Vector Angle Analysis of Multimodal Neuromonitoring Data for Continuous Prediction of Delayed Cerebral Ischemia.
Aneurysmal subarachnoid hemorrhage
Cerebral autoregulation
Classification
Machine learning
Neurocritical care
Journal
Neurocritical care
ISSN: 1556-0961
Titre abrégé: Neurocrit Care
Pays: United States
ID NLM: 101156086
Informations de publication
Date de publication:
08 2022
08 2022
Historique:
received:
16
12
2021
accepted:
28
02
2022
pubmed:
31
3
2022
medline:
4
8
2022
entrez:
30
3
2022
Statut:
ppublish
Résumé
Dysfunctional cerebral autoregulation often precedes delayed cerebral ischemia (DCI). Currently, there are no data-driven techniques that leverage this information to predict DCI in real time. Our hypothesis is that information using continuous updated analyses of multimodal neuromonitoring and cerebral autoregulation can be deployed to predict DCI. Time series values of intracranial pressure, brain tissue oxygenation, cerebral perfusion pressure (CPP), optimal CPP (CPPOpt), ΔCPP (CPP - CPPOpt), mean arterial pressure, and pressure reactivity index were combined and summarized as vectors. A validated temporal signal angle measurement was modified into a classification algorithm that incorporates hourly data. The time-varying temporal signal angle measurement (TTSAM) algorithm classifies DCI at varying time points by vectorizing and computing the angle between the test and reference time signals. The patient is classified as DCI+ if the error between the time-varying test vector and DCI+ reference vector is smaller than that between the time-varying test vector and DCI- reference vector. Finally, prediction at time point t is calculated as the majority voting over all the available signals. The leave-one-patient-out cross-validation technique was used to train and report the performance of the algorithms. The TTSAM and classifier performance was determined by balanced accuracy, F1 score, true positive, true negative, false positive, and false negative over time. One hundred thirty-one patients with aneurysmal subarachnoid hemorrhage who underwent multimodal neuromonitoring were identified from two centers (Columbia University: 52 [39.7%], Aachen University: 79 [60.3%]) and included in the analysis. Sixty-four (48.5%) patients had DCI, and DCI was diagnosed 7.2 ± 3.3 days after hemorrhage. The TTSAM algorithm achieved a balanced accuracy of 67.3% and an F1 score of 0.68 at 165 h (6.9 days) from bleed day with a true positive of 0.83, false positive of 0.16, true negative of 0.51, and false negative of 0.49. A TTSAM algorithm using multimodal neuromonitoring and cerebral autoregulation calculations shows promise to classify DCI in real time.
Sections du résumé
BACKGROUND
Dysfunctional cerebral autoregulation often precedes delayed cerebral ischemia (DCI). Currently, there are no data-driven techniques that leverage this information to predict DCI in real time. Our hypothesis is that information using continuous updated analyses of multimodal neuromonitoring and cerebral autoregulation can be deployed to predict DCI.
METHODS
Time series values of intracranial pressure, brain tissue oxygenation, cerebral perfusion pressure (CPP), optimal CPP (CPPOpt), ΔCPP (CPP - CPPOpt), mean arterial pressure, and pressure reactivity index were combined and summarized as vectors. A validated temporal signal angle measurement was modified into a classification algorithm that incorporates hourly data. The time-varying temporal signal angle measurement (TTSAM) algorithm classifies DCI at varying time points by vectorizing and computing the angle between the test and reference time signals. The patient is classified as DCI+ if the error between the time-varying test vector and DCI+ reference vector is smaller than that between the time-varying test vector and DCI- reference vector. Finally, prediction at time point t is calculated as the majority voting over all the available signals. The leave-one-patient-out cross-validation technique was used to train and report the performance of the algorithms. The TTSAM and classifier performance was determined by balanced accuracy, F1 score, true positive, true negative, false positive, and false negative over time.
RESULTS
One hundred thirty-one patients with aneurysmal subarachnoid hemorrhage who underwent multimodal neuromonitoring were identified from two centers (Columbia University: 52 [39.7%], Aachen University: 79 [60.3%]) and included in the analysis. Sixty-four (48.5%) patients had DCI, and DCI was diagnosed 7.2 ± 3.3 days after hemorrhage. The TTSAM algorithm achieved a balanced accuracy of 67.3% and an F1 score of 0.68 at 165 h (6.9 days) from bleed day with a true positive of 0.83, false positive of 0.16, true negative of 0.51, and false negative of 0.49.
CONCLUSIONS
A TTSAM algorithm using multimodal neuromonitoring and cerebral autoregulation calculations shows promise to classify DCI in real time.
Identifiants
pubmed: 35352273
doi: 10.1007/s12028-022-01481-8
pii: 10.1007/s12028-022-01481-8
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
230-236Subventions
Organisme : NINDS NIH HHS
ID : R21 NS113055
Pays : United States
Organisme : NIEHS NIH HHS
ID : K01 ES026833
Pays : United States
Informations de copyright
© 2022. Springer Science+Business Media, LLC, part of Springer Nature and Neurocritical Care Society.
Références
Dorsch NW. Therapeutic approaches to vasospasm in subarachnoid hemorrhage. Curr Opin Crit Care. 2002;8(2):128–33.
doi: 10.1097/00075198-200204000-00007
Suarez JI. Diagnosis and management of subarachnoid hemorrhage. Continuum (Minneap Minn). 2015;21:1263–87. https://doi.org/10.1212/CON.0000000000000217 .
doi: 10.1212/CON.0000000000000217
pubmed: 26426230
Rowland MJ, Hadjipavlou G, Kelly M, Westbrook J, Pattinson KT. Delayed cerebral ischaemia after subarachnoid haemorrhage: looking beyond vasospasm. Br J Anaesth. 2012;109(3):315–29. https://doi.org/10.1093/bja/aes264 .
doi: 10.1093/bja/aes264
pubmed: 22879655
Francoeur CL, Mayer SA. Management of delayed cerebral ischemia after subarachnoid hemorrhage. Crit Care. 2016;20(1):277. https://doi.org/10.1186/s13054-016-1447-6 .
doi: 10.1186/s13054-016-1447-6
pubmed: 27737684
pmcid: 5064957
Lai X, Zhang W, Ye M, Liu X, Luo X. Development and validation of a predictive model for the prognosis in aneurysmal subarachnoid hemorrhage. J Clin Lab Anal. e23542.
Claassen J, Hirsch LJ, Kreiter KT, et al. Quantitative continuous EEG for detecting delayed cerebral ischemia in patients with poor-grade subarachnoid hemorrhage. Clin Neurophysiol. 2004;115(12):2699–710. https://doi.org/10.1016/j.clinph.2004.06.017 .
doi: 10.1016/j.clinph.2004.06.017
pubmed: 15546778
Roederer A, Holmes JH, Smith MJ, Lee I, Park S. Prediction of significant vasospasm in aneurysmal subarachnoid hemorrhage using automated data. Neurocrit Care. 2014;21(3):444–50. https://doi.org/10.1007/s12028-014-9976-9 .
doi: 10.1007/s12028-014-9976-9
pubmed: 24715326
Park S, Megjhani M, Frey HP, et al. Predicting delayed cerebral ischemia after subarachnoid hemorrhage using physiological time series data. J Clin Monit Comput. 2018. https://doi.org/10.1007/s10877-018-0132-5 .
doi: 10.1007/s10877-018-0132-5
pubmed: 30008089
pmcid: 6681895
Megjhani M, Terilli K, Frey HP, et al. Incorporating high-frequency physiologic data using computational dictionary learning improves prediction of delayed cerebral ischemia compared to existing methods. Front Neurol. 2018;9:122. https://doi.org/10.3389/fneur.2018.00122 .
doi: 10.3389/fneur.2018.00122
pubmed: 29563892
pmcid: 5845900
Schmidt JM, Sow D, Crimmins M, et al. Heart rate variability for preclinical detection of secondary complications after subarachnoid hemorrhage. Neurocrit Care. 2014;20(3):382–9. https://doi.org/10.1007/s12028-014-9966-y .
doi: 10.1007/s12028-014-9966-y
pubmed: 24610353
pmcid: 4436968
Ramos LA, van der Steen WE, Sales Barros R, et al. Machine learning improves prediction of delayed cerebral ischemia in patients with subarachnoid hemorrhage. J Neurointerv Surg. 2018. https://doi.org/10.1136/neurintsurg-2018-014258 .
doi: 10.1136/neurintsurg-2018-014258
pubmed: 30580284
Megjhani M, Terilli K, Weiss M, et al. Dynamic detection of delayed cerebral ischemia: a study in 3 centers. Stroke. 2021;52(4):1370–9.
doi: 10.1161/STROKEAHA.120.032546
Veldeman M, Albanna W, Weiss M, et al. Invasive multimodal neuromonitoring in aneurysmal subarachnoid hemorrhage: a systematic review. Stroke. 2021;52(11):3624–32.
doi: 10.1161/STROKEAHA.121.034633
Budohoski KP, Czosnyka M, Smielewski P, et al. Impairment of cerebral autoregulation predicts delayed cerebral ischemia after subarachnoid hemorrhage: a prospective observational study. Stroke. 2012;43(12):3230–7. https://doi.org/10.1161/strokeaha.112.669788 .
doi: 10.1161/strokeaha.112.669788
pubmed: 23150652
Weiss Miriam, Walid A, Catharina C, et al. Optimal cerebral perfusion pressure during delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage. Crit Care Med (in press). 2022
Lipton ZC, Kale DC, Elkan C, Wetzell R. Learning to Diagnose with LSTM Recurrent Neural Networks. ArXiv e-prints. 2015;1511. Accessed November 1, 2015. http://adsabs.harvard.edu/abs/2015arXiv151103677L
Xiao C, Choi E, Sun J. Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review. J Am Med Inform Assoc. 2018;25(10):1419–28.
doi: 10.1093/jamia/ocy068
Wang F, Casalino LP, Khullar D. Deep learning in medicine: promise, progress, and challenges. JAMA Intern Med. 2019;179(3):293–4.
doi: 10.1001/jamainternmed.2018.7117
Kwon SB, Park J-H, Kwon C, Kong HJ, Hwang JY, Kim HC. An energy-efficient algorithm for classification of fall types using a wearable sensor. IEEE Access. 2019;7:31321–9.
doi: 10.1109/ACCESS.2019.2902718
Connolly ES Jr, Rabinstein AA, Carhuapoma JR, et al. Guidelines for the management of aneurysmal subarachnoid hemorrhage: a guideline for healthcare professionals from the American Heart Association/american Stroke Association. Stroke. 2012;43(6):1711–37. https://doi.org/10.1161/STR.0b013e3182587839 .
doi: 10.1161/STR.0b013e3182587839
pubmed: 22556195
Steiner T, Juvela S, Unterberg A, et al. European Stroke Organization guidelines for the management of intracranial aneurysms and subarachnoid haemorrhage. Cerebrovasc Dis. 2013;35(2):93–112. https://doi.org/10.1159/000346087 .
doi: 10.1159/000346087
pubmed: 23406828
Stuart RM, Schmidt M, Kurtz P, et al. Intracranial multimodal monitoring for acute brain injury: A single institution review of current practices. Neurocrit Care. 2010;12(2):188–98. https://doi.org/10.1007/s12028-010-9330-9 .
doi: 10.1007/s12028-010-9330-9
pubmed: 20107926
Komotar RJ, Schmidt JM, Starke RM, et al. Resuscitation and critical care of poor-grade subarachnoid hemorrhage. Neurosurgery. 2009;64(3):397–410. https://doi.org/10.1227/01.NEU.0000338946.42939.C7 .
doi: 10.1227/01.NEU.0000338946.42939.C7
pubmed: 19240601
Le-Roux P, Menon DK, Citerio G, et al. The International multidisciplinary consensus conference on multimodality monitoring in neurocritical Care: a list of recommendations and additional conclusions: a statement for healthcare professionals from the Neurocritical Care Society and the European Society of Intensive Care Medicine. Neurocrit Care. 2014;21(Suppl2):282–96. https://doi.org/10.1007/s12028-014-0077-6 .
doi: 10.1007/s12028-014-0077-6
Le Roux P, Menon DK, Citerio G, et al. Consensus summary statement of the international multidisciplinary consensus conference on multimodality monitoring in neurocritical care: a statement for healthcare professionals from the neurocritical care society and the european society of intensive care medicine. Intensive Care Med. 2014;40(9):1189–209. https://doi.org/10.1007/s00134-014-3369-6 .
doi: 10.1007/s00134-014-3369-6
pubmed: 25138226
Vergouwen MD, Vermeulen M, van Gijn J, et al. Definition of delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage as an outcome event in clinical trials and observational studies: proposal of a multidisciplinary research group. Stroke. 2010;41(10):2391–5. https://doi.org/10.1161/strokeaha.110.589275 .
doi: 10.1161/strokeaha.110.589275
pubmed: 20798370
Megjhani M, Terilli K, Martin A, et al. Deriving PRx and CPPopt from 0.2 Hz data: establishing generalizability to bedmaster users. Acta Neurochir Suppl. 2017; Proceedings of Intracranial Pressure & Neuromonitoring XVI.
Zweifel C, Lavinio A, Steiner LA, et al. Continuous monitoring of cerebrovascular pressure reactivity in patients with head injury. Neurosurg Focus. 2008;25(4):E2. https://doi.org/10.3171/FOC.2008.25.10.E2 .
doi: 10.3171/FOC.2008.25.10.E2
pubmed: 18828700
Czosnyka M, Smielewski P, Kirkpatrick P, Laing RJ, Menon D, Pickard JD. Continuous assessment of the cerebral vasomotor reactivity in head injury. Neurosurgery. 1997;41(1):11–9. https://doi.org/10.1097/00006123-199707000-00005 .
doi: 10.1097/00006123-199707000-00005
pubmed: 9218290
Johnson AE, Ghassemi MM, Nemati S, Niehaus KE, Clifton DA, Clifford GD. Machine learning and decision support in critical care. Proc IEEE Inst Electr Electron Eng. 2016;104(2):444–66. https://doi.org/10.1109/jproc.2015.2501978 .
doi: 10.1109/jproc.2015.2501978
pubmed: 27765959
pmcid: 5066876