دورية أكاديمية
أعرض في EDS

Deriving Automated Device Metadata From Intracranial Pressure Waveforms: A Transforming Research and Clinical Knowledge in Traumatic Brain Injury ICU Physiology Cohort Analysis.

التفاصيل البيبلوغرافية
العنوان: Deriving Automated Device Metadata From Intracranial Pressure Waveforms: A Transforming Research and Clinical Knowledge in Traumatic Brain Injury ICU Physiology Cohort Analysis.
المؤلفون: Ack SE; Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, MA., Dolmans RGF; Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, MA.; Department of Neurosurgery, Leiden University Medical Center, Leiden, The Netherlands., Foreman B; Department of Neurology, University of Cincinnati, Cincinnati, OH., Manley GT; Department of Neurology, University of California San Francisco, San Francisco, CA., Rosenthal ES; Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, MA., Zabihi M; Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, MA.
المصدر: Critical care explorations [Crit Care Explor] 2024 Jul 16; Vol. 6 (7), pp. e1118. Date of Electronic Publication: 2024 Jul 16 (Print Publication: 2024).
نوع المنشور: Journal Article; Multicenter Study
اللغة: English
بيانات الدورية: Publisher: Wolters Kluwer Health Country of Publication: United States NLM ID: 101746347 Publication Model: eCollection Cited Medium: Internet ISSN: 2639-8028 (Electronic) Linking ISSN: 26398028 NLM ISO Abbreviation: Crit Care Explor Subsets: MEDLINE
أسماء مطبوعة: Original Publication: Philadelphia, PA : Wolters Kluwer Health, [2019]-
مواضيع طبية MeSH: Brain Injuries, Traumatic*/physiopathology , Brain Injuries, Traumatic*/diagnosis , Intracranial Pressure*/physiology , Intensive Care Units* , Machine Learning*, Humans ; Male ; Middle Aged ; Female ; Adult ; Prospective Studies ; Cohort Studies ; Monitoring, Physiologic/methods ; Monitoring, Physiologic/instrumentation ; Aged
مستخلص: Importance: Treatment for intracranial pressure (ICP) has been increasingly informed by machine learning (ML)-derived ICP waveform characteristics. There are gaps, however, in understanding how ICP monitor type may bias waveform characteristics used for these predictive tools since differences between external ventricular drain (EVD) and intraparenchymal monitor (IPM)-derived waveforms have not been well accounted for.
Objectives: We sought to develop a proof-of-concept ML model differentiating ICP waveforms originating from an EVD or IPM.
Design, Setting, and Participants: We examined raw ICP waveform data from the ICU physiology cohort within the prospective Transforming Research and Clinical Knowledge in Traumatic Brain Injury multicenter study.
Main Outcomes and Measures: Nested patient-wise five-fold cross-validation and group analysis with bagged decision trees (BDT) and linear discriminant analysis were used for feature selection and fair evaluation. Nine patients were kept as unseen hold-outs for further evaluation.
Results: ICP waveform data totaling 14,110 hours were included from 82 patients (EVD, 47; IPM, 26; both, 9). Mean age, Glasgow Coma Scale (GCS) total, and GCS motor score upon admission, as well as the presence and amount of midline shift, were similar between groups. The model mean area under the receiver operating characteristic curve (AU-ROC) exceeded 0.874 across all folds. In additional rigorous cluster-based subgroup analysis, targeted at testing the resilience of models to cross-validation with smaller subsets constructed to develop models in one confounder set and test them in another subset, AU-ROC exceeded 0.811. In a similar analysis using propensity score-based rather than cluster-based subgroup analysis, the mean AU-ROC exceeded 0.827. Of 842 extracted ICP features, 62 were invariant within every analysis, representing the most accurate and robust differences between ICP monitor types. For the nine patient hold-outs, an AU-ROC of 0.826 was obtained using BDT.
Conclusions and Relevance: The developed proof-of-concept ML model identified differences in EVD- and IPM-derived ICP signals, which can provide missing contextual data for large-scale retrospective datasets, prevent bias in computational models that ingest ICP data indiscriminately, and control for confounding using our model's output as a propensity score by to adjust for the monitoring method that was clinically indicated. Furthermore, the invariant features may be leveraged as ICP features for anomaly detection.
Competing Interests: Dr. Foreman received honoraria from UCB Pharma, grant funding from the National Institute of Neurological Disorders And Stroke (NINDS) of the National Institutes of Health (NIH; K23NS101123), and he is a member of the Curing Coma Campaign Scientific Advisory Committee. Dr. Rosenthal receives grant funding (R01NS117904 from the NIH/NINDS, K23NS105950 from the NIH/NINDS, OT2OD032701 from the NIH/Office of the Director, W81XWH-18-DMRDP-PTCRA from the U.S. Army (subcontract from Moberg Analytics), and R01NS113541 from the NIH/NINDS, and he is a member of the Curing Coma Campaign Scientific Advisory Committee and Technical Working Group. The remaining authors have disclosed that they do not have any potential conflicts of interest.
(Copyright © 2024 The Authors. Published by Wolters Kluwer Health, Inc. on behalf of the Society of Critical Care Medicine.)
References: J Neurotrauma. 2013 Nov 15;30(22):1831-44. (PMID: 23815563)
Med Eng Phys. 2012 Oct;34(8):1058-65. (PMID: 22401795)
Curr Neurol Neurosci Rep. 2021 Feb 2;21(3):6. (PMID: 33527217)
Intensive Care Med. 2011 May;37(5):875-9. (PMID: 21359608)
J Neurol Neurosurg Psychiatry. 2004 Jun;75(6):813-21. (PMID: 15145991)
Proc IAPR Int Conf Pattern Recogn. 2016 Dec;2016:2491-2496. (PMID: 28936494)
Sensors (Basel). 2018 Feb 05;18(2):. (PMID: 29401746)
Physiol Meas. 2020 Feb 05;41(1):014001. (PMID: 31851948)
J Clin Monit Comput. 2006 Dec;20(6):411-4. (PMID: 17016744)
Gigascience. 2022 Mar 12;11:. (PMID: 35277962)
Genomics. 2012 Jun;99(6):323-9. (PMID: 22546560)
ScientificWorldJournal. 2015;2015:471371. (PMID: 25879059)
Crit Care Med. 2021 Oct 1;49(10):1769-1778. (PMID: 33935162)
Neurol Res. 2003 Jun;25(4):339-50. (PMID: 12870259)
Crit Care Med. 2013 Feb;41(2):554-64. (PMID: 23263587)
Springerplus. 2015 Jan 06;4:10. (PMID: 25674495)
IEEE J Transl Eng Health Med. 2022 Jun 02;10:4901008. (PMID: 35795876)
JAMA Neurol. 2021 Aug 1;78(8):982-992. (PMID: 34228047)
PLoS One. 2017 Nov 15;12(11):e0181025. (PMID: 29141045)
J Neurosci Nurs. 2000 Oct;32(5):271-7. (PMID: 11089200)
Surg Neurol Int. 2015 May 25;6(Suppl 6):S271-4. (PMID: 26069848)
IEEE J Biomed Health Inform. 2020 Feb;24(2):543-555. (PMID: 30932854)
Front Neurol. 2020 Aug 28;11:959. (PMID: 33013638)
IEEE Trans Biomed Eng. 2009 Mar;56(3):696-705. (PMID: 19272879)
Physiol Meas. 2023 Jul 04;44(6):. (PMID: 37327793)
BMC Med Inform Decis Mak. 2019 Dec 19;19(Suppl 6):266. (PMID: 31856801)
IEEE Trans Biomed Eng. 2013 Jan;60(1):235-9. (PMID: 22851230)
Interdiscip Perspect Infect Dis. 2014;2014:708531. (PMID: 25484896)
Sci Rep. 2022 Jun 10;12(1):9600. (PMID: 35688885)
Physiol Meas. 2019 Jan 18;40(1):015002. (PMID: 30562165)
Neurosurgery. 2017 Jan 01;80(1):6-15. (PMID: 27654000)
J Trauma Nurs. 2012 Jul-Sep;19(3):160-7. (PMID: 22955712)
Brain. 2022 Aug 27;145(8):2910-2919. (PMID: 35139181)
Comput Methods Programs Biomed. 2016 Sep;133:55-70. (PMID: 27393800)
معلومات مُعتمدة: K23 NS101123 United States NS NINDS NIH HHS; R01 NS117904 United States NS NINDS NIH HHS; OT2 OD032701 United States OD NIH HHS; R01 NS113541 United States NS NINDS NIH HHS; K23 NS105950 United States NS NINDS NIH HHS
تواريخ الأحداث: Date Created: 20240717 Date Completed: 20240717 Latest Revision: 20240719
رمز التحديث: 20240719
مُعرف محوري في PubMed: PMC11254120
DOI: 10.1097/CCE.0000000000001118
PMID: 39016273
قاعدة البيانات: MEDLINE
الوصف
تدمد:2639-8028
DOI:10.1097/CCE.0000000000001118