MétaCan
Menu
← Back to cohort
Record W2603635611 · doi:10.1161/str.47.suppl_1.161

Abstract 161: Prediction of Thrombolysis-induced Parenchymal Hemorrhage in Patients With Acute Ischemic Stroke: Use of MR Perfusion and Diffusion Biomarkers

2016· article· en· W2603635611 on OpenAlexaff
Kambiz Nael, James R. Knitter, Reza Jahan, Jeffry R. Alger, Val Nenov, Zahra Ajani, Lei Feng, Brett C. Meyer, Scott Olson, Lee H. Schwamm, Albert J. Yoo, Randolph S. Marshall, Philip M. Meyers, Dileep R. Yavagal, Max Wintermark, David S. Liebeskind, Judy Guzy, Jeffrey L. Saver, Chelsea S. Kidwell

Bibliographic record

VenueStroke · 2016
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsStuart Olson (Canada)
Fundersnot available
KeywordsMedicineThrombolysisReceiver operating characteristicEffective diffusion coefficientInfarctionUnivariate analysisStroke (engine)Logistic regressionInternal medicineArea under the curvePenumbraPerfusion scanningDiffusion MRINuclear medicinePerfusionCardiologyRadiologyMultivariate analysisMagnetic resonance imagingIschemiaMyocardial infarction

Abstract

fetched live from OpenAlex

Purpose: Ischemic stroke patients with low cerebral blood volume (CBV), low apparent diffusion coefficient (ADC) and increased microvascular permeability (K2) have increased risk of parenchymal hemorrhage (PH) after recanalization therapies. We have developed a predictive model to examine the risk of PH following revascularization therapies using combined MR perfusion and diffusion biomarkers. Methods: Voxel-based values of rCBV, K2, and ADC from the infarction core were obtained using pre-treatment MRI data from patients enrolled in the Mechanical Retrieval and Recanalization of Stroke Clots Using Embolectomy (MR RESCUE) clinical trial. Using histogram analyses the 10 th and 90 th percentile values were calculated for the rCBV, ADC, and K2 variables for each patient. The associations between PH and extreme values of CBV (10%rCBV), ADC (10%ADC), and K2 (90%K2) in each patient were assessed in univariate and multivariate analyses. Receiver operating characteristic (ROC) analysis was performed to determine the optimal parameter/s and threshold for predicting PH. Results: In 83 patients included in this analysis, 20 (24%, 13 PH1, 7 PH2) developed PH. Univariate analysis showed significantly lower 10%rCBV and 10%ADC values and significantly higher 90%K2 values in patients with PH. After controlling for age, baseline NIHSS, infarct volume, and status of recanalization, multivariate logistic regression analysis identified 10%rCBV (p=0.002) and 90%K2 (p=0.03), but not 10%ADC (p=0.07), as independent predictors of PH. For 10%RCBV, ROC analysis showed the greatest AUC (0.87) at a threshold < 0.45 with sensitivity/specificity of 95%70%. For 90%K2, the greatest AUC (0.75) was obtained at a threshold of > 0.27 with sensitivity/specificity of 90%/60%. In a separate model, a combined K2-rCBV classifier remained the single independent predictor of PH (OR=33). Conclusion: Our results suggest that combined increased permeability and decreased rCBV derived from MR perfusion can be used for risk stratification in patients with AIS before undergoing revascularization therapies.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.003
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.001
Threshold uncertainty score0.005

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.009
GPT teacher head0.237
Teacher spread0.228 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2016
Admission routes1
Has abstractyes

Explore more

Same venueStroke→Same topicRadiomics and Machine Learning in Medical Imaging→French-language works237,207→