Development and validation of outcome prediction model for reperfusion therapy in acute ischemic stroke using nomogram and machine learning.

OBJECTIVE: To develop logistic regression nomogram and machine learning (ML)-based models to predict 3-month unfavorable functional outcome for acute ischemic stroke (AIS) patients undergoing reperfusion therapy. METHODS: Patients undergoing reperfusion therapy (intravenous thrombolysis and/or endovascular treatment) were prospectively recruited. Unfavorable outcome was defined as 3-month modified Rankin Scale (mRS) score 3-6. The independent risk factors associated with unfavorable outcome were obtained by regression analysis and included in the prediction model. The performance of nomogram was assessed by the area under the curve (AUC), calibration curve, and decision curve analysis (DCA). ML models were compared with nomogram using AUC; the generalizability of all models was ascertained in an external cohort. RESULTS: A total of 505 patients were enrolled, with 256 in the model construction, and 249 in the external validation. Five variables were identified as prognostic factors: baseline NIHSS, D-dimer level, random blood glucose (RBG), blood urea nitrogen (BUN), and systolic blood pressure (SBP) before reperfusion. The AUC values of nomogram were 0.865, 0.818, and 0.779 in the training set, test set, and external validation, respectively. The calibration curve and DCA indicated appreciable reliability and good net benefits. The best three ML models were extra trees (ET), CatBoost, and random forest (RF) models; all of them showed favorable discrimination in the training cohort, and confirmed in the test and external sets. CONCLUSION: Baseline NIHSS, D-dimer, RBG, BUN, and SBP before reperfusion were independent predictors for 3-month unfavorable outcome after reperfusion therapy in AIS patients. Both nomogram and ML models showed good discrimination and generalizability.

ANRIL overexpression globally induces expression and alternative splicing of genes involved in inflammation in HUVECs.

Long non­coding (lnc)RNAs serve important cellular functions and certain lncRNAs have roles in different mechanisms of gene regulation. lncRNA­antisense non­coding RNA in the INK4 locus (ANRIL) affects cell inflammation; however, the potential genes underlying the inflammatory response regulated by ANRIL remain unclear. In the present study, the potential function of ANRIL in regulating gene expression and alternative splicing was assessed. ANRIL­regulated human umbilical vein endothelial cell (HUVEC) transcriptome was obtained using high­throughput RNA sequencing (RNA­seq) to evaluate the potential role of ANRIL. Following plasmid transfection, gene expression profile and alternative splicing pattern of HUVECs overexpressing ANRIL were analyzed using RNA­seq. ANRIL overexpression affected the transcription levels of genes associated with the inflammatory response, NF­κB signaling pathway, type I interferon­mediated signal transduction pathway and innate immune response. ANRIL regulated the alternative splicing of hundreds of genes with functions such as gene expression, translation, DNA repair, RNA processing and participation in the NF­κB signaling pathway. Many of these genes serve a key role in the inflammatory response. ANRIL­regulated inflammatory response may be achieved by regulating alternate splicing and transcription. The present study broadened the understanding of ANRIL­mediated gene regulation mechanisms and clarified the role of ANRIL in mediating inflammatory response mechanisms.

Impact of collateral circulation status on favorable outcomes in thrombolysis treatment: A systematic review and meta-analysis.

Collateral circulation affects the prognosis of patients with acute ischemic stroke (AIS) treated by thrombolysis. The present study performed a systematic assessment of the impact of the collateral circulation status on the outcomes of patients receiving thrombolysis treatment. Relevant full-text articles from the Cochrane Library, Ovid, Medline, Embase and PubMed databases published from January 1, 2000 to November 1, 2016 were retrieved. The quality of the studies was assessed and data were extracted by 2 independent investigators. The random-effects model was used to estimate the impact of good vs. poor collateral circulation, as well as baseline characteristics, on the outcome within the series presented as risk ratios. Subgroup analyses explored the potential factors that may interfere with the effects of the collateral circulation status on the outcome. A total of 29 studies comprising 4,053 patients were included in the present meta-analysis. A good collateral circulation status was revealed to have a beneficial effect on favorable functional outcome (modified Rankin scale, 0-3 at 3-6 months; P<0.001) and a higher rate of recanalization (P<0.001) compared with poor collateral circulation. Good collateral circulation was also associated with a lower rate of symptomatic intracranial hemorrhage (P<0.01), a lower rate of mortality (P<0.01) and a smaller infarct size (P<0.01). In conclusion, good collateral circulation was demonstrated to have a favorable prognostic value regarding the outcome for patients with AIS receiving thrombolysis treatment. Assessment of collateral circulation and penumbra area during pre-treatment imaging within an appropriate time-window prior to thrombolytic therapy will therefore improve the identification of AIS patients who may benefit from thrombolysis treatment.