Predictive Model and Mortality Risk Score during Admission for Ischaemic Stroke with Conservative Treatment

Prädiktoren für die Folgen eines Schlaganfalls: eine systematische Literaturübersicht für GKV-Routinedatenanalysen

Zielsetzung Ermittlung unabhängiger Variablen (UVs) des Schlaganfallrezidivs, der Mortalität und der Kosten nach Schlaganfall oder transitorisch-ischämischer Attacke, abbildbar in Routinedaten der Gesetzlichen Krankenversicherung.

Methodik Durchführung einer systematischen Literaturrecherche in PubMed und Embase unter Anwendung festgelegter Auswahlkriterien.

Ergebnisse Von 1 982 Treffern wurden 23 eingeschlossen. Robuste UVs für Rezidiv und Mortalität waren Alter, Schlaganfalltyp, Diabetes mellitus und Vorhofflimmern. Bei Mortalität waren zudem Geschlecht, stationärer Aufnahmezeitpunkt und Stroke Unit-Behandlung relevant. Für Kosten war die Evidenzlage zu gering.

Schlussfolgerung Eine Übersicht zu UVs des Rezidivs und der Mortalität wurde gegeben. Folgestudien sollten einheitliche Ansätze hinsichtlich Schlaganfall- und Outcomedefinitionen sowie Evaluationszeiträumen wählen.

External Validation and Recalibration of a Mortality Prediction Model for Patients with Ischaemic Stroke

BACKGROUND

Stroke is a highly prevalent disease that can provoke severe disability. We evaluate a predictive model based on the Minimum Basic Data Set (MBDS) compiled by the Spain Health Ministry, obtained for the period 2008-2012 for patients with ischaemic stroke in Spain, to establish the model's validity and to optimise its calibration. The MBDS is the main clinical-administrative database for hospitalisations recorded in Spain, and to our knowledge, no predictive models for stroke mortality have previously been developed using this resource. The main study aim is to perform an external validation and recalibration of the coefficients of this predictive model with respect to a chronologically later cohort.

MATERIAL AND METHODS

External validation (testing the model on a different cohort to assess its performance) and recalibration (validation with optimisation of model coefficients) were performed using the MBDS for patients admitted for ischaemic stroke in the period 2016-2018. A cohort study was designed, in which a recalibrated model was obtained by applying the variables of the original model without their coefficients. The variables from the original model were then applied to the subsequent cohort, together with the coefficients from the initial model. The areas under the curve (AUC) of the recalibration and the external validation procedure were compared.

RESULTS

The recalibrated model produced an AUC of 0.743 and was composed of the following variables: age (odds ratio, OR:1.073), female sex (OR:1.143), ischaemic heart disease (OR:1.192), hypertension (OR:0.719), atrial fibrillation (OR:1.414), hyperlipidaemia (OR:0.652), heart failure (OR:2.133) and posterior circulation stroke (OR: 0.755). External validation produced an AUC of 0.726.

CONCLUSIONS

The recalibrated clinical model thus obtained presented moderate-high discriminant ability and was generalisable to predict death for patients with ischaemic stroke. Rigorous external validation slightly decreased the AUC but confirmed the validity of the baseline model for the chronologically later cohort.

The Combination of Whole-Brain Features and Local-Lesion Features in DSC-PWI May Improve Ischemic Stroke Outcome Prediction

Accurate and reliable outcome predictions can help evaluate the functional recovery of ischemic stroke patients and assist in making treatment plans. Given that recovery factors may be hidden in the whole-brain features, this study aims to validate the role of dynamic radiomics features (DRFs) in the whole brain, DRFs in local ischemic lesions, and their combination in predicting functional outcomes of ischemic stroke patients. First, the DRFs in the whole brain and the DRFs in local lesions of dynamic susceptibility contrast-enhanced perfusion-weighted imaging (DSC-PWI) images are calculated. Second, the least absolute shrinkage and selection operator (Lasso) is used to generate four groups of DRFs, including the outstanding DRFs in the whole brain (Lasso (WB)), the outstanding DRFs in local lesions (Lasso (LL)), the combination of them (combined DRFs), and the outstanding DRFs in the combined DRFs (Lasso (combined)). Then, the performance of the four groups of DRFs is evaluated to predict the functional recovery in three months. As a result, Lasso (combined) in the four groups achieves the best AUC score of 0.971, which improves the score by 8.9% compared with Lasso (WB), and by 3.5% compared with Lasso (WB) and combined DRFs. In conclusion, the outstanding combined DRFs generated from the outstanding DRFs in the whole brain and local lesions can predict functional outcomes in ischemic stroke patients better than the single DRFs in the whole brain or local lesions.

A Focus on the Role of DSC-PWI Dynamic Radiomics Features in Diagnosis and Outcome Prediction of Ischemic Stroke

Background: The ability to accurately detect ischemic stroke and predict its neurological recovery is of great clinical value. This study intended to evaluate the performance of whole-brain dynamic radiomics features (DRF) for ischemic stroke detection, neurological impairment assessment, and outcome prediction. Methods: The supervised feature selection (Lasso) and unsupervised feature-selection methods (five-feature dimension-reduction algorithms) were used to generate four experimental groups with DRF in different combinations. Ten machine learning models were used to evaluate their performance by ten-fold cross-validation. Results: In experimental group_A, the best AUCs (0.873 for stroke detection, 0.795 for NIHSS assessment, and 0.818 for outcome prediction) were obtained by outstanding DRF selected by Lasso, and the performance of significant DRF was better than the five-feature dimension-reduction algorithms. The selected outstanding dimension-reduction DRF in experimental group_C obtained a better AUC than dimension-reduction DRF in experimental group_A but were inferior to the outstanding DRF in experimental group_A. When combining the outstanding DRF with each dimension-reduction DRF (experimental group_B), the performance can be improved in ischemic stroke detection (best AUC = 0.899) and NIHSS assessment (best AUC = 0.835) but failed in outcome prediction (best AUC = 0.806). The performance can be further improved when combining outstanding DRF with outstanding dimension-reduction DRF (experimental group_D), achieving the highest AUC scores in all three evaluation items (0.925 for stroke detection, 0.853 for NIHSS assessment, and 0.828 for outcome prediction). By the method in this study, comparing the best AUC of Ft-test in experimental group_A and the best_AUC in experimental group_D, the AUC in stroke detection increased by 19.4% (from 0.731 to 0.925), the AUC in NIHSS assessment increased by 20.1% (from 0.652 to 0.853), and the AUC in prognosis prediction increased by 14.9% (from 0.679 to 0.828). This study provided a potential clinical tool for detailed clinical diagnosis and outcome prediction before treatment.

Novel Survival Features Generated by Clinical Text Information and Radiomics Features May Improve the Prediction of Ischemic Stroke Outcome

BACKGROUND

Accurate outcome prediction is of great clinical significance in customizing personalized treatment plans, reducing the situation of poor recovery, and objectively and accurately evaluating the treatment effect. This study intended to evaluate the performance of clinical text information (CTI), radiomics features, and survival features (SurvF) for predicting functional outcomes of patients with ischemic stroke.

METHODS

SurvF was constructed based on CTI and mRS radiomics features (mRSRF) to improve the prediction of the functional outcome in 3 months (90-day mRS). Ten machine learning models predicted functional outcomes in three situations (2-category, 4-category, and 7-category) using seven feature groups constructed by CTI, mRSRF, and SurvF.

RESULTS

For 2-category, ALL (CTI + mRSRF+ SurvF) performed best, with an mAUC of 0.884, mAcc of 0.864, mPre of 0.877, mF1 of 0.86, and mRecall of 0.864. For 4-category, ALL also achieved the best mAuc of 0.787, while CTI + SurvF achieved the best score with mAcc = 0.611, mPre = 0.622, mF1 = 0.595, and mRe-call = 0.611. For 7-category, CTI + SurvF performed best, with an mAuc of 0.788, mPre of 0.519, mAcc of 0.529, mF1 of 0.495, and mRecall of 0.47.

CONCLUSIONS

The above results indicate that mRSRF + CTI can accurately predict functional outcomes in ischemic stroke patients with proper machine learning models. Moreover, combining SurvF will improve the prediction effect compared with the original features. However, limited by the small sample size, further validation on larger and more varied datasets is necessary.