To develop one or more novel AI-based 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.
ID
Source
Brief title
Condition
- Central nervous system vascular disorders
Synonym
Research involving
Sponsors and support
Intervention
Outcome measures
Primary outcome
Based on the EEG data, and using the final diagnosis established by an
adjudication committee as the gold standard, one or more novel AI-based EEG
algorithms will be developed with maximal diagnostic accuracy to identify
patients with an LVO stroke of the anterior circulation in a population of
patients with suspected AIS.
Secondary outcome
- AUC, sensitivity, specificity, positive predictive value (PPV) and negative
predictive value (NPV) of the AI-STROKE algorithms based on ambulant EEG for
diagnosis of LVO of the anterior circulation in suspected AIS patients in the
prehospital setting;
- AUC, sensitivity, specificity, PPV and NPV of existing EEG algorithms based
on ambulant EEG for diagnosis of LVO of the anterior circulation in suspected
AIS patients in the prehospital setting;
- AUC, sensitivity, specificity, PPV and NPV of existing and newly developed
EEG algorithms based on ambulant EEG for detection of LVO stroke of the
posterior circulation, intracerebral hemorrhage, transient ischemic attack, and
stroke mimics;
- Technical and logistical feasibility (e.g. in terms of EEG channel
reliability) of paramedics performing ambulant EEG in patients with a suspected
AIS in the prehospital setting;
Background summary
Endovascular thrombectomy (EVT) is standard treatment for acute ischemic stroke
(AIS) if there is a large vessel occlusion in the anterior circulation (LVO).
Because of its complexitiy, EVT is performed in selected hospitals only.
Currently, approximately half of the EVT-eligible patients are initially
admitted to hospitals that do not provide this therapy. This delays initiation
of treatment by approximately one hour, which decreases the chance of a good
functional outcome. Direct presentation of all patients with a suspected AIS to
EVT-capable hospitals is not feasible, as only circa 7% of these patients are
eligible for EVT. Therefore, an advanced triage method that reliably identifies
patients with an LVO in the pre-hospital setting is necessary.
Previous studies have shown almost immediate changes in the EEG signal in
response to reduction of the cerebral blood flow. Furthermore, differences
between the EEG-signal of patients with an LVO and all other suspected stroke
patients have been found. Results from our pilot ELECTRA-STROKE study
(NL65939.018.18) suggest that, by using dry electrodes, an EEG registration can
be performed in the pre-hospital setting by relatively unexperienced ambulance
paramedics, within five minutes. A next crucial step is to develop an EEG-based
algorithm that accurately and reliably identifies patients with an LVO and
gives an easy to interpret binary outcome: LVO or no LVO.
Study objective
To develop one or more novel AI-based 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 study.
Part A: Algorithm development and validation in patients with suspected stroke
in the prehospital setting. Furthermore, analysis of the technical and
logistical feasibility of ambulance paramedics performing EEG registrations in
the pre-hospital setting in suspected stroke patients.
Part B: Algorithm development and validation in patients with suspected stroke
in the emergency room.
Study burden and risks
A single EEG will be performed in each patient. An EEG-measurement is a safe
and non-invasive procedure, regularly performed in standard medical practice.
The use of dry electrodes makes it possible to perform the measurement in less
than five minutes. Initiation of stroke treatment will therefore not be
delayed. The dry electrodes will cause no to minimal discomfort, and only
during the measurement. We expect no health risks, since we will use only CE
marked products for performing the EEG. The treating physicians and the
ambulance paramedics are not trained nor instructed to interpret the EEG,
therefore the EEG results will not influence choices regarding diagnosis or
treatment. Deferred informed consent will be asked as soon as feasible,
preferably within 72 hours after arrival at the hospital or at discharge
(whichever comes first). If informed consent is given, a case report form (CRF)
will be filled out containing information on patient characteristics, medical
history, medication use, physical and neurological examination performed by the
treating physician, results of imaging studies, diagnosis and treatment as well
as logistical, technical and usability information, obtained from the patient,
the treating physician and the Emergency Medical Service (EMS). There are no
follow up visits. For the patient, there is no benefit of participation in the
study.
Meibergdreef 9
Amsterdam 1105 AZ
NL
Meibergdreef 9
Amsterdam 1105 AZ
NL
Listed location countries
Age
Inclusion criteria
- Suspected acute ischemic stroke, as assessed by the attending ambulance
paramedic, or patients with a known LVO stroke who are transferred for EVT;
- Onset of symptoms or, if onset not witnessed, last seen well <24 hours ago;
- Age of 18 years or older;
- Written informed consent by patient or legal representative.
Exclusion criteria
- Injury or active infection of electrode cap placement area.
- Suspected COVID-19 infection.
Design
Recruitment
Medical products/devices used
Followed up by the following (possibly more current) registration
No registrations found.
Other (possibly less up-to-date) registrations in this register
No registrations found.
In other registers
| Register | ID |
|---|---|
| CCMO | NL75429.018.22 |