1
|
Nair SS, Guo A, Boen J, Aggarwal A, Chahal O, Tandon A, Patel M, Sankararaman S, Durr NJ, Azad TD, Pirracchio R, Stevens RD. A deep learning approach for generating intracranial pressure waveforms from extracranial signals routinely measured in the intensive care unit. Comput Biol Med 2024; 177:108677. [PMID: 38833800 DOI: 10.1016/j.compbiomed.2024.108677] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2024] [Revised: 05/27/2024] [Accepted: 05/28/2024] [Indexed: 06/06/2024]
Abstract
Intracranial pressure (ICP) is commonly monitored to guide treatment in patients with serious brain disorders such as traumatic brain injury and stroke. Established methods to assess ICP are resource intensive and highly invasive. We hypothesized that ICP waveforms can be computed noninvasively from three extracranial physiological waveforms routinely acquired in the Intensive Care Unit (ICU): arterial blood pressure (ABP), photoplethysmography (PPG), and electrocardiography (ECG). We evaluated over 600 h of high-frequency (125 Hz) simultaneously acquired ICP, ABP, ECG, and PPG waveform data in 10 patients admitted to the ICU with critical brain disorders. The data were segmented in non-overlapping 10-s windows, and ABP, ECG, and PPG waveforms were used to train deep learning (DL) models to re-create concurrent ICP. The predictive performance of six different DL models was evaluated in single- and multi-patient iterations. The mean average error (MAE) ± SD of the best-performing models was 1.34 ± 0.59 mmHg in the single-patient and 5.10 ± 0.11 mmHg in the multi-patient analysis. Ablation analysis was conducted to compare contributions from single physiologic sources and demonstrated statistically indistinguishable performances across the top DL models for each waveform (MAE±SD 6.33 ± 0.73, 6.65 ± 0.96, and 7.30 ± 1.28 mmHg, respectively, for ECG, PPG, and ABP; p = 0.42). Results support the preliminary feasibility and accuracy of DL-enabled continuous noninvasive ICP waveform computation using extracranial physiological waveforms. With refinement and further validation, this method could represent a safer and more accessible alternative to invasive ICP, enabling assessment and treatment in low-resource settings.
Collapse
Affiliation(s)
- Shiker S Nair
- Department of Biomedical Engineering, Johns Hopkins University Whiting School of Engineering, Baltimore, MD, USA.
| | - Alina Guo
- Department of Biomedical Engineering, Johns Hopkins University Whiting School of Engineering, Baltimore, MD, USA
| | - Joseph Boen
- Department of Biomedical Engineering, Johns Hopkins University Whiting School of Engineering, Baltimore, MD, USA
| | - Ataes Aggarwal
- Department of Biomedical Engineering, Johns Hopkins University Whiting School of Engineering, Baltimore, MD, USA
| | - Ojas Chahal
- Department of Biomedical Engineering, Johns Hopkins University Whiting School of Engineering, Baltimore, MD, USA
| | - Arushi Tandon
- Department of Biomedical Engineering, Johns Hopkins University Whiting School of Engineering, Baltimore, MD, USA
| | - Meer Patel
- Department of Biomedical Engineering, Johns Hopkins University Whiting School of Engineering, Baltimore, MD, USA
| | - Sreenidhi Sankararaman
- Department of Biomedical Engineering, Johns Hopkins University Whiting School of Engineering, Baltimore, MD, USA
| | - Nicholas J Durr
- Department of Biomedical Engineering, Johns Hopkins University Whiting School of Engineering, Baltimore, MD, USA
| | - Tej D Azad
- Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Romain Pirracchio
- Department of Anesthesia and Perioperative Care, UCSF, San Francisco, USA
| | - Robert D Stevens
- Department of Biomedical Engineering, Johns Hopkins University Whiting School of Engineering, Baltimore, MD, USA; Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA; Department of Anesthesiology and Critical Care Medicine, Johns Hopkins University, Baltimore, MD, USA; Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA.
| |
Collapse
|
2
|
Müller SJ, Henkes E, Gounis MJ, Felber S, Ganslandt O, Henkes H. Non-Invasive Intracranial Pressure Monitoring. J Clin Med 2023; 12:jcm12062209. [PMID: 36983213 PMCID: PMC10051320 DOI: 10.3390/jcm12062209] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2023] [Revised: 03/09/2023] [Accepted: 03/11/2023] [Indexed: 03/15/2023] Open
Abstract
(1) Background: Intracranial pressure (ICP) monitoring plays a key role in the treatment of patients in intensive care units, as well as during long-term surgeries and interventions. The gold standard is invasive measurement and monitoring via ventricular drainage or a parenchymal probe. In recent decades, numerous methods for non-invasive measurement have been evaluated but none have become established in routine clinical practice. The aim of this study was to reflect on the current state of research and shed light on relevant techniques for future clinical application. (2) Methods: We performed a PubMed search for “non-invasive AND ICP AND (measurement OR monitoring)” and identified 306 results. On the basis of these search results, we conducted an in-depth source analysis to identify additional methods. Studies were analyzed for design, patient type (e.g., infants, adults, and shunt patients), statistical evaluation (correlation, accuracy, and reliability), number of included measurements, and statistical assessment of accuracy and reliability. (3) Results: MRI-ICP and two-depth Doppler showed the most potential (and were the most complex methods). Tympanic membrane temperature, diffuse correlation spectroscopy, natural resonance frequency, and retinal vein approaches were also promising. (4) Conclusions: To date, no convincing evidence supports the use of a particular method for non-invasive intracranial pressure measurement. However, many new approaches are under development.
Collapse
Affiliation(s)
- Sebastian Johannes Müller
- Neuroradiologische Klinik, Klinikum Stuttgart, D-70174 Stuttgart, Germany
- Correspondence: ; Tel.: +49-(0)711-278-34501
| | - Elina Henkes
- Neuroradiologische Klinik, Klinikum Stuttgart, D-70174 Stuttgart, Germany
| | - Matthew J. Gounis
- New England Center for Stroke Research, Department of Radiology, University of Massachusetts, Worcester, MA 01655, USA
| | - Stephan Felber
- Institut für Diagnostische und Interventionelle Radiologie und Neuroradiologie, Stiftungsklinikum Mittelrhein, D-56068 Koblenz, Germany
| | - Oliver Ganslandt
- Neurochirurgische Klinik, Klinikum Stuttgart, D-70174 Stuttgart, Germany
| | - Hans Henkes
- Neuroradiologische Klinik, Klinikum Stuttgart, D-70174 Stuttgart, Germany
- Medizinische Fakultät, Universität Duisburg-Essen, D-47057 Duisburg, Germany
| |
Collapse
|
3
|
Ultrasonic Assessment of the Medial Temporal Lobe Tissue Displacements in Alzheimer’s Disease. Diagnostics (Basel) 2020; 10:diagnostics10070452. [PMID: 32635379 PMCID: PMC7399840 DOI: 10.3390/diagnostics10070452] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/17/2020] [Revised: 06/30/2020] [Accepted: 07/01/2020] [Indexed: 12/31/2022] Open
Abstract
We aim to estimate brain tissue displacements in the medial temporal lobe (MTL) using backscattered ultrasound radiofrequency (US RF) signals, and to assess the diagnostic ability of brain tissue displacement parameters for the differentiation of patients with Alzheimer’s disease (AD) from healthy controls (HC). Standard neuropsychological evaluation and transcranial sonography (TCS) for endogenous brain tissue motion data collection are performed for 20 patients with AD and for 20 age- and sex-matched HC in a prospective manner. Essential modifications of our previous method in US waveform parametrization, raising the confidence of micrometer-range displacement signals in the presence of noise, are done. Four logistic regression models are constructed, and receiver operating characteristic (ROC) curve analyses are applied. All models have cut-offs from 61.0 to 68.5% and separate AD patients from HC with a sensitivity of 89.5% and a specificity of 100%. The area under a ROC curve of predicted probability in all models is excellent (from 95.2 to 95.7%). According to our models, AD patients can be differentiated from HC by a sharper morphology of some individual MTL spatial point displacements (i.e., by spreading the spectrum of displacements to the high-end frequencies with higher variability across spatial points within a region), by lower displacement amplitude differences between adjacent spatial points (i.e., lower strain), and by a higher interaction of these attributes.
Collapse
|