急性缺血性卒中静脉溶栓后症状性颅内出血预测模型的系统评价

doi:10.3969/j.issn.1673-5765.2024.01.011

摘要/Abstract

摘要： 目的系统评价急性缺血性卒中静脉溶栓后症状性颅内出血预测模型的特征，为静脉溶栓临床决策提供参考。
方法检索中国知网、万方数据知识服务平台、维普资讯、PubMed、Embase、Web of Science和The Cochrane Library数据库，收集急性缺血性卒中静脉溶栓后症状性颅内出血预测模型相关研究信息，检索时限为建库至2022年12月18日。由2位研究员独立筛选文献、提取资料并评价偏倚风险后对纳入模型的基本特征和方法论进行系统评价。
结果纳入20项研究，共30个预测模型。纳入模型ROC曲线的AUC值范围为0.42～0.94。24个（80%）预测模型的整体预测性能较好，模型对不同结局的定义和算法的区分度有明显差异。最常见的预测因子包括NIHSS评分、年龄、梗死的影像学征象或评分、血糖、收缩压和抗血小板药物。
结论急性缺血性卒中静脉溶栓后症状性颅内出血预测模型呈现出建模算法多样化、模型性能更佳化、预测因素多元化等特点，但总体偏倚风险较高，未来研究还需要进一步校准模型。此外，应更加关注模型的更新与外部验证，提高其外推性及临床效用，从而发挥模型更大的临床价值。

文章导读： 本研究从症状性颅内出血定义和建模算法的角度，系统评价了急性缺血性卒中静脉溶栓后症状性颅内出血预测模型的性能，并通过箱图进行准确、清晰、直观的呈现，发现采用欧洲协作急性卒中研究标准和机器学习算法的模型性能更佳。

关键词: 急性缺血性卒中; 静脉溶栓; 症状性颅内出血; 预测模型; 系统评价

Abstract: Objective To systematically evaluate the prediction models of symptomatic intracerebral hemorrhage after intravenous thrombolysis in acute ischemic stroke and to provide a reference for clinical decision-making of intravenous thrombolysis.
Methods CNKI, WanFang Data, VIP, PubMed, Embase, Web of Science, and The Cochrane Library databases were searched to collect relevant studies, with a timeframe for searching the database from the establishment of the database to December 18, 2022. Two researchers independently screened the literature, extracted the data, assessed the risk of bias, and then systematically evaluated the basic characteristics and methodology of the included models.
Results Twenty studies were included, with a total of 30 prediction models. The AUC of the included models ranged from 0.42 to 0.94. The overall predictive performance of the 24 (80%) prediction models was good, with significant differences in model differentiation across outcome definitions and algorithms. The most common predictors were NIHSS score, age, imaging signs or scores of infarction, blood glucose, systolic blood pressure, and antiplatelet drugs.
Conclusions In recent years, the prediction models of symptomatic intracerebral hemorrhage after intravenous thrombolysis in acute ischemic stroke have shown the characteristics of diversified modeling algorithms, better model performance, and diversified predictors. However, the overall risk of bias was high, and future studies need to calibrate the models further. More attention should be paid to updating and externally validating the models to improve extrapolation and clinical utility and utilize the models’ clinical practice implications.

Key words: Acute ischemic stroke; Intravenous thrombolysis; Symptomatic intracerebral hemorrhage; Prediction model; Systematic review

中图分类号:

杨嘉欣, 何春渝, 刘蕾, 陈文博, 谢艳. 急性缺血性卒中静脉溶栓后症状性颅内出血预测模型的系统评价[J]. 中国卒中杂志, 2024, 19(1): 76-86.

YANG Jiaxin, HE Chunyu, LIU Lei, CHEN Wenbo, XIE Yan. Prediction Models of Symptomatic Intracerebral Hemorrhage after Intravenous Thrombolysis in Acute Ischemic Stroke: A Systematic Review[J]. Chinese Journal of Stroke, 2024, 19(1): 76-86.

参考文献

[1] GBD 2019 Stroke Collaborators. Global，regional，and national burden of stroke and its risk factors，1990—2019：a systematic analysis for the global burden of disease study 2019[J]. Lancet Neurol，2021，20（10）：795-820.
[2] POWERS W J，RABINSTEIN A A，ACKERSON T，et al. Guidelines for the early management of patients with acute ischemic stroke：2019 update to the 2018 guidelines for the early management of acute ischemic stroke：a guideline for healthcare professionals from the American Heart Association/American Stroke Association[J/OL].
Stroke，2019，50（12）：e344-e418[2023-06-11]. https://doi.org/10.1161/STR.0000000000000211.
[3] BERGER C，FIORELLI M，STEINER T，et al. Hemorrhagic transformation of ischemic brain tissue：asymptomatic or symptomatic？[J]. Stroke，2001，32（6）：1330-1335.
[4] YAGHI S，WILLEY J Z，CUCCHIARA B，et al. Treatment and outcome of hemorrhagic transformation after intravenous alteplase in acute ischemic stroke：a scientific statement for healthcare professionals from the American Heart Association/American Stroke Association[J/OL].
Stroke，2017，48（12）：e343-e361[2023-06-11].
https://doi.org/10.1161/STR.0000000000000152.
[5] HONIG A，PERCY J，SEPEHRY A A，et al. Hemorrhagic transformation in acute ischemic stroke：a quantitative systematic review[J/OL]. J Clin Med，2022，11（5）：1162[2023-05-13]. https://doi.org/10.3390/jcm11051162.
[6] KAMAL H，LOPEZ V，SHETH S A. Machine learning in acute ischemic stroke neuroimaging
[J/OL]. Front Neurol，2018，9：945[2023-05-13]. https://doi.org/10.3389/fneur.2018.00945.
[7] SUNG S M，KANG Y J，CHO H J，et al. Prediction of early neurological deterioration in acute minor ischemic stroke by machine learning algorithms[J/OL]. Clin Neurol Neurosurg，2020，195：105892[2023-05-13]. https://doi.org/10.1016/j.clineuro.2020.105892.
[8] PAGE M J，MCKENZIE J E，BOSSUYT P M，et al. The PRISMA 2020 statement：an updated guideline for reporting systematic reviews[J/OL]. BMJ，2021，372：n71[2023-05-13]. https://doi.org/10.1136/bmj.n71.
[9] MOONS K G，DE GROOT J A，BOUWMEESTER W，et al. Critical appraisal and data extraction for systematic reviews of prediction modelling studies：the CHARMS checklist[J/OL]. PLoS Med，
2014，11（10）：e1001744[2023-05-13]. https://doi.org/10.1371/journal.pmed.1001744.
[10] WOLFF R F，MOONS K G M，RILEY R D，et al. PROBAST：a tool to assess the risk of bias and applicability of prediction model studies[J]. Ann Intern Med，2019，170（1）：51-58.
[11] 陈香萍，张奕，庄一渝，等. PROBAST：诊断或预后多因素预测模型研究偏倚风险的评估工具[J]. 中国循证医学杂志，2020，20（6）：737-744.
CHEN X P，ZHANG Y，ZHUANG Y Y，et al. PROBAST：a tool for assessing risk of bias in the study of diagnostic or prognostic multi-factorial predictive models[J]. Chin J Evid-Based Med，2020，20（6）：737-744.
[12] National Institute of Neurological Disorders and Stroke rt-PA Stroke Study Group. Tissue plasminogen activator for acute ischemic stroke[J]. N Engl J Med，1995，333（24）：1581-1587.
[13] HACKE W，KASTE M，FIESCHI C，et al. Randomised double-blind placebo-controlled trial of thrombolytic therapy with intravenous alteplase in acute ischaemic stroke（ECASS Ⅱ）[J]. Lancet，1998，352（9136）：1245-1251.
[14] HACKE W，KASTE M，BLUHMKI E，et al. Thrombolysis with alteplase 3 to 4.5 hours after acute ischemic stroke[J]. N Engl J Med，2008，359（13）：1317-1329.
[15] WAHLGREN N，AHMED N，DÁVALOS A，et al. Thrombolysis with alteplase for acute ischaemic stroke in the safe implementation of thrombolysis in stroke-monitoring study（SITS-MOST）：an observational study[J]. Lancet，2007，369（9558）：275-282.
[16] ASUZU D，NYSTRÖM K，AMIN H，et al. TURN：a simple predictor of symptomatic intracerebral hemorrhage after Ⅳ thrombolysis[J]. Neurocrit Care，2015，23（2）：166-171.
[17] CAPPELLARI M，TURCATO G，FORLIVESI S，et al. STARTING-SICH nomogram to predict symptomatic intracerebral hemorrhage after intravenous thrombolysis for stroke[J]. Stroke，2018，49（2）：397-404.
[18] CHUNG C C，CHAN L，BAMODU O A，et al. Artificial neural network based prediction of postthrombolysis intracerebral hemorrhage and death[J/OL]. Scientific reports，2020，10（1）：20501[2023-05-13]. https://doi.org/10.1038/s41598-020-77546-5.
[19] CUCCHIARA B，TANNE D，LEVINE S R，et al. A risk score to predict intracranial hemorrhage after recombinant tissue plasminogen activator for acute ischemic stroke[J]. J Stroke Cerebrovasc Dis，2008，17（6）：331-333.
[20] DHARMASAROJA P，DHARMASAROJA P A. Prediction of intracerebral hemorrhage following thrombolytic therapy for acute ischemic stroke using multiple artificial neural networks[J]. Neurol Res，2012，34（2）：120-128.
[21] ERDUR H，POLYMERIS A，GRITTNER U，et al. A score for risk of thrombolysis-associated hemorrhage including pretreatment with statins
[J/OL]. Front Neurol，2018，9：74[2023-05-13]. https://doi.org/10.3389/fneur.2018.00074.
[22] LIU J F，CHEN X Y，GUO X N，et al. Machine learning prediction of symptomatic intracerebral hemorrhage after stroke thrombolysis：a cross-cultural validation in Caucasian and Han Chinese cohort[J/OL]. Ther Adv Neurol Disord，2022，15：81556828[2023-05-13]. https://doi.org/10.1177/17562864221129380.
[23] LOKESKRAWEE T，MUENGTAWEEPONGSA S，PATUMANOND J，et al. Prediction of symptomatic intracranial hemorrhage after intravenous thrombolysis in acute ischemic stroke：the symptomatic intracranial hemorrhage score[J]. J Stroke Cerebrovasc Dis，2017，26（11）：2622-2629.
[24] LOU M，SAFDAR A，MEHDIRATTA M，et al. The HAT score：a simple grading scale for predicting hemorrhage after thrombolysis[J]. Neurology，2008，71（18）：1417-1423.
[25] MAZYA M，EGIDO J A，FORD G A，et al. 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[J]. Stroke，2012，43（6）：1524-1531.
[26] MENON B K，SAVER J L，PRABHAKARAN S，et al. Risk score for intracranial hemorrhage in patients with acute ischemic stroke treated with intravenous tissue-type plasminogen activator[J]. Stroke，2012，43（9）：2293-2299.
[27] REN Y，HE Z X，DU X Y，et al. The SON2A2 score：a novel grading scale for predicting hemorrhage and outcomes after thrombolysis[J/OL]. Front Neurol，2022，13：952843[2023-05-13]. https://doi.org/10.3389/fneur.2022.952843.
[28] SAPOSNIK G，GUZIK A K，REEVES M，et al. Stroke prognostication using age and NIH stroke scale：SPAN-100[J]. Neurology，2013，80（1）：21-28.
[29] SONI M，WIJERATNE T，ACKLAND D C. A risk score for prediction of symptomatic intracerebral haemorrhage following thrombolysis[J/OL]. Int J Med Inform，2021，156：104586[2023-05-13].
https://doi.org/10.1016/j.ijmedinf.2021.104586.
[30] STRBIAN D，ENGELTER S，MICHEL P，et al. Symptomatic intracranial hemorrhage after stroke thrombolysis：the SEDAN score[J]. Ann Neurol，2012，71（5）：634-641.
[31] TANNE D，KASNER S E，DEMCHUK A M，et al. Markers of increased risk of intracerebral hemorrhage after intravenous recombinant tissue plasminogen activator therapy for acute ischemic stroke in clinical practice：the multicenter rt-PA stroke survey[J]. Circulation，2002，105（14）：1679-1685.
[32] WAHLGREN N，AHMED N，ERIKSSON N，et al. Multivariable analysis of outcome predictors and adjustment of main outcome results to baseline data profile in randomized controlled trials：safe implementation of thrombolysis in stroke-monitoring study（SITS-MOST）[J]. Stroke，2008，39（12）：3316-3322.
[33] WANG F，HUANG Y H Q，XIA Y，et al. Personalized risk prediction of symptomatic intracerebral hemorrhage after stroke thrombolysis using a machine-learning model
[J/OL]. Ther Adv Neurol Disord，2020，13：1756286420902358[2023-05-13]. https://doi.org/10.1177/1756286420902358.
[34] WHITELEY W N，THOMPSON D，MURRAY G，et al. Targeting recombinant tissue-type plasminogen activator in acute ischemic stroke based on risk of intracranial hemorrhage or poor functional outcome[J]. Stroke，2014，45（4）：1000-1006.
[35] 王莹，陈会生. 阿替普酶溶栓后症状性颅内出血预测模型的构建及验证[J]. 中国脑血管病杂志，2022，19（10）：657-666.
WANG Y，CHEN H S. Construction and validation of a predictive model for symptomatic intracranial hemorrhage after thrombolytic therapy with alteplase[J]. Chin J Cerebrovasc Dis，2022，19（10）：657-666.
[36] KRISHNAMURTHI R V，IKEDA T，FEIGIN V L. Global，regional and country-specific burden of ischaemic stroke，intracerebral haemorrhage and subarachnoid haemorrhage：a systematic analysis of the global burden of disease study 2017[J]. Neuroepidemiology，2020，54（2）：171-179.
[37] SEET R C，RABINSTEIN A A. Symptomatic intracranial hemorrhage following intravenous thrombolysis for acute ischemic stroke：a critical review of case definitions[J]. Cerebrovasc Dis，2012，34（2）：106-114.
[38] ECHOUFFO-TCHEUGUI J B，WOODWARD M，KENGNE A P. Predicting a post-thrombolysis intracerebral hemorrhage：a systematic review[J]. J Thromb Haemost，2013，11（5）：862-871.
[39] KAMAL H，LOPEZ V，SHETH S A. Machine learning in acute ischemic stroke neuroimaging
[J/OL]. Front Neurol，2018，9：945[2023-05-13]. https://doi.org/10.3389/fneur.2018.00945.
[40] SENDERS J T，STAPLES P C，KARHADE A V，et al. Machine learning and neurosurgical outcome prediction：a systematic review[J/OL]. World Neurosurg，2018，109：476-486，e1[2023-06-11]. https://doi.org/10.1016/j.wneu.2017.09.149.
[41] HUANG Y X，LI W T，MACHERET F，et al. A tutorial on calibration measurements and calibration models for clinical prediction models[J]. J Am Med Inform Assoc，2020，27（4）：621-633.
[42] STEYERBERG E W. Validation in prediction research：the waste by data splitting[J/OL]. J Clin Epidemiol，2018，103：131-133[2023-06-11]. https://doi.org/10.1016/j.jclinepi.2018.07.010.
[43] DAS S，MONDAL G P，BHATTACHARYA R，et al. Predictors of postthrombolysis outcome and symptomatic postthrombolysis hemorrhage following intravenous thrombolysis with alteplase for acute ischemic stroke[J]. J Neurosci Rural Pract，2020，11（2）：315-324.
[44] WNUK M，DRABIK L，DERBISZ J，et al. Prognostic significance of age in patients with acute ischaemic stroke treated with intravenous thrombolysis[J]. Neurol Neurochir Pol，2022，56（1）：81-88.
[45] FILIPOV A，EBERT A D，NEUMAIER-PROBST E，et al. The burden of diabetes and the chance of a previous stroke：thrombolysis for recurrent stroke in diabetics[J]. J Stroke Cerebrovasc Dis，2018，27（5）：1343-1349.
[46] DIEDLER J，AHMED N，SYKORA M，et al. Safety of intravenous thrombolysis for acute ischemic stroke in patients receiving antiplatelet therapy at stroke onset[J]. Stroke，2010，41（2）：288-294.