Prediction of patient survival following postanoxic coma using EEG data and clinical features

Aghaeeaval, Mahsa; Bendahan, Nathaniel; Shivji, Zaitoon; McInnis, Carter; Jamzad, Amoon; Lomax, Lysa Boissé; Shukla, Garima; Mousavi, Parvin; Winston, Gavin P.

doi:10.1109/embc46164.2021.9629946

Cited by 3 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One area of considerable interest is the ability to train artificial intelligence algorithms using qEEG features. Evidence suggests that algorithms can support neurologic prognostication in comatose survivors of cardiac arrest [27–29], adjustment of sedation depth [30], and identification of patients with cognitive motor dissociation [31 ▪ ,32]. The use of artificial intelligence to analyze neuromonitoring data is discussed further below.…”

Section: Quantitative Eegmentioning

confidence: 99%

Neuromonitoring in the ICU – what, how and why?

Mathur,

Meyfroidt,

Robba

et al. 2024

Current Opinion in Critical Care

View full text Add to dashboard Cite

Purpose of review We selectively review emerging noninvasive neuromonitoring techniques and the evidence that supports their use in the ICU setting. The focus is on neuromonitoring research in patients with acute brain injury. Recent findings Noninvasive intracranial pressure evaluation with optic nerve sheath diameter measurements, transcranial Doppler waveform analysis, or skull mechanical extensometer waveform recordings have potential safety and resource-intensity advantages when compared to standard invasive monitors, however each of these techniques has limitations. Quantitative electroencephalography can be applied for detection of cerebral ischemia and states of covert consciousness. Near-infrared spectroscopy may be leveraged for cerebral oxygenation and autoregulation computation. Automated quantitative pupillometry and heart rate variability analysis have been shown to have diagnostic and/or prognostic significance in selected subtypes of acute brain injury. Finally, artificial intelligence is likely to transform interpretation and deployment of neuromonitoring paradigms individually and when integrated in multimodal paradigms. Summary The ability to detect brain dysfunction and injury in critically ill patients is being enriched thanks to remarkable advances in neuromonitoring data acquisition and analysis. Studies are needed to validate the accuracy and reliability of these new approaches, and their feasibility and implementation within existing intensive care workflows.

show abstract

Section: Quantitative Eegmentioning

confidence: 99%

Neuromonitoring in the ICU – what, how and why?

Mathur,

Meyfroidt,

Robba

et al. 2024

Current Opinion in Critical Care

View full text Add to dashboard Cite

show abstract

Electroencephalography (EEG) for Neurological Prognostication in Post-Anoxic Coma Following Cardiac Arrest and Its Relationship to Outcome

Shivji,

Bendahan,

McInnis

et al. 2024

Brain Sciences

View full text Add to dashboard Cite

Background/Objectives: Cardiac arrest may cause significant hypoxic–ischemic injury leading to coma, seizures, myoclonic jerks, or status epilepticus. Mortality is high, but accurate prognostication is challenging. A multimodal approach is employed, in which electroencephalography (EEG) forms a key part with several recognised patterns of prognostic significance. Methods: In this retrospective study, clinical and qualitative features of the EEG of patients admitted to the Intensive Care Unit (ICU) at Kingston General Hospital following cardiac arrest from 2017 to 2020 were reviewed. The study included 81 adult patients (≥18 years). Outcome was assessed using the Cerebral Performance Category (CPC) as 1–2 (favourable) or 3–5 (unfavourable). EEG patterns were divided into groups within the highly malignant, malignant and benign patterns described in the literature. Results: There were a wide range of causes and 22% had a favourable outcome. Highly malignant, malignant and benign patterns were associated with survival in 0%, 70% and 100%, respectively, and favourable outcomes in 0%, 48% and 100%. All patients with seizures died, and 94% with myoclonus had unfavourable outcomes. In contrast, EEG reactivity and improvement on follow-up EEG were associated with a favourable outcome. Conclusions: Highly malignant EEG, seizures and myoclonus were associated with unfavourable outcomes, while patients with malignant EEG had better outcomes.

show abstract

Internet of Things-Combined Deep Learning for Electroencephalography-Based E-Healthcare

Das,

Ghosh,

Saha

2024

Advances in Medical Diagnosis, Treatment, and Care

View full text Add to dashboard Cite

Deep Learning (DL) is the most popular subset of machine learning, with many applications in healthcare and other areas. On the other hand, electroencephalography has effectively solved different brain activity-related healthcare applications. This non-invasive data collection method can monitor and diagnose brain-based health conditions as it is painless and safe. This chapter discusses different smart healthcare applications of DL. Different DL models applied in the existing literature have been described also, from which future researchers will benefit by having a clear insight into the concerned area. Then a smart health framework has been proposed where step by step-by-step process of designing the system has been presented using the Internet of Things (IoT) combined with DL.

show abstract

Prediction of patient survival following postanoxic coma using EEG data and clinical features

Cited by 3 publications

References 16 publications

Neuromonitoring in the ICU – what, how and why?

Neuromonitoring in the ICU – what, how and why?

Electroencephalography (EEG) for Neurological Prognostication in Post-Anoxic Coma Following Cardiac Arrest and Its Relationship to Outcome

Internet of Things-Combined Deep Learning for Electroencephalography-Based E-Healthcare

Contact Info

Product

Resources

About