Pre-hospital detection of acute ischemic stroke secondary to emergent large vessel occlusion: lessons learned from electrocardiogram and acute myocardial infarction

Modern Prehospital Screening Technology for Emergent Neurovascular Disorders

Stroke is a serious neurological disease and a significant contributor to disability worldwide. Traditional in-hospital imaging techniques such as computed tomography (CT) and magnetic resonance imaging (MRI) remain the standard modalities for diagnosing stroke. The development of prehospital stroke detection devices may facilitate earlier diagnosis, initiation of stroke care, and ultimately better patient outcomes. In this review, the authors summarize the features of eight stroke detection devices using noninvasive brain scanning technology. The review summarizes the features of stroke detection devices including portable CT, MRI, transcranial Doppler ultrasound , microwave tomographic imaging, electroencephalography, near-infrared spectroscopy, volumetric impedance phaseshift spectroscopy, and cranial accelerometry. The technologies utilized, the indications for application, the environments indicated for application, the physical features of the eight stroke detection devices, and current commercial products are discussed. As technology advances, multiple portable stroke detection instruments exhibit the promising potential to expedite the diagnosis of stroke and enhance the time taken for treatment, ultimately aiding in prehospital stroke triage.

Case report: Flow changes in routes of collateral circulation in patients with LVO and low NIHSS: a point favor to treat

The effectiveness of endovascular thrombectomy in patients presenting low National Institutes of Health Stroke Scale (NIHSS) scores remains controversial, and the acquisition of additional evidence is required to refine the selection of candidates who may benefit the most from this therapeutic modality. In this study, we present the case of a 62-year-old individual, with left internal carotid occlusion stroke and low NIHSS, who had compensatory collateral flow from Willis polygon via the anterior communicating artery. The patient subsequently exhibited neurological deterioration and collateral flow failure from Willis polygon, indicating the need for urgent intervention. The study of collaterals in patients with large vessel occlusion stroke has garnered considerable attention, with research suggesting that individuals with low NIHSS scores and poor collateral profiles may be at a heightened risk of early neurological deterioration. We postulate that such patients may derive significant benefits from endovascular thrombectomy, and may posit that an intensive transcranial Doppler monitoring protocol could facilitate the identification of suitable candidates for such intervention.

Machine Learning Methods in Predicting Patients with Suspected Myocardial Infarction Based on Short-Time HRV Data

Diagnosis of cardiovascular diseases is an urgent task because they are the main cause of death for 32% of the world's population. Particularly relevant are automated diagnostics using machine learning methods in the digitalization of healthcare and introduction of personalized medicine in healthcare institutions, including at the individual level when designing smart houses. Therefore, this study aims to analyze short 10-s electrocardiogram measurements taken from 12 leads. In addition, the task is to classify patients with suspected myocardial infarction using machine learning methods. We have developed four models based on the k-nearest neighbor classifier, radial basis function, decision tree, and random forest to do this. An analysis of time parameters showed that the most significant parameters for diagnosing myocardial infraction are SDNN, BPM, and IBI. An experimental investigation was conducted on the data of the open PTB-XL dataset for patients with suspected myocardial infarction. The results showed that, according to the parameters of the short ECG, it is possible to classify patients with a suspected myocardial infraction as sick and healthy with high accuracy. The optimized Random Forest model showed the best performance with an accuracy of 99.63%, and a root mean absolute error is less than 0.004. The proposed novel approach can be used for patients who do not have other indicators of heart attacks.

Prehospital Comprehensive Stroke Center vs Primary Stroke Center Triage in Patients With Suspected Large Vessel Occlusion Stroke

Importance

Endovascular therapy (EVT) improves functional outcomes in acute ischemic stroke (AIS) with large vessel occlusion (LVO). Whether implementation of a regional prehospital transport policy for comprehensive stroke center triage increases use of EVT is uncertain.

Objective

To evaluate the association of a regional prehospital transport policy that directly triages patients with suspected LVO stroke to the nearest comprehensive stroke center with rates of EVT.

Design, Setting, and Participants

This retrospective, multicenter preimplementation-postimplementation study used an interrupted time series analysis to compare treatment rates before and after implementation in patients with AIS arriving at 15 primary stroke centers and 8 comprehensive stroke centers in Chicago, Illinois, via emergency medical services (EMS) transport from December 1, 2017, to May 31, 2019 (9 months before and after implementation in September 2018). Data were analyzed from December 1, 2017, to May 31, 2019.

Interventions

Prehospital EMS transport policy to triage patients with suspected LVO stroke, using a 3-item stroke scale, to comprehensive stroke centers.

Main Outcomes and Measures

Rates of EVT before and after implementation among EMS-transported patients within 6 hours of AIS onset.

Results

Among 7709 patients with stroke, 663 (mean [SD] age, 68.5 [14.9] years; 342 women [51.6%] and 321 men [48.4%]; and 348 Black individuals [52.5%]) with AIS arrived within 6 hours of stroke onset by EMS transport: 310 of 2603 (11.9%) in the preimplementation period and 353 of 2637 (13.4%) in the postimplementation period. The EVT rate increased overall among all patients with AIS (preimplementation, 4.9% [95% CI, 4.1%-5.8%]; postimplementation, 7.4% [95% CI, 7.5%-8.5%]; P < .001) and among EMS-transported patients with AIS within 6 hours of onset (preimplementation, 4.8% [95% CI, 3.0%-7.8%]; postimplementation, 13.6% [95% CI, 10.4%-17.6%]; P < .001). On interrupted time series analysis among EMS-transported patients, the level change within 1 month of implementation was 7.15% (P = .04) with no slope change before (0.16%; P = .71) or after (0.08%; P = .89), which indicates a step rather than gradual change. No change in time to thrombolysis or rate of thrombolysis was observed (step change, 1.42%; P = .82). There were no differences in EVT rates in patients not arriving by EMS in the 6- to 24-hour window or by interhospital transfer or walk-in, irrespective of time window.

Conclusions and Relevance

Implementation of a prehospital transport policy for comprehensive stroke center triage in Chicago was associated with a significant, rapid, and sustained increase in EVT rate for patients with AIS without deleterious associations with thrombolysis rates or times.

Time from image acquisition to endovascular team notification: a new target for enhancing acute stroke workflow

OBJECTIVE

To quantify the time between initial image acquisition (CT angiography (CTA)) and notification of the neuroendovascular surgery (NES) team, a potentially high yield time window to target for optimization of endovascular thrombectomy (ET) treatment times.

METHODS

We reviewed our multihospital database for all patients with a stroke with emergent large vessel occlusion treated with ET between January 1, 2017 and August 5, 2020. We dichotomized patients into rapid (≤20 min) and delayed (>20 min) notification times and analyzed treatment characteristics and outcomes.

RESULTS

Of 367 patients with ELVO undergoing ET for whom notification data were available, the median time from CTA to NES team notification was 24 min (IQR 12-47). The median total treatment time was 180 min (IQR 129-252). The median times from CTA to NES team notification for rapid (n=163) and delayed (n=204) cohorts were 11 (IQR 6-15) and 43 (IQR 30-80) min, respectively (p<0.001). The median overall times to reperfusion were 134 min (IQR 103-179) and 213 min (IQR 172-291), respectively (p<0.001). The delayed patients had a significantly lower National Institutes of Health Stroke Scale (NIHSS) score on presentation (15 (IQR 9-20) vs 16 (IQR 11-22), p=0.03), were younger (70 (IQR 60-79) vs 77 (IQR 64-85), p<0.001), and more often presented with posterior circulation occlusion (16.7% vs 7.4%, p<0.01). The group with rapid notification time had a statistically larger median improvement in NIHSS score from admission to discharge (6 (IQR 0.5-14) vs 5 (IQR 0.5-10), p=0.04).

CONCLUSIONS

Time delays from initial CTA acquisition to NES team notification can prevent expedient treatment with ET. Process improvements and automated stroke detection on imaging with automated notification of the NES team may ultimately improve time to reperfusion.

Artificial intelligence to diagnose ischemic stroke and identify large vessel occlusions: a systematic review

Background and purpose

Acute stroke caused by large vessel occlusions (LVOs) requires emergent detection and treatment by endovascular thrombectomy. However, radiologic LVO detection and treatment is subject to variable delays and human expertise, resulting in morbidity. Imaging software using artificial intelligence (AI) and machine learning (ML), a branch of AI, may improve rapid frontline detection of LVO strokes. This report is a systematic review of AI in acute LVO stroke identification and triage, and characterizes LVO detection software.

Methods

A systematic review of acute stroke diagnostic-focused AI studies from January 2014 to February 2019 in PubMed, Medline, and Embase using terms: ‘artificial intelligence’ or ‘machine learning or deep learning’ and ‘ischemic stroke’ or ‘large vessel occlusion’ was performed.

Results

Variations of AI, including ML methods of random forest learning (RFL) and convolutional neural networks (CNNs), are used to detect LVO strokes. Twenty studies were identified that use ML. Alberta Stroke Program Early CT Score (ASPECTS) commonly used RFL, while LVO detection typically used CNNs. Image feature detection had greater sensitivity with CNN than with RFL, 85% versus 68%. However, AI algorithm performance metrics use different standards, precluding ideal objective comparison. Four current software platforms incorporate ML: Brainomix (greatest validation of AI for ASPECTS, uses CNNs to automatically detect LVOs), General Electric, iSchemaView (largest number of perfusion study validations for thrombectomy), and Viz.ai (uses CNNs to automatically detect LVOs, then automatically activates emergency stroke treatment systems).

Conclusions

AI may improve LVO stroke detection and rapid triage necessary for expedited treatment. Standardization of performance assessment is needed in future studies.

Non-invasive sensor technology for prehospital stroke diagnosis: Current status and future directions

BACKGROUND

The diagnosis of stroke in the prehospital environment is the subject of intense interest and research. There are a number of non-invasive external brain monitoring devices in development that utilize various technologies to function as sensors for stroke and other neurological conditions. Future increased use of one or more of these devices could result in substantial changes in the current processes for stroke diagnosis and treatment, including transportation of stroke patients by emergency medical services.

AIMS

The present review will summarize information about 10 stroke sensor devices currently in development, utilizing various forms of technology, and all of which are external, non-invasive brain monitoring devices.

SUMMARY OF REVIEW

Ten devices are discussed including the technology utilized, the indications for use (stroke and, when relevant, other neurological conditions), the environment(s) indicated for use (with a focus on the prehospital setting), a description of the physical structure of each instrument, and, when available, findings that have been published in peer-reviewed journals or otherwise reported. The review is organized based on the technology utilized by each device, and seven distinct forms were identified: accelerometers, electroencephalography (EEG), microwaves, near-infrared, radiofrequency, transcranial doppler ultrasound, and volumetric impedance phase shift spectroscopy.

CONCLUSIONS

Non-invasive external brain monitoring devices are in various stages of development and have promise as stroke sensors in the prehospital setting. Some of the potential applications include to differentiate stroke from non-stroke, ischemic from hemorrhage stroke, and large vessel occlusion (LVO) from non-LVO ischemic stroke. Successful stroke diagnosis prior to hospital arrival could transform the current diagnostic and treatment paradigm for this disease.

Long-term implementation of a prehospital severity scale for EMS triage of acute stroke: a real-world experience

Background

Data on the implementation of prehospital large vessel occlusion (LVO) scales to identify and triage patients with acute ischemic stroke (AIS) in the field are limited, with the majority of studies occurring outside the USA.

Objective

To report our long-term experience of a US countywide emergency medical services (EMS) acute stroke triage protocol using the Rapid Arterial oCclusion Evaluation (RACE) score.

Methods

Our prospective database was used to identify all consecutive patients triaged within Lucas County, Ohio by the EMS with (1) a RACE score ≥5, taken directly to an endovascular capable center (ECC) as RACE-alerts (RA) and (2) a RACE score <5, taken to the nearest hospital as stroke-alerts (SA). Baseline demographics, RACE score, time metrics, final diagnosis, treatments, and clinical and angiographic outcomes were captured. The sensitivity and specificity for patients with a RACE score ≥5 with LVO, eligible for mechanical thrombectomy (MT), were calculated.

Results

Between July 2015 and June 2018, 492 RA and 1147 SA were triaged within our five-hospital network. Of the RA, 37% had AIS secondary to LVOs. Of the 492 RA and 1147 SA, 125 (25.4%) and 38 (3.3%), respectively, underwent MT (OR=9.9; 95% CI 6.8 to 14.6; p<0.0001). Median times from onset-to-ECC arrival (74 vs 167 min, p=0.03) and dispatch-to-ECC arrival (31 vs 46 min, p=0.0002) were shorter in the RA-MT than in the SA-MT cohort. A RACE cut-off point ≥5 showed a sensitivity and specificity of 0.77 and 0.75 for detection of patients with LVO eligible for MT, respectively.

Conclusions

We have demonstrated the long-term feasibility of a countywide EMS-based prehospital triage protocol using the RACE Scale within our hospital network.

Technological innovation for prehospital stroke triage: ripe for disruption

Background

With the benefit of mechanical thrombectomy firmly established, the focus has shifted to improved delivery of care. Reducing time from symptom onset to reperfusion is a primary goal. Technology promises tremendous opportunities in the prehospital space to achieve this goal.

Methods

This review explores existing, fledgling, and potential future technologies for application in the prehospital space.

Results

The opportunity for technology to improve stroke care resides in the detection, evaluation, triage, and transport of patients to an appropriate healthcare facility. Most prehospital technology remains in the early stages of design and implementation.

Conclusion

The major challenges to tackle for future improvement in prehospital stroke care are that of public awareness, emergency medical service detection, and triage, and improved systems of stroke care. Thoughtfully applied technology will transform all these areas.

The VITAL study and overall pooled analysis with the VIPS non-invasive stroke detection device

INTRODUCTION

Effective triage of patients with emergent large vessel occlusion (ELVO) to endovascular therapy capable centers may decrease time to treatment and improve outcome for these patients. Here we performed a derivation study to evaluate the accuracy of a portable, non-invasive, and easy to use severe stroke detector.

METHODS

The volumetric impedance phase shift spectroscopy (VIPS) device was used to assign a bioimpedance asymmetry score to 248 subjects across three cohorts, including 41 subjects presenting as acute stroke codes at a major comprehensive stroke center (CSC), 79 healthy volunteers, and 128 patients presenting to CSCs with a wide variety of brain pathology including additional stroke codes. Diagnostic parameters were calculated for the ability of the device to discern (1) severe stroke from minor stroke and (2) severe stroke from all other subjects. Patients with intracranial hardware were excluded from the analysis.

RESULTS

The VIPS device was able to differentiate severe stroke from minor strokes with a sensitivity of 93% (95% CI 83 to 98), specificity of 92% (95% CI 75 to 99), and an area under the curve (AUC) of 0.93 (95% CI 0.85 to 0.97). The device was able to differentiate severe stroke from all other subjects with a sensitivity of 93% (95% CI 83 to 98), specificity of 87% (95% CI 81 to 92), and an AUC of 0.95 (95% CI 0.89 to 0.96).

CONCLUSION

The VIPS device is a portable, non-invasive, and easy to use tool that may aid in the detection of severe stroke, including ELVO, with a sensitivity of 93% and specificity of 92% in this derivation study. This device has the potential to improve the triage of patients suffering severe stroke.

A review of acute ischemic stroke triage protocol evidence: a context for discussion

Endovascular thrombectomy (EVT) is now the standard of care for eligible patients with acute ischemic stroke (AIS) secondary to emergent large vessel occlusion (ELVO). However, there remains uncertainty in how hospital systems can most efficiently route patients with suspected ELVO for EVT treatment. Given the relative geographic distribution of centers with and without endovascular capabilities, the value of prehospital triage directly to centers with the ability to provide EVT remains debated. While there are no randomized trial data available to date, there is substantial evidence in the literature that may offer guidance on the subject. In this review we examine the available data in the context of improving the existing AIS triage systems and discuss how prehospital triage directly to endovascular-capable centers may confer clinical benefits for patients with suspected ELVO.