机器学习在缺血性卒中诊治中的应用与展望
PDF下载 (63)徐瑾妍,陆浩轩,谢燕青,计礼丽,何文明.机器学习在缺血性卒中诊治中的应用与展望[J].宁波大学学报(理工版),2024,37(3):104-112.DOI:10.20098/j.cnki.1001-5132.2024.0101
XU Jinyan,LU Haoxuan,XIE Yanqing,JI Lili,HE Wenming.Application and prospect of machine learning in the diagnosis and treatment of ischemic stroke[J].Journal of Ningbo University(Natural Science & Engineering Edition),2024,37(3):104-112.DOI:10.20098/j.cnki.1001-5132.2024.0101
| Title: | Application and prospect of machine learning in the diagnosis and treatment of ischemic stroke |
| 作者: | 徐瑾妍, 陆浩轩, 谢燕青, 计礼丽, 何文明 |
| Author(s): | XU Jinyan, LU Haoxuan, XIE Yanqing, JI Lili, HE Wenming |
| 关键词: | 缺血性卒中; 人工智能; 机器学习; 影像诊断; 医疗决策 |
| Keywords: | ischemic stroke; artificial intelligence; machine learning; imaging diagnosis; medical decision |
| 分类号: | R743.3 |
| DOI: | 10.20098/j.cnki.1001-5132.2024.0101 |
| 文献标识码: | A |
| 摘要: | 缺血性卒中有高死亡率、高致残率和高复发率的特点, 临床上常出现漏诊、误诊现象. 而基于机器学习的计算机辅助技术能够通过对医学文本、影像等资料的特征挖掘, 辅助医生快速、准确地提高诊疗效率. 本文通过梳理机器学习的不同方法, 及其在缺血性卒中预测、诊断、治疗和预后的应用, 对未来机器学习在该领域的预测、诊断、制定个性化治疗方案以及医疗资源合理性配置等方面进行展望. |
| Abstract: | Ischemic stroke leads to high mortality, high disability rate, and high recurrence rate. Missed diagnoses and misdiagnoses are common. Computer-assisted technologies based on machine learning, by mining features from medical texts and images are suggested to help doctors improve diagnostic and treatment efficiency quickly and accurately. This review provides an overview of various machine learning methods and research progress in predicting, diagnosing, treating, and prognosis of ischemic stroke. The review is also summarized the future application of machine learning in the field of ischemic stroke for prediction, diagnosis, developing personalized treatment plans, and optimizing medical resource allocation. |
| 参考文献 /References: | [1].SOUN J E, CHOW D S, NAGAMINE M, et al. Artificial intelligence and acute stroke imaging[J]. American Journal of Neuroradiology, 2021, 42(1):2-11. [2].BOEHME A K, ESENWA C, ELKIND M S V. Stroke risk factors, genetics, and prevention[J]. Circulation Research, 2017, 120(3):472-495. [3].YE Y, ZHU Y T, ZHANG J C, et al. Burden and attributable risk factors of ischemic stroke in China from 1990 to 2019: an analysis from the Global Burden of Disease Study 2019[J]. Frontiers in Neurology, 2023, 14: 1216777. [4].THAYABARANATHAN T, KIM J, CADILHAC D A, et al. Global stroke statistics 2022[J]. International Journal of Stroke, 2022, 17(9):946-956. [5].LEE E J, KIM Y H, KIM N, et al. Deep into the brain: artificial intelligence in stroke imaging[J]. Journal of Stroke, 2017, 19(3):277-285. [6].王陇德, 彭斌, 张鸿祺, 等. 《中国脑卒中防治报告2020》概要[J]. 中国脑血管病杂志, 2022, 19(2):136- 144. [7].CAMPBELL B C V, DE SILVA D A, MACLEOD M R, et al. Ischaemic stroke[J]. Nature Reviews Disease Primers, 2019, 5(1):70. [8].PENDLEBURY S T, ROTHWELL P M. Prevalence, incidence, and factors associated with pre-stroke and post-stroke dementia: a systematic review and meta- analysis[J]. The Lancet Neurology, 2009, 8(11):1006- 1018. [9].SACCO R L, KASNER S E, BRODERICK J P, et al. An updated definition of stroke for the 21st century: a statement for healthcare professionals from the American Heart Association/American Stroke Association[J]. Stroke, 2013, 44(7):2064-2089. [10].VALLIANI A A A, RANTI D, OERMANN E K. Deep learning and neurology: a systematic review[J]. Neurology and Therapy, 2019, 8(2):351-365. [11].BELAGAJE S R. Stroke rehabilitation[J]. Continuum (Minneap Minn), 2017, 23:238-253. [12].BRENNER D A, ZWEIFLER R M, GOMEZ C R, et al. Awareness, treatment, and control of vascular risk factors among stroke survivors[J]. Journal of Stroke and Cerebrovascular Diseases, 2010, 19(4):311-320. [13].LANGHORNE P, BERNHARDT J, KWAKKEL G. Stroke rehabilitation[J]. The Lancet, 2011, 377(9778): 1693-1702. [14].GOOD D C, BETTERMANN K, REICHWEIN R K. Stroke rehabilitation[J]. Continuum (Minneap Minn), 2011, 17:545-567. [15].HEILMAN M K M, VALENSTEIN E. Clinical neuropsychology[M]. Oxford: Oxford University Press, 2010. [16].OSTMEIER S, AXELROD B, LIU Y K, et al. Random expert sampling for deep learning segmentation of acute ischemic stroke on non-contrast CT[EB/OL]. [2023-12- 01]. https://doi.org/10.48550/arXiv.2309.03930. [17].FANG T, LIU N J, NIE S D, et al. A deep learning and radiomics based Alberta stroke program early CT score method on CTA to evaluate acute ischemic stroke[J]. Journal of X-Ray Science and Technology, 2024, 32(1): 17-30. [18].OSTMEIER S, AXELROD B, VERHAAREN B F J, et al. Non-inferiority of deep learning ischemic stroke segmentation on non-contrast CT within 16-hours compared to expert neuroradiologists[J]. Scientific Reports, 2023, 13(1):16153. [19].BENTO M, SOUZA R, SALLUZZI M, et al. Automatic identification of atherosclerosis subjects in a heterogeneous MR brain imaging data set[J]. Magnetic Resonance Imaging, 2019, 62:18-27. [20].CHEN Y S, DHAR R, HEITSCH L, et al. Automated quantification of cerebral edema following hemispheric infarction: application of a machine-learning algorithm to evaluate CSF shifts on serial head CTs[J]. NeuroImage Clinical, 2016, 12:673-680. [21].JUNG S, SONG M K, LEE E, et al. Predicting ischemic stroke in patients with atrial fibrillation using machine learning[J]. Frontiers in Bioscience (Landmark Edition), 2022, 27(3):80. [22].MYERS K D, KNOWLES J W, STASZAK D, et al. Precision screening for familial hypercholesterolaemia: a machine learning study applied to electronic health encounter data[J]. The Lancet Digital Health, 2019, 1(8): e393-e402. [23].HOPE T M H, SEGHIER M L, LEFF A P, et al. Predicting outcome and recovery after stroke with lesions extracted from MRI images[J]. NeuroImage Clinical, 2013, 2:424-433. [24].MOULTON E, VALABREGUE R, LEHÉRICY S, et al. Multivariate prediction of functional outcome using lesion topography characterized by acute diffusion tensor imaging[J]. NeuroImage Clinical, 2019, 23:101821. [25].SALE P, FERRIERO G, CIABATTONI L, et al. Predicting motor and cognitive improvement through machine learning algorithm in human subject that underwent a rehabilitation treatment in the early stage of stroke[J]. Journal of Stroke and Cerebrovascular Diseases, 2018, 27(11):2962-2972. [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]. Academic Radiology, 2020, 27(2):e19-e23. [27].WEN R, WANG M R, BIAN W, et al. Machine learning- based prediction of symptomatic intracerebral hemorrhage after intravenous thrombolysis for stroke: a large multicenter study[J]. Frontiers in Neurology, 2023, 14: 1247492. [28].GE Y Q, WANG Q H, WANG L, et al. Predicting post- stroke pneumonia using deep neural network approaches [J]. International Journal of Medical Informatics, 2019, 132: 103986. [29].BADESA F J, MORALES R, GARCIA-ARACIL N, et al. Auto-adaptive robot-aided therapy using machine learning techniques[J]. Computer Methods and Programs in Bio- medicine, 2014, 116(2):123-130. [30].BOCHNIEWICZ E M, EMMER G, MCLEOD A, et al. Measuring functional arm movement after stroke using a single wrist-worn sensor and machine learning[J]. Journal of Stroke and Cerebrovascular Diseases, 2017, 26(12): 2880-2887. [31].LI C, RUSÁK Z, HORVÁTH I, et al. Development of engagement evaluation method and learning mechanism in an engagement enhancing rehabilitation system[J]. Engineering Applications of Artificial Intelligence, 2016, 51:182-190. [32].YU L, XIONG D X, GUO L Q, et al. A remote quantitative Fugl-Meyer assessment framework for stroke patients based on wearable sensor networks[J]. Computer Methods and Programs in Biomedicine, 2016, 128:100- 110. [33].JIANG F, JIANG Y, ZHI H, et al. Artificial intelligence in healthcare: past, present and future[J]. Stroke and Vascular Neurology, 2017, 2(4):230-243. [34].徐洪学, 孙万有, 杜英魁, 等. 机器学习经典算法及其应用研究综述[J]. 电脑知识与技术, 2020, 16(33):17- 19. [35].FERNÁNDEZ-DELGADO M, CERNADAS E, BARRO S, et al. Do we need hundreds of classifiers to solve real world classification problems?[J]. Journal of Machine Learning Research, 2014, 15:3133-3181. [36].LANDWEHR N, HALL M, FRANK E. Logistic model trees[J]. Machine Learning, 2005, 59(1):161-205. [37].JOHN G H, LANGLEY P. Estimating continuous distributions in Bayesian classifiers[EB/OL]. [2023-12- 01]. http://arxiv.org/abs/1302.4964. [38].BENTLEY P, GANESALINGAM J, JONES A L C A L, et al. Prediction of stroke thrombolysis outcome using CT brain machine learning[J]. NeuroImage Clinical, 2014, 4: 635-640. [39].严海兵, 周刚, 朱振刚, 等. 基于朴素贝叶斯的学术论文推荐算法研究[J]. 苏州科技大学学报(自然科学版), 2023, 40(4):69-75. [40].焦李成, 杨淑媛, 刘芳, 等. 神经网络七十年: 回顾与展望[J]. 计算机学报, 2016, 39(8):1697-1716. [41].RICHARDS J A. Clustering and unsupervised classification [M]//Remote sensing digital image analysis. Cham: Springer, 2022:369-401. [42].SAXENA A, PRASAD M, GUPTA A, et al. A review of clustering techniques and developments[J]. Neurocomputing, 2017, 267:664-681. [43].ALAWADI S, FERNÁNDEZ-DELGADO M, MERA D, et al. Polynomial Kernel Discriminant Analysis for 2D visualization of classification problems[J]. Neural Computing and Applications, 2019, 31(8):3515-3531. [44].SAHLAB N, SONJI I, WEYRICH M. Graph-based association rule learning for context-based health monitoring to enable user-centered assistance[J]. Artificial Intelligence in Medicine, 2023, 135:102455. [45].CHOI R Y, COYNER A S, KALPATHY-CRAMER J, et al. Introduction to machine learning, neural networks, and deep learning[J]. Translational Vision Science & Technology, 2020, 9(2):14. [46].LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521:436-444. [47].DUMKA A, ASHOK A, VERMA P, et al. Advanced digital image processing and its applications in big data[M]. Boca Raton: CRC Press, 2020. [48].YANG W X, WANG F F, PAN Y Y, et al. Comparison of ischemic stroke diagnosis models based on machine learning[J]. Frontiers in Neurology, 2022, 13:1014346. [49].DHAR R. Automated quantitative assessment of cerebral edema after ischemic stroke using CSF volumetrics[J]. Neuroscience Letters, 2020, 724:134879. [50].HU Y X, YANG T T, ZHANG J, et al. Dynamic prediction of mechanical thrombectomy outcome for acute ischemic stroke patients using machine learning[J]. Brain Sciences, 2022, 12(7):938. [51].魏航, 陈沁群, 王正飞, 等. 医工结合背景下数据科学能力培养模式探索[J]. 电脑知识与技术, 2023, 19(8): 68-70. [52].CHAVVA I R, CRAWFORD A L, MAZUREK M H, et al. Deep learning applications for acute stroke management [J]. Annals of Neurology, 2022, 92(4):574-587. [53].BISWAS M, KUPPILI V, ARAKI T, et al. Deep learning strategy for accurate carotid intima-media thickness measurement: an ultrasound study on Japanese diabetic cohort[J]. Computers in Biology and Medicine, 2018, 98: 100-117. [54].MENCHÓN-LARA R M, SANCHO-GÓMEZ J L. Fully automatic segmentation of ultrasound common carotid artery images based on machine learning[J]. Neuro- computing, 2015, 151:161-167. [55].KASABOV N, FEIGIN V, HOU Z G, et al. Evolving spiking neural networks for personalised modelling, classification and prediction of spatio-temporal patterns with a case study on stroke[J]. Neurocomputing, 2014, 134:269-279. [56].THORNHILL R E, LUM C, JABERI A, et al. Can shape analysis differentiate free-floating internal carotid artery thrombus from atherosclerotic plaque in patients evaluated with CTA for stroke or transient ischemic attack?[J]. Academic Radiology, 2014, 21(3):345-354. [57].PEIXOTO S A, REBOUÇAS FILHO P P. Neurologist- level classification of stroke using a Structural Co- Occurrence Matrix based on the frequency domain[J]. Computers & Electrical Engineering, 2018, 71:398-407. [58].DE SOUZA J W M, ALMEIDA J S, HOLANDA G B, et al. New approach to detect and classify stroke in skull CT images via structural co-occurrence matrix and machine learning[C]//COSTA-FELIX R, MACHADO J, ALVARENGA A. XXVI Brazilian Congress on Biomedical Engineering. Singapore: Springer, 2019:341-348. [59].VARGAS J, SPIOTTA A, CHATTERJEE A R. Initial experiences with artificial neural networks in the detection of computed tomography perfusion deficits[J]. World Neurosurgery, 2019, 124:e10-e16. [60].GARG R, OH E, NAIDECH A, et al. Automating ischemic stroke subtype classification using machine learning and natural language processing[J]. Journal of Stroke and Cerebrovascular Diseases, 2019, 28(7):2045- 2051. [61].QU Y M, ZHUO Y Y, LEE J, et al. Ischemic and haemorrhagic stroke risk estimation using a machine- learning-based retinal image analysis[J]. Frontiers in Neurology, 2022, 13:916966. [62].WANG C Y, SHI Z, YANG M, et al. Deep learning-based identification of acute ischemic core and deficit from non-contrast CT and CTA[J]. Journal of Cerebral Blood Flow and Metabolism: Official Journal of the International Society of Cerebral Blood Flow and Metabolism, 2021, 41(11):3028-3038. [63].LU J, ZHOU Y R, LV W Z, et al. Identification of early invisible acute ischemic stroke in non-contrast computed tomography using two-stage deep-learning model[J]. Theranostics, 2022, 12(12):5564-5573. [64].STIB M T, VASQUEZ J, DONG M P, et al. Detecting large vessel occlusion at multiphase CT angiography by using a deep convolutional neural network[J]. Radiology, 2020, 297(3):640-649. [65].YANG Y, YANG J J, FENG J, et al. Early diagnosis of acute ischemic stroke by brain computed tomography perfusion imaging combined with head and neck computed tomography angiography on deep learning algorithm[J]. Contrast Media & Molecular Imaging, 2022, 2022:5373585. [66].ABEDI V, GOYAL N, TSIVGOULIS G, et al. Novel screening tool for stroke using artificial neural network[J]. Stroke, 2017, 48(6):1678-1681. |
| 备注/Memo: | 收稿日期: 2024−01−01. 宁波大学学报（理工版）网址: http://journallg.nbu.edu.cn/ 基金项目: 宁波市自然科学基金（2021J240, 202003N4231）; 浙江省中医药科技计划项目（2024ZL892）. 第一作者: 徐瑾妍, 副主任医师, 主要研究方向: 脑血管. E-mail: xujinyantt@163.com *通信作者: 何文明, 博士/主任医师, 主要研究方向: 心血管. E-mail: fyhewenming@nbu.edu.cn 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ |
