessel Occlusion ◽

Accurate Identification ◽

Vessel Occlusion ◽

The Mean ◽

Stroke Center

Introduction: Identification of Large Vessel Occlusion (LVO) in acute ischemic stroke (AIS) patients is critical for proper decision-making. Limited availability of trained experts and delays in LVO recognition can have a detrimental effect on outcomes. We sought to evaluate an artificial intelligence-based algorithm for LVO detection in AIS. Methods: A retrospective analysis of a prospectively-collected database of AIS patients admitted to a large volume stroke center between 2014-2018 was performed. Experienced vascular neurologists graded CTA for presence and site of LVO. Concurrently, studies were analyzed by the Viz-LVO Algorithm® version 1.4 (GA) - a convolutional neural network programmed to detect occlusions from the internal carotid artery terminus (ICA-T) to the sylvian fissure, which would include all MCA M1-segment and most M2-segment lesions. CTA readings were categorized as LVOs (ICA-T, MCA-M1, MCA-M2) versus non-LVOs/more distal occlusions. Comparisons between human and AI-based readings were done by accuracy analysis and calculating Cohen’s kappa. Results: A total of 610 CTAs were analyzed. The AI algorithm rejected 3.4% of the CTAs due to poor quality. Viz-LVO identified LVOs with an overall sensitivity of 81.3%, specificity of 87.8%, and accuracy of 83.2% (AUC 0.845 (95%CI:0.81-0.88, p<0.001). Table 1 shows the results per occlusion site. Accuracy was higher for ICA-T and M1 occlusions as compared to M2 occlusions. The mean run time of the algorithm was 2.78±0.5minutes. Conclusion: Our study demonstrates that automated AI reading allows for fast and accurate identification of LVO strokes. Future efforts should be made to improve the detection of the more distal occlusions.

Download Full-text

Impact of the COVID-19-pandemic on thrombectomy services in Germany

Neurological Research and Practice ◽

10.1186/s42466-020-00090-0 ◽

2020 ◽

Vol 2 (1) ◽

Author(s):

Steffen Tiedt ◽

◽

Felix J. Bode ◽

Timo Uphaus ◽

Anna Alegiani ◽

...

Keyword(s):

Functional Outcome ◽

Functional Outcomes ◽

Large Cohort ◽

Large Vessel ◽

Time Interval ◽

Large Vessel Occlusion ◽

Time Intervals ◽

Vessel Occlusion ◽

Endovascular Thrombectomy ◽

Interhospital Transfer

Abstract Background The Coronavirus Disease 2019 (COVID-19) pandemic may have altered emergency workflows established to optimize the outcome of patients with large-vessel occlusion (LVO) stroke. Aims We here analyzed workflow time intervals and functional outcomes of LVO patients treated with endovascular thrombectomy (ET) during the COVID-19 pandemic in Germany. Methods We compared the frequency, pre- and intrahospital workflow time intervals, rates of reperfusion, and functional outcome of patients admitted from March 1st to May 31st 2020 with patients admitted during the same time interval in 2019 to 12 university and municipal hospitals across Germany (N = 795). Results The number of LVO patients treated with ET between March to May 2020 was similar when compared to the same interval in 2019. Direct-to-center patients and patients admitted through interhospital transfer in 2020 showed similar pre- and intrahospital workflow time intervals compared to patients admitted in 2019, except for a longer door-to-groin time in patients admitted through interhospital transfer in 2020 (47 min vs 38 min, p = 0.005). Rates of reperfusion were not significantly different between 2020 and 2019. Functional outcome at discharge of LVO patients treated in 2020 was not significantly different compared to patients treated in 2019. Conclusion Pre- and intrahospital workflows, ET efficacy, and functional outcome of LVO patients treated with ET were not affected during the COVID-19 pandemic in our large cohort from centers across Germany.

Download Full-text

Pre- and Interhospital Workflow Times for Patients With Large Vessel Occlusion Stroke Transferred for Endovasvular Thrombectomy

Frontiers in Neurology ◽

10.3389/fneur.2021.730250 ◽

2021 ◽

Vol 12 ◽

Author(s):

Laura C. C. van Meenen ◽

Frank Riedijk ◽

Jeffrey Stolp ◽

Bas van der Veen ◽

Patricia H. A. Halkes ◽

...

Keyword(s):

Intravenous Thrombolysis ◽

Large Vessel ◽

Time Interval ◽

Large Vessel Occlusion ◽

Related Factors ◽

Vessel Occlusion ◽

Interhospital Transfer ◽

Primary Stroke Center ◽

Comprehensive Stroke Center ◽

Stroke Center

Background: Patients with large vessel occlusion (LVO) stroke are often initially admitted to a primary stroke center (PSC) and subsequently transferred to a comprehensive stroke center (CSC) for endovascular thrombectomy (EVT). This interhospital transfer delays initiation of EVT. To identify potential workflow improvements, we analyzed pre- and interhospital time metrics for patients with LVO stroke who were transferred from a PSC for EVT.Methods: We used data from the regional emergency medical services and our EVT registry. We included patients with LVO stroke who were transferred from three nearby PSCs for EVT (2014–2021). The time interval between first alarm and arrival at the CSC (call-to-CSC time) and other time metrics were calculated. We analyzed associations between various clinical and workflow-related factors and call-to-CSC time, using multivariable linear regression.Results: We included 198 patients with LVO stroke. Mean age was 70 years (±14.9), median baseline NIHSS was 14 (IQR: 9–18), 136/198 (69%) were treated with intravenous thrombolysis, and 135/198 (68%) underwent EVT. Median call-to-CSC time was 162 min (IQR: 137–190). In 133/155 (86%) cases, the ambulance for transfer to the CSC was dispatched with the highest level of urgency. This was associated with shorter call-to-CSC time (adjusted β [95% CI]: −27.6 min [−51.2 to −3.9]). No clinical characteristics were associated with call-to-CSC time.Conclusion: In patients transferred from a PSC for EVT, median call-to-CSC time was over 2.5 h. The highest level of urgency for dispatch of ambulances for EVT transfers should be used, as this clearly decreases time to treatment.

Download Full-text

Mobile Interventional Stroke Team Model Improves Early Outcomes in Large Vessel Occlusion Stroke

Stroke ◽

10.1161/strokeaha.120.030248 ◽

2020 ◽

Vol 51 (12) ◽

pp. 3495-3503 ◽

Cited By ~ 1

Author(s):

Jacob R. Morey ◽

Thomas J. Oxley ◽

Daniel Wei ◽

Christopher P. Kellner ◽

Neha S. Dangayach ◽

...

Keyword(s):

Clinical Outcomes ◽

Endovascular Therapy ◽

Large Vessel ◽

Large Vessel Occlusion ◽

Vessel Occlusion ◽

Stroke Team ◽

Primary Stroke Center ◽

Comprehensive Stroke Center ◽

Stroke Center ◽

Patient Presentation

Background and Purpose: Triage of patients with emergent large vessel occlusion stroke to primary stroke centers followed by transfer to comprehensive stroke centers leads to increased time to endovascular therapy. A Mobile Interventional Stroke Team (MIST) provides an alternative model by transferring a MIST to a Thrombectomy Capable Stroke Center (TSC) to perform endovascular therapy. Our aim is to determine whether the MIST model is more time-efficient and leads to improved clinical outcomes compared with standard drip-and-ship (DS) and mothership models. Methods: This is a prospective observational cohort study with 3-month follow-up between June 2016 and December 2018 at a multicenter health system, consisting of one comprehensive stroke center, 4 TSCs, and several primary stroke centers. A total of 228 of 373 patients received endovascular therapy via 1 of 4 models: mothership with patient presentation to a comprehensive stroke center, DS with patient transfer from primary stroke center or TSC to comprehensive stroke center, MIST with patient presentation to TSC and MIST transfer, or a combination of DS with patient transfer from primary stroke center to TSC and MIST. The prespecified primary end point was initial door-to-recanalization time and secondary end points measured additional time intervals and clinical outcomes at discharge and 3 months. Results: MIST had a faster mean initial door-to-recanalization time than DS by 83 minutes ( P <0.01). MIST and mothership had similar median door-to-recanalization times of 192 minutes and 179 minutes, respectively ( P =0.83). A greater proportion had a complete recovery (National Institutes of Health Stroke Scale of 0 or 1) at discharge in MIST compared with DS (37.9% versus 16.7%; P <0.01). MIST had 52.8% of patients with modified Rankin Scale of ≤2 at 3 months compared with 38.9% in DS ( P =0.10). Conclusions: MIST led to significantly faster initial door-to-recanalization times compared with DS, which was comparable to mothership. This decrease in time has translated into improved short-term outcomes and a trend towards improved long-term outcomes. Registration: URL: https://www.clinicaltrials.gov . Unique identifier: NCT03048292.

Download Full-text

Effect of “drip-and-ship” and “drip-and-drive” on endovascular treatment of acute ischemic stroke with large vessel occlusion: a single-center retrospective study

Acta Radiologica ◽

10.1177/02841851211006897 ◽

2021 ◽

pp. 028418512110068

Author(s):

Yu Hang ◽

Zhen Yu Jia ◽

Lin Bo Zhao ◽

Yue Zhou Cao ◽

Huang Huang ◽

...

Keyword(s):

Ischemic Stroke ◽

Endovascular Treatment ◽

Acute Ischemic Stroke ◽

Large Vessel ◽

Large Vessel Occlusion ◽

Vessel Occlusion ◽

Primary Stroke Center ◽

Secondary Endpoints ◽

Comprehensive Stroke Center ◽

Stroke Center

Background Patients with acute ischemic stroke (AIS) caused by large vessel occlusion (LVO) were usually transferred from a primary stroke center (PSC) to a comprehensive stroke center (CSC) for endovascular treatment (drip-and-ship [DS]), while driving the doctor from a CSC to a PSC to perform a procedure is an alternative strategy (drip-and-drive [DD]). Purpose To compare the efficacy and prognosis of the two strategies. Material and Methods From February 2017 to June 2019, 62 patients with LVO received endovascular treatment via the DS and DD models and were retrospectively analyzed from the stroke alliance based on our CSC. Primary endpoint was door-to-reperfusion (DTR) time. Secondary endpoints included puncture-to-recanalization (PTR) time, modified Thrombolysis in Cerebral Infarction (mTICI) rates at the end of the procedure, and modified Rankin Scale (mRS) at 90 days. Results Forty-one patients received the DS strategy and 21 patients received the DD strategy. The DTR time was significantly longer in the DS group compared to the DD group (315.5 ± 83.8 min vs. 248.6 ± 80.0 min; P < 0.05), and PTR time was shorter (77.2 ± 35.9 min vs. 113.7 ± 69.7 min; P = 0.033) compared with the DD group. Successful recanalization (mTICI 2b/3) was achieved in 89% (36/41) of patients in the DS group and 86% (18/21) in the DD group ( P = 1.000). Favorable functional outcomes (mRS 0–2) were observed in 49% (20/41) of patients in the DS group and 71% (15/21) in the DD group at 90 days ( P = 0.089). Conclusion Compared with the DS strategy, the DD strategy showed more effective and a trend of better clinical outcomes for AIS patients with LVO.

Download Full-text

EXPRESS: Off-hour effect on time metrics and clinical outcomes in endovascular treatment for large vessel occlusion, a systematic review and meta-analysis

International Journal of Stroke ◽

10.1177/17474930211012545 ◽

2021 ◽

pp. 174749302110125

Author(s):

Mingming Zha ◽

Qingwen Yang ◽

Shuo Liu ◽

Min Wu ◽

Kangmo Huang ◽

...

Keyword(s):

Endovascular Treatment ◽

Clinical Outcomes ◽

Meta Analysis ◽

Working Hours ◽

Good Prognosis ◽

Large Vessel ◽

Cochrane Library ◽

Large Vessel Occlusion ◽

Vessel Occlusion ◽

Significant Difference

Background There is an ongoing debate on the off-hour effect on endovascular treatment (EVT) for acute large vessel occlusion (LVO). Aims This meta-analysis aimed to compare time metrics and clinical outcomes of acute LVO patients who presented/were treated during off-hour with those during working hours. Summary of review Structured searches on the PubMed, Embase, Web of Science, and Cochrane Library databases were conducted through February 23rd, 2021. The primary outcomes were onset to door, door to imaging, door to puncture, puncture to recanalization, procedural time, successful recanalization, symptomatic intracerebral hemorrhage (SICH), mortality in hospital, good prognosis (90-day modified Rankin Scale [mRS] score 0-2), and 90-day mortality. The secondary outcomes were imaging to puncture, onset to puncture, onset to recanalization, door to recanalization time, mRS 0-2 at discharge, and consecutive 90-day mRS score. The odds ratio (OR) and weighted mean difference (WMD) with 95% confidence interval (CI) of the outcomes were calculated using random-effect models. Heterogenicity and publication bias were analyzed. Subgroup and sensitivity analyses were conducted as appropriate. Nineteen studies published between 2014 and 2021 with a total of 14185 patients were eligible for quantitative synthesis. Patients in the off-hour group were significantly younger than those in the on-hour group and with comparable stroke severity and intravenous thrombolysis rate. The off-hour group had longer onset to door (WMD [95%CI], 12.83 [1.84-23.82] min), door to puncture (WMD [95%CI], 11.45 [5.93-16.97] min), imaging to puncture (WMD [95%CI], 10.39 [4.61-16.17] min), onset to puncture (WMD [95%CI], 25.30 [13.11-37.50] min), onset to recanalization (WMD [95%CI], 25.16 [10.28-40.04] min), and door to recanalization (WMD [95%CI], 18.02 [10.01-26.03] min) time. Significantly lower successful recanalization rate (OR [95%CI], 0.85 [0.76-0.95]; P=0.004; I2=0%) was detected in the off-hour group. No significant difference was noted regarding SICH and prognosis. But a trend towards lower OR of good prognosis was witnessed in the off-hour group (OR [95%CI], 0.92 [0.84-1.01]; P=0.084; I2=0%). Conclusions Patients who presented/were treated during off-hour were associated with excessive delays before the initiation of EVT, lower successful reperfusion rate, and a trend towards worse prognosis when compared with working hours. Optimizing the workflows of EVT during off-hour is needed.

Download Full-text