Description:
Reference #: 01627
The University of South Carolina is offering licensing opportunities for Using EEG to predict delirium using limited lead device.
Background:
This study demonstrates a machine learning-based approach to detect delirium using limited lead EEG data with a high accuracy of 98% prior to the onset of clinical symptoms. In contrast to the current bedside clinical screening method, which relies on patient participation, this approach enables non-invasive detection of delirium in patients who may not be able to participate in the assessment.
Invention Description:
This innovation is an algorithm using an available limited lead device that can detect delirium before symptom onset with high accuracy. It can be used in various settings, including home, hospital, and long-term care, with minimal training, enabling assessment of patients who cannot participate in clinical screening.
Potential Applications:
Delirium is a common and serious issue that affects around 80% of patients in intensive care units (ICUs). The condition often leads to impaired memory and attention, making it difficult for patients to manage their treatment plans at home, and is associated with a threefold increase in one-year mortality risk, increased need for long-term care, and hospital readmission costs of approximately $164 billion per year. Delirium is not limited to the ICU, hospital, or healthcare facilities and can occur in any setting or environment. Older adults are at greater risk, making the problem more prevalent as the population ages and more people survive critical illness. Despite being a national guideline from over 10 professional organizations for more than 10 years, less than 10% of clinicians report using a validated method for detecting ICU delirium. Bedside clinical assessments detect less than 20% of cases when a validated tool is used, highlighting the urgent need for more accurate detection methods.
This innovation offers a solution to the problem by introducing a wireless EEG device with a machine learning algorithm that can accurately detect delirium before symptom onset, with high accuracy and minimal training required. This approach enables assessment of patients who cannot participate in clinical screening, facilitating more accurate testing of interventions and prevention strategies.
Advantages and Benefits:
The proposed study offers superior performance in detecting ICU delirium. The wireless EEG device with a machine learning algorithm can accurately detect delirium before symptom onset with high accuracy, enabling more accurate testing of interventions and prevention strategies. This approach overcomes the shortcomings of bedside clinical assessments, which detect less than 20% of cases even when validated tools are used, and the lack of uptake of validated methods by clinicians, despite being a national guideline for over 10 years from multiple professional organizations. Furthermore, the wireless EEG device requires minimal training and can be used in a variety of settings, including the home, hospital, and long-term care, improving detection rates and patient outcomes.