Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Endovascular thrombectomy (EVT) enormously improves the prognosis of patients with large vessel occlusion (LVO) stroke, but its effect is highly time-dependent. Direct presentation of patients with an LVO stroke to an EVT-capable hospital reduces onset-to-treatment time by 40-115 minutes and thereby improves clinical outcome. Electroencephalography (EEG) may be a suitable prehospital stroke triage instrument for identifying LVO stroke, as differences have been found between EEG recordings of patients with an LVO stroke and those of suspected acute ischemic stroke patients with a smaller or no vessel occlusion. The investigators expect EEG can be performed in less than five minutes in the prehospital setting using a dry electrode EEG cap. An automatic LVO-detection algorithm will be the key to reliable, simple and fast interpretation of EEG recordings by ambulance paramedics. The primary objective of this study is to develop one or more novel AI-based algorithms (the AI-STROKE algorithms) with optimal diagnostic accuracy for identification of LVO stroke in patients with a suspected acute ischemic stroke in the prehospital setting, based on ambulant EEG data.
RATIONALE
Large vessel occlusion (LVO) stroke causes around 30% of acute ischemic strokes (AIS) and is associated with severe deficits and poor neurological outcomes. Endovascular thrombectomy (EVT) enormously improves the prognosis of patients with LVO stroke, but its effect is highly time-dependent. Because of its complexity and required resources, EVT can be performed in selected hospitals only. In the Netherlands, approximately half of the EVT-eligible patients are initially admitted to a hospital incapable of performing EVT, and - once it has been ascertained that the patient requires EVT - the patient needs to be transported a second time by ambulance to an EVT-capable hospital. Interhospital transfer leads to a treatment delay of 40-115 minutes, which decreases the absolute chance of a good outcome of the patient by 5-15%. To solve this issue, a prehospital stroke triage instrument is needed, which reliably identifies LVO stroke in the ambulance, so that these patients can be brought directly to an EVT-capable hospital. Electroencephalography (EEG) may be suitable for this purpose, since it shows almost instantaneous changes in response to cerebral blood flow reduction. Moreover, significant differences between EEGs of patients with an LVO stroke and those of suspected AIS patients with a smaller or no vessel occlusion have been found. A dry electrode EEG cap enables ambulance paramedics to perform an EEG in the prehospital setting, with significant reduced preparation time compared to conventional wet electrode EEG. An automatic LVO-detection algorithm will be the key to reliable, simple and fast interpretation of the EEG by paramedics, enabling direct admission of suspected AIS patients to the right hospital.
HYPOTHESIS
An EEG-based algorithm, developed with artificial intelligence (AI), will have sufficiently high diagnostic accuracy to be used by ambulance paramedics for prehospital LVO detection.
OBJECTIVE
The primary objective of this study is to develop one or more novel AI-based algorithms (the AI-STROKE algorithms) with optimal diagnostic accuracy for identification of LVO stroke in patients with a suspected AIS in the prehospital setting, based on ambulant EEG data.
STUDY DESIGN
AI-STROKE is an investigator-initiated, multicenter, diagnostic test accuracy study.
STUDY POPULATION
Part A: Adult patients with a (suspected) AIS, in the prehospital setting. Part B: Adult patients with a (suspected) AIS, in the in-hospital setting.
INTERVENTION
A single EEG measurement with a dry electrode cap (approximately 2 minutes recording duration) will be performed in each patient. In addition, clinical and radiological data will be collected. EEG data will be acquired with a CE approved portable dry electrode EEG device.
MAIN END POINTS
Primary end point: Based on the EEG data, and using the final diagnosis based on CT angiography data established by an adjudication committee as the gold standard, one or more novel AI-based EEG algorithms (the AI-STROKE algorithms) will be developed with maximal diagnostic accuracy (i.e. area under the receiver operating characteristic curve; AUC) to identify patients with an LVO stroke of the anterior circulation in a population of patients with suspected AIS.
Secondary end points:
Not provided
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Dry electrode cap EEG | Experimental | All patients that are included in the study will undergo a dry electrode electroencephalography (EEG). |
|
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| Dry electrode EEG | Diagnostic Test | A single dry electrode electroencephalography (EEG) will be performed in each patient that is included in this study. For this purpose the Waveguard touch dry electrode EEG cap and compatible eego mini amplifier (ANT Neuro B.V., Hengelo, Netherlands) are used to record and amplify the EEG signal, respectively. Both products are CE marked as medical devices in the European Union and will be used within the intended use as described in the user manuals. |
| Measure | Description | Time Frame |
|---|---|---|
| One or more novel AI-based EEG algorithms based on dry electrode EEG-data with optimal diagnostic accuracy for LVO-a | One or more novel artificial intelligence (AI) based electroencephalography (EEG) algorithms (the AI-STROKE algorithms) with maximal diagnostic accuracy to identify patients with an large vessel occlusion of the anterior circulation (LVO-a) in a population of patients with suspected acute ischemic stroke. For each patient a single dry electrode electroencephalography (EEG) will be performed and the presence or absence of an LVO-a will be assessed based on CT angiography data acquired at the emergency department. | EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| Measure | Description | Time Frame |
|---|---|---|
| AUC of the AI-STROKE algorithms for diagnosis of LVO-a | Area under the receiver operating characteristic curve (AUC) of the AI-STROKE algorithms based on ambulant electroencephalography (EEG) for diagnosis of large vessel occlusion of the anterior circulation (LVO-a) in suspected acute ischemic stroke patients in the prehospital setting. For each patient a single dry electrode electroencephalography (EEG) will be performed and the presence or absence of an LVO-a will be assessed based on CT angiography data acquired at the emergency department. |
Not provided
Inclusion Criteria:
Exclusion Criteria:
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Role | Phone | Extension | |
|---|---|---|---|---|
| Maritta N van Stigt, MSc | Contact | 0031 20 566 8417 | m.n.vanstigt@amterdamumc.nl | |
| Jonathan M Coutinho, MD, PhD | Contact | 0031 20 566 2004 | j.coutinho@amsterdamumc.nl |
| Name | Affiliation | Role |
|---|---|---|
| Jonathan M Coutinho, MD, PhD | Academisch Medisch Centrum - Universiteit van Amsterdam (AMC-UvA) | Principal Investigator |
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| Amsterdam University Medical Centers, location AMC | Recruiting | Amsterdam | North Holland | 1105AZ | Netherlands |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Type | Includes Protocol | Includes SAP | Includes ICF | Document Label | Document Date | Document Uploaded Date | Document File Name |
|---|---|---|---|---|---|---|---|
| Prot_SAP | Yes | Yes | No | Study Protocol and Statistical Analysis Plan | Apr 14, 2022 | Jun 7, 2022 | Prot_SAP_000.pdf |
| ICF | No | No | Yes | Informed Consent Form | Apr 14, 2022 | Jun 7, 2022 | ICF_001.pdf |
Not provided
| ID | Term |
|---|---|
| D000083242 | Ischemic Stroke |
| ID | Term |
|---|---|
| D020521 | Stroke |
| D002561 | Cerebrovascular Disorders |
| D001927 | Brain Diseases |
| D002493 | Central Nervous System Diseases |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
|
| EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| Sensitivity of the AI-STROKE algorithms for diagnosis of LVO-a | Sensitivity of the AI-STROKE algorithms based on ambulant electroencephalography (EEG) for diagnosis of large vessel occlusion of the anterior circulation (LVO-a) in suspected acute ischemic stroke patients in the prehospital setting. For each patient a single dry electrode electroencephalography (EEG) will be performed and the presence or absence of an LVO-a will be assessed based on CT angiography data acquired at the emergency department. | EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| Specificity of the AI-STROKE algorithms for diagnosis of LVO-a | Specificity of the AI-STROKE algorithms based on ambulant electroencephalography (EEG) for diagnosis of large vessel occlusion of the anterior circulation (LVO-a) in suspected acute ischemic stroke patients in the prehospital setting. For each patient a single dry electrode electroencephalography (EEG) will be performed and the presence or absence of an LVO-a will be assessed based on CT angiography data acquired at the emergency department. | EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| PPV of the AI-STROKE algorithms for diagnosis of LVO-a | Positive predictive value (PPV) of the AI-STROKE algorithms based on ambulant electroencephalography (EEG) for diagnosis of large vessel occlusion of the anterior circulation (LVO-a) in suspected acute ischemic stroke patients in the prehospital setting. For each patient a single dry electrode electroencephalography (EEG) will be performed and the presence or absence of an LVO-a will be assessed based on CT angiography data acquired at the emergency department. | EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| NPV of the AI-STROKE algorithms for diagnosis of LVO-a | Negative predictive value (NPV) of the AI-STROKE algorithms based on ambulant electroencephalography (EEG) for diagnosis of large vessel occlusion of the anterior circulation (LVO-a) in suspected acute ischemic stroke patients in the prehospital setting. For each patient a single dry electrode electroencephalography (EEG) will be performed and the presence or absence of an LVO-a will be assessed based on CT angiography data acquired at the emergency department. | EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| AUC of existing EEG algorithms for diagnosis of LVO-a | Area under the receiver operating characteristic curve (AUC) of existing electroencephalography (EEG) algorithms based on ambulant EEG for diagnosis of large vessel occlusion of the anterior circulation (LVO-a) in suspected acute ischemic stroke patients in the prehospital setting. For each patient a single dry electrode electroencephalography (EEG) will be performed and the presence or absence of an LVO-a will be assessed based on CT angiography data acquired at the emergency department. | EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| Sensitivity of existing EEG algorithms for diagnosis of LVO-a | Sensitivity of existing electroencephalography (EEG) algorithms based on ambulant EEG for diagnosis of large vessel occlusion of the anterior circulation (LVO-a) in suspected acute ischemic stroke patients in the prehospital setting. For each patient a single dry electrode electroencephalography (EEG) will be performed and the presence or absence of an LVO-a will be assessed based on CT angiography data acquired at the emergency department. | EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| Specificity of existing EEG algorithms for diagnosis of LVO-a | Specificity of existing electroencephalography (EEG) algorithms based on ambulant EEG for diagnosis of large vessel occlusion of the anterior circulation (LVO-a) in suspected acute ischemic stroke patients in the prehospital setting. For each patient a single dry electrode electroencephalography (EEG) will be performed and the presence or absence of an LVO-a will be assessed based on CT angiography data acquired at the emergency department. | EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| PPV of existing EEG algorithms for diagnosis of LVO-a | Positive predictive value (PPV) of existing electroencephalography (EEG) algorithms based on ambulant EEG for diagnosis of large vessel occlusion of the anterior circulation (LVO-a) in suspected acute ischemic stroke patients in the prehospital setting. For each patient a single dry electrode electroencephalography (EEG) will be performed and the presence or absence of an LVO-a will be assessed based on CT angiography data acquired at the emergency department. | EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| NPV of existing EEG algorithms for diagnosis of LVO-a | Negative predictive value (NPV) of existing electroencephalography (EEG) algorithms based on ambulant EEG for diagnosis of large vessel occlusion of the anterior circulation (LVO-a) in suspected acute ischemic stroke patients in the prehospital setting. For each patient a single dry electrode electroencephalography (EEG) will be performed and the presence or absence of an LVO-a will be assessed based on CT angiography data acquired at the emergency department. | EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| AUC of existing and newly developed EEG algorithms for detection of LVO-p, intracerebral hemorrhage, transient ischemic attack, and stroke mimics | Area under the receiver operating characteristic curve (AUC) of existing and newly developed electroencephalography (EEG) algorithms based on ambulant EEG for detection of an large vessel occlusion of the posterior circulation (LVO-p), intracerebral hemorrhage, transient ischemic attack, and stroke mimics. | EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| Sensitivity of existing and newly developed EEG algorithms for detection of LVO-p, intracerebral hemorrhage, transient ischemic attack, and stroke mimics | Sensitivity of existing and newly developed electroencephalography (EEG) algorithms based on ambulant EEG for detection of an large vessel occlusion of the posterior circulation (LVO-p), intracerebral hemorrhage, transient ischemic attack, and stroke mimics. | EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| Specificity of existing and newly developed EEG algorithms for detection of LVO-p, intracerebral hemorrhage, transient ischemic attack, and stroke mimics | Specificity of existing and newly developed electroencephalography (EEG) algorithms based on ambulant EEG for detection of an large vessel occlusion of the posterior circulation (LVO-p), intracerebral hemorrhage, transient ischemic attack, and stroke mimics. | EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| PPV of existing and newly developed EEG algorithms for detection of LVO-p, intracerebral hemorrhage, transient ischemic attack, and stroke mimics | Positive predictive value (PPV) of existing and newly developed electroencephalography (EEG) algorithms based on ambulant EEG for detection of an large vessel occlusion of the posterior circulation (LVO-p), intracerebral hemorrhage, transient ischemic attack, and stroke mimics. | EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| NPV of existing and newly developed EEG algorithms for detection of LVO-p, intracerebral hemorrhage, transient ischemic attack, and stroke mimics | Negative predictive value (NPV) of existing and newly developed electroencephalography (EEG) algorithms based on ambulant EEG for detection of an large vessel occlusion of the posterior circulation (LVO-p), intracerebral hemorrhage, transient ischemic attack, and stroke mimics. | EEG-data for development of the algorithm will be recorded within 24 hours after onset of symptoms or last seen well |
| Technical feasibility of performing ambulant EEGs in the prehospital setting | Assessing whether it is technically possible for paramedics to perform ambulant electroencephalography (EEG) in patients with a suspected AIS in the prehospital setting. | Feedback on technical issues by the paramedic that performs the EEG and by the EEG-expert, will be collected directly at arrival in the emergency department (within 24 hours after the patient is included in the study) |
| Logistical feasibility of performing ambulant EEGs in the prehospital setting | Assessing whether it is logistically possible for paramedics to perform ambulant electroencephalography (EEG) in patients with a suspected AIS in the prehospital setting. | Feedback on logistical issues by the paramedic that performs the EEG, will be collected directly at arrival in the emergency department (within 24 hours after the patient is included in the study) |
| D009422 |
| Nervous System Diseases |
| D014652 | Vascular Diseases |
| D002318 | Cardiovascular Diseases |