Publication: Novel Intracranial Pressure Monitoring Using Non-Invasive Deep Learning Approach
A research study published as a preprint on February 27, 2024, by the AIMS Lab, showcases an innovative deep-learning approach that could redefine the field of intracranial pressure monitoring. In conditions like severe acute brain injuries (SABIs), including strokes and traumatic brain injuries, accurate measurement of intracranial pressure (ICP) can be significant for managing the condition and preventing further neurological damage.
Phenome wide scan depicting unadjusted P-values from a phenome wide scan of aICP across different categories colored and sized by odds ratio with the red dashed line representing the unadjusted threshold and the orange dashed line representing the adjusted threshold
The current gold standard for ICP monitoring involves invasive monitors that pose risks like infections and hemorrhages, limiting their widespread application. The groundbreaking study by AIMS Lab proposes a safer and non-invasive monitoring using deep learning methodologies. The approach termed as ‘aICP’ leverages non-cranial waveform measurements to estimate ICP.
Basing their research on a staggering 19 million waveforms, equating to 5297 patient-hours from a total of 157 and 56 patients for the development and external validation of aICP respectively, the researchers also tested the association with clinical outcomes using data from 1,694 patients without intracranial monitors.
Setting a record in the field, Gulamali et al. at AIMS Lab have completed the first study that externally validates the effectiveness of this non-invasive algorithm for ICP monitoring. Moreover, this research sets another milestone by being the first to demonstrate an association with neurological outcomes, such as subdural haemorrhages (OR=24.2, P<3.01 x10-2). This significant conclusion could potentially broaden the sphere of ICP estimation to all patients in the intensive care domain, making it a groundbreaking stride in neuromonitoring.
This revolutionary research by the AIMS lab marks a significant milestone in the endeavour to make ICP monitoring safer, more accessible, and potentially life-saving for patients around the world.
Cite as: Gulamali F, Jayaraman P, Sawant AS, Desman J, Fox B, Chang A, Soong BY, Arivazaghan N, Reynolds AS, Duong SQ, Vaid A, Kovatch P, Freeman R, Hofer IS, Sakhuja A, Dangayach NS, Reich DS, Charney AW, Nadkarni GN. Derivation, External Validation and Clinical Implications of a deep learning approach for intracranial pressure estimation using non-cranial waveform measurements. medRxiv [Preprint]. 2024 Jan 30:2024.01.30.24301974. doi: 10.1101/2024.01.30.24301974. PMID: 38352556; PMCID: PMC10863000.