A Big-Data Variational Bayesian Framework for Supporting the Prediction of Functional Outcomes in Wake-Up Stroke Patients

Prognosis in Wake-up ischemic stroke (WUS) is important for guiding treatment and rehabilitation strategies, in order to improve recovery and minimize disability. For this reason, there is growing interest on models to predict functional recovery after acute ischemic events in order to personalize the therapeutic intervention and improve the final functional outcome. The aim of this preliminary study is to evaluate the possibility to predict a good functional outcome, in terms of modified Rankin Scale (mRS ≤ 2), in thrombolysis treated WUS patients by Bayesian analysis of clinical, demographic and neuroimaging data at admission. The study was conducted on 54 thrombolysis treated WUS patients. The Variational Bayesian logistic regression with Automatic Relevance Determination (VB-ARD) was used to produce model and select informative features to predict a good functional outcome (mRS ≤ 2) at discharge. The produced model showed moderately high 10 × 5-fold cross validation accuracy of 71% to predict outcome. The sparse model highlighted the relevance of NIHSS at admission, age, TACI stroke syndrome, ASPECTs, ischemic core CT Perfusion volume, hypertension and diabetes mellitus. In conclusion, in this preliminary study we assess the possibility to model the prognosis in thrombolysis treated WUS patients by using VB ARD. The identified features related to initial neurological deficit, history of diabetes and hypertension, together with necrotic tissue relate ASPECT and CTP core volume neuroimaging features, were able to predict outcome with moderately high accuracy.

[1]  J. Bamford,et al.  Classification and natural history of clinically identifiable subtypes of cerebral infarction , 1991, The Lancet.

[2]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[3]  Joseph P. Broderick,et al.  Tissue plasminogen activator for acute ischemic stroke. The National Institute of Neurological Disorders and Stroke rt-PA Stroke Study Group. , 1995 .

[4]  Koroshetz Wj,et al.  Tissue plasminogen activator for acute ischemic stroke. , 1996, The New England journal of medicine.

[5]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[6]  W R Clarke,et al.  Baseline NIH Stroke Scale score strongly predicts outcome after stroke , 1999, Neurology.

[7]  A. Demchuk,et al.  Validity and reliability of a quantitative computed tomography score in predicting outcome of hyperacute stroke before thrombolytic therapy , 2000, The Lancet.

[8]  Michael I. Jordan,et al.  Bayesian parameter estimation via variational methods , 2000, Stat. Comput..

[9]  Michael E. Tipping.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001, J. Mach. Learn. Res..

[10]  A. Ziegler,et al.  Age and National Institutes of Health Stroke Scale Score Within 6 Hours After Onset Are Accurate Predictors of Outcome After Cerebral Ischemia: Development and External Validation of Prognostic Models , 2003, Stroke.

[11]  Reto Meuli,et al.  Perfusion-CT Assessment of Infarct Core and Penumbra: Receiver Operating Characteristic Curve Analysis in 130 Patients Suspected of Acute Hemispheric Stroke , 2006, Stroke.

[12]  Alfredo Cuzzocrea,et al.  Combining multidimensional user models and knowledge representation and management techniques for making web services knowledge-aware , 2006, Web Intell. Agent Syst..

[13]  Domenico Consoli,et al.  Risk factors and outcome of subtypes of ischemic stroke. Data from a multicenter multinational hospital-based registry. The European Community Stroke Project , 2006, Journal of the Neurological Sciences.

[14]  D. Ashby.  Bayesian statistics in medicine: a 25 year review , 2006, Statistics in medicine.

[15]  Jamie L Banks,et al.  Outcomes Validity and Reliability of the Modified Rankin Scale: Implications for Stroke Clinical Trials: A Literature Review and Synthesis , 2007, Stroke.

[16]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[17]  Nobuhiko Omori,et al.  High blood pressure in acute ischemic stroke and clinical outcome , 2009, Neurology international.

[18]  Alfredo Cuzzocrea,et al.  Privacy Preserving OLAP and OLAP Security , 2009, Encyclopedia of Data Warehousing and Mining.

[19]  Scott Hamilton,et al.  Improving the Reliability of Stroke Disability Grading in Clinical Trials and Clinical Practice: The Rankin Focused Assessment (RFA) , 2010, Stroke.

[20]  B. Blankertz,et al.  (C)overt attention and visual speller design in an ERP-based brain-computer interface , 2010, Behavioral and Brain Functions.

[21]  R. Hornung,et al.  Population-based study of wake-up strokes , 2011, Neurology.

[22]  Paul Zikopoulos,et al.  Understanding Big Data: Analytics for Enterprise Class Hadoop and Streaming Data , 2011 .

[23]  Elisa Bertino,et al.  Privacy Preserving OLAP over Distributed XML Data: A Theoretically-Sound Secure-Multiparty-Computation Approach , 2011, J. Comput. Syst. Sci..

[24]  Jeffrey L. Saver,et al.  Relationship Between Neurologic Deficit Severity and Final Functional Outcome Shifts and Strengthens During First Hours After Onset , 2012, Stroke.

[25]  Pierre Amarenco,et al.  Diabetes Mellitus, Admission Glucose, and Outcomes After Stroke Thrombolysis: A Registry and Systematic Review , 2013, Stroke.

[26]  Guandong Xu,et al.  OLAP*: Effectively and Efficiently Supporting Parallel OLAP over Big Data , 2013, MEDI.

[27]  Dimitrios Gunopulos,et al.  A novel distributed framework for optimizing query routing trees in wireless sensor networks via optimal operator placement , 2013, J. Comput. Syst. Sci..

[28]  Jan Drugowitsch.  Variational Bayesian inference for linear and logistic regression , 2013, 1310.5438.

[29]  Ivana Galinovic,et al.  A Multicenter, Randomized, Double-Blind, Placebo-Controlled Trial to Test Efficacy and Safety of Magnetic Resonance Imaging-Based Thrombolysis in Wake-up Stroke (WAKE-UP) , 2014, International journal of stroke : official journal of the International Stroke Society.

[30]  Babak Shahbaba,et al.  Neural function, injury, and stroke subtype predict treatment gains after stroke , 2015, Annals of neurology.

[31]  Yeong-Bae Lee,et al.  Predicting stroke outcome using clinical- versus imaging-based scoring system. , 2015, Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association.

[32]  Cheryl Ann Alexander,et al.  Stroke Care and the Role of Big Data in Healthcare and Stroke , 2016 .

[33]  K. Iihara,et al.  Status and Future Perspectives of Utilizing Big Data in Neurosurgical and Stroke Research , 2016, Neurologia medico-chirurgica.

[34]  Pedro Vilela,et al.  Brain ischemia: CT and MRI techniques in acute ischemic stroke. , 2017, European journal of radiology.

[35]  P. Widimsky,et al.  Acute stroke therapy: A review. , 2017, Trends in cardiovascular medicine.

[36]  Paolo Manganotti,et al.  Ischemic Volume and Neurological Deficit: Correlation of Computed Tomography Perfusion with the National Institutes of Health Stroke Scale Score in Acute Ischemic Stroke. , 2018, Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association.

[37]  Ana Catarina Fonseca,et al.  Quantitative EEG and functional outcome following acute ischemic stroke , 2018, Clinical Neurophysiology.

[38]  Christopher Levi,et al.  Tissue Is More Important than Time in Stroke Patients Being Assessed for Thrombolysis , 2018, Front. Neurol..

[39]  A. Rigas,et al.  A Bayesian Logistic Regression approach in Asthma Persistence Prediction , 2018, Epidemiology Biostatistics and Public Health.

[40]  Paolo Manganotti,et al.  Wake-up stroke and CT perfusion: effectiveness and safety of reperfusion therapy , 2018, Neurological Sciences.

[41]  Paolo Manganotti,et al.  Brain oscillatory activity and CT perfusion in hyper-acute ischemic stroke , 2019, Journal of Clinical Neuroscience.

[42]  P. Gorelick,et al.  The global burden of stroke: persistent and disabling , 2019, The Lancet Neurology.

[43]  Min Lou,et al.  Influence of occlusion site and baseline ischemic core on outcome in patients with ischemic stroke , 2019, Neurology.

[44]  Paolo Manganotti,et al.  Wake-up stroke: thrombolysis reduces ischemic lesion volume and neurological deficit , 2019, Journal of Neurology.

[45]  Agostino Accardo,et al.  Slow Cortical Potential BCI Classification Using Sparse Variational Bayesian Logistic Regression with Automatic Relevance Determination , 2019, IFMBE Proceedings.

[46]  Extend Investigators,et al.  Thrombolysis Guided by Perfusion Imaging up to 9 Hours after Onset of Stroke. , 2019, The New England journal of medicine.

[47]  J. Jeng,et al.  Thrombolysis Guided by Perfusion Imaging up to 9 Hours after Onset of Stroke , 2019, The New England journal of medicine.

[48]  Paolo Manganotti,et al.  A novel computed tomography perfusion-based quantitative tool for evaluation of perfusional abnormalities in migrainous aura stroke mimic , 2020, Neurological Sciences.

[49]  P. Manganotti,et al.  A CT perfusion based model predicts outcome in wake-up stroke patients treated with recombinant tissue plasminogen activator , 2020, Physiological measurement.

[50]  Agostino Accardo,et al.  A CT perfusion based model predicts outcome in wake-up stroke patients treated with recombinant tissue plasminogen activator , 2020, Physiological Measurement.

[51]  Paolo Manganotti,et al.  Thrombolysis safety and effectiveness in acute ischemic stroke patients with pre-morbid disability , 2019, Journal of Clinical Neuroscience.