AI-based Algorithm Development for Improved Diagnostics in the Intensive Care and Acute Stroke Setting Using Electroencephalography

**RATIONALE**

Electroencephalography (EEG) is a noninvasive tool for detecting and monitoring neuronal activity. It plays a crucial role in predicting neurological outcome in postanoxic coma after cardiac arrest (CA). It is also promising for prehospital detection of intracranial hemorrhage (ICrH), including intracerebral hemorrhage (ICH) and subarachnoid hemorrhage (SAH).

Conventional scalp EEG has two practical limitations. Its electrodes must be carefully placed on the scalp by specialized personnel. Its interpretation requires expertise, is time-consuming and is prone to interrater variability.

In critical care and emergency settings, time is critical and specialist availability is often limited. In acute stroke care, rapid detection of ICrH is essential to start early appropriate treatment. In postanoxic coma after CA, early EEG monitoring after ICU admission is recommended to accurately predict neurological outcome.

Recent pilot studies suggest that subhairline EEG is a reliable and easy alternative to scalp EEG for these time-critical settings. Subhairline EEG is a simplified configuration consisting of a single patch applied on the forehead and behind the ears. In addition, artificial intelligence (AI) algorithms for automated interpretation of subhairline EEG could provide rapid and reliable decision support in both settings.

**HYPOTHESIS**

The investigators hypothesize that AI algorithms based on subhairline EEG can accurately predict neurological outcome in patients with postanoxic coma after CA. The investigators also hypothesize that such algorithms can accurately detect ICH in patients with suspected stroke.

**OBJECTIVE**

* Use case 1 (UC1): To develop and validate an AI algorithm based on subhairline EEG for outcome prediction in postanoxic coma at 24 hours after CA.
* Use case 2 (UC2): To develop and validate an AI algorithm based on subhairline EEG and clinical symptoms for detection of ICH in patients with (suspected) stroke.

**STUDY DESIGN**

This is an investigator-initiated, monocenter, observational study at Amsterdam UMC. It consists of three steps.

Step 1: Algorithm development. Several EEG-based AI algorithms will be developed and pre-trained using existing scalp EEG data and clinical data (UC1: >900 patients, UC2: >1000 patients).

Step 2: Prospective data collection. Subhairline EEG data and clinical data will be collected with the TrianecT subhairline EEG recording device. Sample sizes are based on 10-20 events per predictor.

* UC1: 180-360 patients
* UC2.1 (suspected stroke): 300-600 patients
* UC2.2 (suspected SAH): 100 patients

Step 3: Algorithm fine-tuning, validation and feasibility. The pre-trained algorithms will be fine-tuned and validated on the collected subhairline EEG data using transfer learning. The algorithms will then be integrated into the TrianecT software (SMART-EEG). Practical and clinical feasibility will be evaluated in up to 10 patients per use case. This evaluation is not intended for CE certification.

**STUDY POPULATION**

All participants are 18 years or older.

* UC1: Patients in postanoxic coma after CA admitted to the ICU.
* UC2.1: Patients with suspected stroke, as assessed by ambulance personnel, or with confirmed stroke.
* UC2.2: Patients with suspected SAH, as judged by the attending paramedic, or with confirmed SAH.

**INTERVENTION**

All participants undergo a subhairline EEG recording with a single patch applied on the forehead and behind the ears.

* UC1: continuous subhairline EEG recording, in addition to the standard scalp EEG used in routine care. The recording starts as soon as possible after ICU admission and continues up to 72 hours after CA.
* UC2: a single subhairline EEG recording of approximately 2 minutes, performed as soon as possible after presentation at the hospital.

**MAIN END POINTS**

Primary end points:

* UC1: the prognostic performance of subhairline EEG-based AI algorithms for prediction of neurological outcome at 24 hours after CA in postanoxic coma patients in the ICU. This is expressed as the area under the ROC curve (AUC), sensitivity, specificity and predictive values, with 95% confidence intervals. The optimal cut-off for poor outcome is defined as the highest sensitivity at a false positive rate of 0%.
* UC2: the diagnostic accuracy of subhairline EEG-based AI algorithms for detection of ICH in (suspected) stroke patients in the emergency department. This is expressed as the AUC, and as sensitivity, specificity, PPV and NPV at the optimal cut-off, each with 95% confidence intervals.

Secondary end points:

* Prognostic performance of AI algorithms based on subhairline EEG for outcome prediction at each hour between 6 and 24 hours after CA.
* Diagnostic accuracy of AI algorithms based on subhairline EEG and clinical symptoms for detection of SAH.
* Feasibility of SMART-EEG use in the ICU setting.
* Feasibility of SMART-EEG use in the acute stroke setting, including user-friendliness as rated by users.

Primary outcomes

• Prognostic performance of a subhairline EEG-based AI algorithm for neurological outcome prediction in postanoxic coma [EEG at 24 hours after cardiac arrest; neurological outcome at hospital discharge (up to 3 months after CA)]: Performance of the AI algorithm, based on subhairline EEG recorded at 24 hours after cardiac arrest, in predicting poor neurological outcome. Poor outcome is defined as CPC 3-5 at hospital discharge. Performance is expressed as the area under the ROC curve (AUC), sensitivity, specificity, positive and negative predictive values, each with 95% confidence intervals. The optimal cut-off for poor outcome is defined as the highest sensitivity at a false positive rate of 0%.
• Diagnostic accuracy of a subhairline EEG-based AI algorithm for detection of intracerebral hemorrhage [EEG at presentation (within 24 hours of symptom onset); final diagnosis at hospital discharge (up to 3 months after presentation)]: Diagnostic accuracy of the AI algorithm, based on subhairline EEG and clinical symptoms, in detecting intracerebral hemorrhage (ICH) in patients with suspected stroke. The reference standard is the final diagnosis based on neuroimaging. Accuracy is expressed as the area under the ROC curve (AUC), and as sensitivity, specificity, positive and negative predictive values at the optimal cut-off, each with 95% confidence intervals.

Secondary outcomes

• Prognostic performance of subhairline EEG-based AI algorithms for neurological outcome prediction at hourly intervals between 6 and 24 hours after cardiac arrest [EEG at each hour from 6 to 24 hours after cardiac arrest; neurological outcome at hospital discharge (up to 3 months after CA)]: Performance of AI algorithms, based on subhairline EEG recorded at each hour between 6 and 24 hours after cardiac arrest, in predicting poor neurological outcome. Poor outcome is defined as CPC 3-5 at hospital discharge. Performance is expressed as AUC, sensitivity, specificity, positive and negative predictive values, each with 95% confidence intervals. The cut-off is defined as the highest sensitivity at a false positive rate of 0%.
• Diagnostic accuracy of a subhairline EEG-based AI algorithm for detection of subarachnoid hemorrhage [EEG at presentation (within 48 hours of symptom onset); final diagnosis at hospital discharge (up to 3 months after presentation)]: Diagnostic accuracy of the AI algorithm, based on subhairline EEG and clinical symptoms, in detecting subarachnoid hemorrhage (SAH) in patients with suspected SAH. Accuracy is expressed as AUC, and as sensitivity, specificity, positive and negative predictive values at the optimal cut-off, each with 95% confidence intervals.
• Feasibility of SMART-EEG in the intensive care unit [During the recording, from ICU admission up to 72 hours after cardiac arrest]: Practical and clinical feasibility of the subhairline EEG device with integrated AI algorithms (SMART-EEG) in up to 10 postanoxic coma patients in the ICU. Feasibility includes user-friendliness as rated by users . Algorithm results are not used for clinical decisions.
• Feasibility of SMART-EEG in the in-hospital acute stroke setting [At the time of the EEG recording, at presentation (Day 1)]: Practical and clinical feasibility of SMART-EEG in up to 10 patients with suspected stroke in the emergency department. Feasibility includes user-friendliness as rated by users. Algorithm results are not used for clinical decisions.

Sex: All, ages: 18 Years to any

Inclusion Criteria:

All participants:

\- Age 18 years or older

Postanoxic coma (ICU):

* Postanoxic coma after cardiac arrest, admitted to the intensive care unit
* No objection to participation within 4 weeks of receiving an opt-out information letter

Suspected stroke (emergency department):

* Suspected stroke as assessed by the ambulance personnel presenting the patient to the emergency department, or confirmed stroke.
* Symptom onset, or last seen well if onset was not witnessed, less than 24 hours ago.
* Written (deferred) informed consent by the patient or legal representative

Suspected subarachnoid hemorrhage (emergency department):

* Suspected subarachnoid hemorrhage as judged by the attending ambulance paramedic, or confirmed subarachnoid hemorrhage.
* Symptom onset, or last seen well if onset was not witnessed, less than 48 hours ago.
* Written (deferred) informed consent by the patient or legal representative.

Exclusion Criteria:

All participants:

\- (Suspected) skin damage or infection at the placement area of the subhairline EEG patch

Postanoxic coma (ICU):

\- Other types of severe brain injury, either pre-existing or coinciding with cardiac arrest. These include stroke, traumatic brain injury and progressive neurodegenerative disease.