Progress of Machine Learning-based Prediction Model for Complications and Prognosis in Acute Ischemic Stroke

doi:10.3969/j.issn.1673-5765.2020.06.007

Abstract

Abstract:

With the development of medical big data and the rapid increasing of computer analyzing capabilities, research on machine learning-based prediction models in stroke has gradually become hotspots in interdisciplinary research. Compared with traditional scales, machine learning-based models have great advantages such as fast, accurate and repeatable, which have been applied in the diagnosis and prognosis assessment in stroke, to help clinicians accurately judge the patient's condition. This article reviewed the progress of machine learning-based prediction models for complications and prognosis in acute ischemic stroke, and discussed the existing problems, such as the limited number of studies, small sample size, and the lack of external verification, etc.

Key words: Acute ischemic stroke; Machine learning; Complication prediction; Prognosis prediction

摘要：

随着医疗数据的不断集成和计算机运算能力的大幅提升，基于机器学习的卒中预测研究逐渐成为交叉学科中的研究热点。相较于传统量表评分，机器学习模型具有快速、准确、可重复性等优势，已被用于卒中的诊断和预后预测，帮助临床医师准确判断患者病情及预后。本文介绍了目前机器学习算法用于急性缺血性卒中并发症及预后预测的研究进展，并分析了当前研究存在的问题，如研究数量不足、样本量过少、缺少外部验证等。

关键词: 急性缺血性卒中; 机器学习; 并发症预测; 预后预测

QIN Wei, JIANG Yong, LIU Bao-Hua. Progress of Machine Learning-based Prediction Model for Complications and Prognosis in Acute Ischemic Stroke[J]. Chinese Journal of Stroke, 2020, 15(06): 611-615.

覃伟，姜勇，刘宝花. 机器学习模型在急性缺血性卒中并发症及预后预测中的研究进展[J]. 中国卒中杂志, 2020, 15(06): 611-615.

References

[1] 霍晓川，高峰. 急性缺血性卒中血管内治疗中国指南

2018[J]. 中国卒中杂志，2018，13（7）：706-729.

[2] HUANG G Q，LIN Y T，WU Y M，et al.

Individualized prediction of stroke-associated

pneumonia for patients with acute ischemic stroke[J].

Clin Interv Aging，2019，14：1951-1962.

[3] GE Y Q，WANG Q H，WANG L，et al. Predicting

post-stroke pneumonia using deep neural network

approaches[J/OL]. Int J Med Inform，2019[2020-

03-15]. https：//doi. org/10. 1016/j. ijmedinf. 2019.

103986.

[4] LI X，WU M，SUN C Z，et al. Using machine

learning to predict stroke-associated pneumonia in

Chinese patients with acute ischemic stroke[J/OL].

Eur J Neurol，2020[2020-03-15]. https：//doi.org/10.

1111/ene.14295.

[5] HACKETT M L，YAPA C，PARAG V，et al.

Frequency of depression after stroke：a systematic

review of observational studies[J]. Stroke，36（6）：

1330-1340.

[6] SCHEPERS V，POST M，VISSER-MEILY A，et al.

Prediction of depressive symptoms up to three years

post-stroke[J]. J Rehabil Med，2009，41（11）：930-

935.

[7] LIU R，YUE Y，JIANG H，et al. A risk prediction

model for post-stroke depression in Chinese stroke

survivors based on clinical and socio-psychological

features[J]. Oncotarget，2017，8（38）：62891-62899.

[8] DE MAN-VAN GINKEL J M，

HAFSTEINSDOTTIR T B，LINDEMAN E，et al.

In-hospital risk prediction for post-stroke depression：

development and validation of the post-stroke

depression prediction scale[J]. Stroke，2013，44（9）：

2441-2445.

[9] 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.

[10] BENTLEY P，GANESALINGAM J，CARLTON

JONES A L，et al. Prediction of stroke thrombolysis

outcome using CT brain machine learning[J].

Neuroimage Clin，2014，4：635-640.

[11] 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.

[12] FLINT A C，CULLEN S P，RAO V A，et al. The

THRIVE score strongly predicts outcomes in

patients treated with the Solitaire device in the

SWIFT and STAR trials[J]. Int J Stroke，2014，9（6）：

698-704.

[13] NTAIOS G，FAOUZI M，FERRARI J，et al. An

integer-based score to predict functional outcome

in acute ischemic stroke：the ASTRAL score[J].

Neurology，2012，78（24）：1916-1922.

[14] PAPAVASILEIOU V，MILIONIS H，MICHEL P，et

al. ASTRAL score predicts 5-year dependence and

mortality in acute ischemic stroke[J]. Stroke，2013，

44（6）：1616-1620.

[15] 高金颖，胡蓉，金迪，等. SOAR量表和ASTRAL量

表评分对急性缺血性卒中患者1年不良预后的预测功

能评价[J]. 神经损伤与功能重建，2019，14（8）：383-

385.

[16] MICHEL P，ODIER C，RUTGERS M，et al. The

Acute STroke Registry and Analysis of Lausanne

（ASTRAL）：design and baseline analysis of an

ischemic stroke registry including acute multimodal

imaging[J]. Stroke，2010，41（11）：2491-2498.

[17] MONTEIRO M，FONSECA A C，FREITAS A T，et

al. Using machine learning to improve the prediction

of functional outcome in ischemic stroke patients[J].

IEEE/ACM Trans Comput Biol Bioinform，2018，15

（6）：1953-1959.

[18] PARK E，CHANG H J，NAM H S. A Bayesian

network model for predicting post-stroke outcomes

with available risk factors[J/OL]. Front Neurol，

2018[2020-03-15]. https：//doi.org/10.3389/fneur.

2018.00699.

[19] HEO J，YOON J G，PARK H，et al. Machine

learning-based model for prediction of outcomes in

acute stroke[J]. Stroke，2019，50（5）：1263-1265.

[20] VAN OS H J A，RAMOS L A，HILBERT A，et al.

Predicting outcome of endovascular treatment for

acute ischemic stroke：potential value of machine

learning algorithms[J/OL]. Front Neurol，2018[2020-

03-15]. https：//doi.org/10.3389/fneur.2018.00784.

[21] NISHI H，OISHI N，ISHII A，et al. Predicting

clinical outcomes of large vessel occlusion before

mechanical thrombectomy using machine learning[J].

Stroke，2019，50（9）：2379-2388.

[22] 钟迪，张舒婷，吴波. 《中国急性缺血性脑卒中诊治

指南2018》解读[J]. 中国现代神经疾病杂志，2019，19

（11）：897-901.

[23] ZHOU Y F，YAN S J，SONG X Y，et al. Intravenous

thrombolytic therapy for acute ischemic stroke in

Hubei，China：a survey of thrombolysis rate and

barriers[J]. BMC Neurology，2019，19（1）：202.

[24] WANG Y L，LIAO X L，ZHAO X Q，et al. Using

recombinant tissue plasminogen activator to treat

acute ischemic stroke in China：analysis of the

results from the Chinese National Stroke Registry

（CNSR）[J]. Stroke，2011，42（6）：1658-1664.

[25] CHENG C A，LIN Y C，CHIU H W. Prediction

of the prognosis of ischemic stroke patients after

intravenous thrombolysis using artificial neural

networks[J]. Stud Health Technol Inform，2014，202：

115-118.

[26] BACCHI S，ZERNER T，OAKDEN-RAYNER L，

et al. Deep learning in the prediction of ischaemic

stroke thrombolysis functional outcomes：a

pilot study[J/OL]. Acad Radiol，2020，27（2）：

e19-e23[2020-03-15]. https：//doi.org/10.1016/j.acra.

2019.03.015.