26
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Population-Based Stroke Atlas for Outcome Prediction: Method and Preliminary Results for Ischemic Stroke from CT

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Background and Purpose

          Knowledge of outcome prediction is important in stroke management. We propose a lesion size and location-driven method for stroke outcome prediction using a Population-based Stroke Atlas (PSA) linking neurological parameters with neuroimaging in population. The PSA aggregates data from previously treated patients and applies them to currently treated patients. The PSA parameter distribution in the infarct region of a treated patient enables prediction. We introduce a method for PSA calculation, quantify its performance, and use it to illustrate ischemic stroke outcome prediction of modified Rankin Scale (mRS) and Barthel Index (BI).

          Methods

          The preliminary PSA was constructed from 128 ischemic stroke cases calculated for 8 variants (various data aggregation schemes) and 3 case selection variables (infarct volume, NIHSS at admission, and NIHSS at day 7), each in 4 ranges. Outcome prediction for 9 parameters (mRS at 7th, and mRS and BI at 30th, 90th, 180th, 360th day) was studied using a leave-one-out approach, requiring 589,824 PSA maps to be analyzed.

          Results

          Outcomes predicted for different PSA variants are statistically equivalent, so the simplest and most efficient variant aiming at parameter averaging is employed. This variant allows the PSA to be pre-calculated before prediction. The PSA constrained by infarct volume and NIHSS reduces the average prediction error (absolute difference between the predicted and actual values) by a fraction of 0.796; the use of 3 patient-specific variables further lowers it by 0.538. The PSA-based prediction error for mild and severe outcomes (mRS =  [2][5]) is (0.5–0.7). Prediction takes about 8 seconds.

          Conclusions

          PSA-based prediction of individual and group mRS and BI scores over time is feasible, fast and simple, but its clinical usefulness requires further studies. The case selection operation improves PSA predictability. A multiplicity of PSAs can be computed independently for different datasets at various centers and easily merged, which enables building powerful PSAs over the community.

          Related collections

          Most cited references32

          • Record: found
          • Abstract: found
          • Article: not found

          Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration.

          All fields of neuroscience that employ brain imaging need to communicate their results with reference to anatomical regions. In particular, comparative morphometry and group analysis of functional and physiological data require coregistration of brains to establish correspondences across brain structures. It is well established that linear registration of one brain to another is inadequate for aligning brain structures, so numerous algorithms have emerged to nonlinearly register brains to one another. This study is the largest evaluation of nonlinear deformation algorithms applied to brain image registration ever conducted. Fourteen algorithms from laboratories around the world are evaluated using 8 different error measures. More than 45,000 registrations between 80 manually labeled brains were performed by algorithms including: AIR, ANIMAL, ART, Diffeomorphic Demons, FNIRT, IRTK, JRD-fluid, ROMEO, SICLE, SyN, and four different SPM5 algorithms ("SPM2-type" and regular Normalization, Unified Segmentation, and the DARTEL Toolbox). All of these registrations were preceded by linear registration between the same image pairs using FLIRT. One of the most significant findings of this study is that the relative performances of the registration methods under comparison appear to be little affected by the choice of subject population, labeling protocol, and type of overlap measure. This is important because it suggests that the findings are generalizable to new subject populations that are labeled or evaluated using different labeling protocols. Furthermore, we ranked the 14 methods according to three completely independent analyses (permutation tests, one-way ANOVA tests, and indifference-zone ranking) and derived three almost identical top rankings of the methods. ART, SyN, IRTK, and SPM's DARTEL Toolbox gave the best results according to overlap and distance measures, with ART and SyN delivering the most consistently high accuracy across subjects and label sets. Updates will be published on the http://www.mindboggle.info/papers/ website.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Predicting the risk of symptomatic intracerebral hemorrhage in ischemic stroke treated with intravenous alteplase: safe Implementation of Treatments in Stroke (SITS) symptomatic intracerebral hemorrhage risk score.

            Symptomatic intracerebral hemorrhage (SICH) is a serious complication in patients with acute ischemic stroke treated with intravenous thrombolysis. We aimed to develop a clinical score that can easily be applied to predict the risk of SICH. We analyzed data from 31 627 patients treated with intravenous alteplase enrolled in the Safe Implementation of Treatments in Stroke (SITS) International Stroke Thrombolysis Register. The outcome measure was SICH per the Safe Implementation of Thrombolysis in Stroke-Monitoring Study (SITS-MOST) definition: a Type 2 parenchymal hemorrhage with deterioration in National Institutes of Health Stroke Scale score of ≥ 4 points or death. Univariate risk factors associated with the outcome were entered into a logistic regression model after stratification of continuous variables. Adjusted ORs for the independent risk factors were converted into points, which were summated to produce a risk score. We identified 9 independent risk factors for SICH: baseline National Institutes of Health Stroke Scale, serum glucose, systolic blood pressure, age, body weight, stroke onset to treatment time, aspirin or combined aspirin and clopidogrel, and history of hypertension. The overall rate of SICH was 1.8%. The risk score ranged from 0 to 12 points and showed a >70-fold graded increase in the rate of SICH for patients with a score ≥ 10 points (14.3%) compared with a score of 0 point (0.2%). The prognostic discriminating capability by C statistic was 0.70. The SITS SICH risk score predicts large cerebral parenchymal hemorrhages associated with severe clinical deterioration. The score could aid clinicians to identify patients at high as well as low risk of SICH after intravenous alteplase.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Stroke Prognostication using Age and NIH Stroke Scale: SPAN-100.

              Age and stroke severity are major determinants of stroke outcomes, but systematically incorporating these prognosticators in the routine practice of acute ischemic stroke can be challenging. We evaluated the effect of an index combining age and stroke severity on response to IV tissue plasminogen activator (tPA) among patients in the National Institute of Neurological Disorders and Stroke (NINDS) tPA stroke trials. We created the Stroke Prognostication using Age and NIH Stroke Scale (SPAN) index by combining age in years plus NIH Stroke Scale (NIHSS) ≥100. We applied the SPAN-100 index to patients in the NINDS tPA stroke trials (parts I and II) to evaluate its ability to predict clinical response and risk of intracerebral hemorrhage (ICH) after thrombolysis. The main outcome measures included ICH (any type) and a composite favorable outcome (defined as a modified Rankin Scale score of 0 or 1, NIHSS ≤1, Barthel index ≥95, and Glasgow Outcome Scale score of 1) at 3 months. Bivariate and multivariable logistic regression analyses were used to determine the association between SPAN-100 and outcomes of interest. Among 624 patients in the NINDS trials, 62 (9.9%) participants were SPAN-100 positive. Among those receiving tPA, ICH rates were higher for SPAN-100-positive patients (42% vs 12% in SPAN-100-negative patients; p < 0.001); similarly, ICH rates were higher in SPAN-100-positive patients (19% vs 5%; p = 0.005) among those not receiving tPA. SPAN-100 was associated with worse outcomes. The benefit of tPA, defined as favorable composite outcome at 3 months, was present in SPAN-100-negative patients (55.4% vs 40.2%; p < 0.001), but not in SPAN-100-positive patients (5.6% tPA vs 3.9%; p = 0.76). Similar trends were found for secondary outcomes (e.g., symptomatic ICH, catastrophic outcome, discharge home). The SPAN-100 index could be a simple method for estimating the clinical response and risk of hemorrhagic complications after tPA for acute ischemic stroke. These results need further confirmation in larger contemporary datasets.
                Bookmark

                Author and article information

                Contributors
                Role: Editor
                Journal
                PLoS One
                PLoS ONE
                plos
                plosone
                PLoS ONE
                Public Library of Science (San Francisco, USA )
                1932-6203
                2014
                14 August 2014
                : 9
                : 8
                : e102048
                Affiliations
                [1 ]Biomedical Imaging Lab, Singapore Bioimaging Consortium, Agency for Science Technology and Research, Singapore, Singapore
                [2 ]Department of Neurology, Poznan University of Medical Sciences, Poznan, Poland
                [3 ]Department of Neurology and Cerebrovascular Disorders (L. Bierkowski Hospital), Poznan University of Medical Sciences, Poznan, Poland
                INSERM U894, Centre de Psychiatrie et Neurosciences, Hopital Sainte-Anne and Université Paris 5, France
                Author notes

                Competing Interests: The authors have declared that no competing interests exist.

                Conceived and designed the experiments: WLN VG. Performed the experiments: WLN VG GQ. Analyzed the data: VG GQ RK WLN. Contributed reagents/materials/analysis tools: RK WA GQ VG WLN. Wrote the paper: WLN VG GQ WA RK.

                Article
                PONE-D-14-07004
                10.1371/journal.pone.0102048
                4133199
                25121979
                90a7a054-7b6c-4833-9b3b-a5aac0655cf4
                Copyright @ 2014

                This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

                History
                : 14 February 2014
                : 15 June 2014
                Page count
                Pages: 11
                Funding
                This research was funded by Biomedical Research Council, Agency for Science, Technology and Research ASTAR, Singapore. The data contribution to this study was a part of a joined Polish-Singaporean project funded by the Ministry of Science and Higher Education, Poland and ASTAR, Singapore (project No. 62/N-Singapur/2007/0 and 072-1340049). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
                Categories
                Research Article
                Biology and Life Sciences
                Astrobiology
                Computer and Information Sciences
                Computerized Simulations
                Medicine and Health Sciences
                Critical Care and Emergency Medicine
                Neurology
                Radiology and Imaging
                Physical Sciences
                Astronomical Sciences
                Mathematics
                Applied Mathematics
                Algorithms
                Statistics (Mathematics)

                Uncategorized
                Uncategorized

                Comments

                Comment on this article