Journal of Medicine and Life Science

Institute for Medical Science (제주대학교 의과학연구소)
권호 표지
DOI QR코드

DOI QR Code

Machine learning application in ischemic stroke diagnosis, management, and outcome prediction: a narrative review

허혈성 뇌졸중의 진단, 치료 및 예후 예측에 대한 기계 학습의 응용: 서술적 고찰

  • Mi-Yeon Eun (Department of Neurology, Kyungpook National University Chilgok Hospital, School of Medicine, Kyungpook National University) ;
  • Eun-Tae Jeon (Department of Neurology, Korea University Ansan Hospital, Korea University College of Medicine) ;
  • Jin-Man Jung (Department of Neurology, Korea University Ansan Hospital, Korea University College of Medicine)
  • 은미연 (경북대학교 의과대학 칠곡경북대학교병원 신경과) ;
  • 전은태 (고려대학교 의과대학 고려대학교안산병원 신경과) ;
  • 정진만 (고려대학교 의과대학 고려대학교안산병원 신경과)
  • Received : 2023.07.15
  • Accepted : 2023.10.13
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Stroke is a leading cause of disability and death. The condition requires prompt diagnosis and treatment. The quality of care provided to patients with stroke can vary depending on the availability of medical resources, which in turn, can affect prognosis. Recently, there has been growing interest in using machine learning (ML) to support stroke diagnosis and treatment decisions based on large medical data sets. Current ML applications in stroke care can be divided into two categories: analysis of neuroimaging data and clinical information-based predictive models. Using ML to analyze neuroimaging data can increase the efficiency and accuracy of diagnoses. Commercial software that uses ML algorithms is already being used in the medical field. Additionally, the accuracy of predictive ML models is improving with the integration of radiomics and clinical data. is expected to be important for improving the quality of care for patients with stroke.

Keywords

Acknowledgement

This research was supported by Ansan-Si hidden champion fostering and supporting project funded by Ansan city.

References

  1. Aho K, Harmsen P, Hatano S, Marquardsen J, Smirnov VE, Strasser T. Cerebrovascular disease in the community: results of a WHO collaborative study. Bull World Health Organ 1980;58:113-30.
  2. GBD 2016 Stroke Collaborators. Global, regional, and national burden of stroke, 1990-2016: a systematic analysis for the Global Burden of Disease Study 2016. Lancet Neurol 2019;18:439-58. https://doi.org/10.1016/S1474-4422(19)30034-1
  3. Saver JL. Time is brain--quantified. Stroke 2006;37:263-6. https://doi.org/10.1161/01.STR.0000196957.55928.ab
  4. Sanelli PC, Sykes JB, Ford AL, Lee JM, Vo KD, Hallam DK. Imaging and treatment of patients with acute stroke: an evidence-based review. AJNR Am J Neuroradiol 2014;35:1045-51. https://doi.org/10.3174/ajnr.A3518
  5. Albers GW, Thijs VN, Wechsler L, Kemp S, Schlaug G, Skalabrin E, et al. Magnetic resonance imaging profiles predict clinical response to early reperfusion: the diffusion and perfusion imaging evaluation for understanding stroke evolution (DEFUSE) study. Ann Neurol 2006;60:508-17. https://doi.org/10.1002/ana.20976
  6. Meinel TR, Kaesmacher J, Mosimann PJ, Seiffge D, Jung S, Mordasini P, et al. Association of initial imaging modality and futile recanalization after thrombectomy. Neurology 2020;95:e2331-42. https://doi.org/10.1212/WNL.0000000000010614
  7. Naylor J, Churilov L, Chen Z, Koome M, Rane N, Campbell BCV. Reliability, reproducibility and prognostic accuracy of the alberta stroke program early CT score on CT perfusion and non-contrast CT in hyperacute stroke. Cerebrovasc Dis 2017;44:195-202. https://doi.org/10.1159/000479707
  8. Babiarz LS, Yousem DM. Quality control in neuroradiology: discrepancies in image interpretation among academic neuroradiologists. AJNR Am J Neuroradiol 2012;33:37-42. https://doi.org/10.3174/ajnr.A2704
  9. Ye H, Gao F, Yin Y, Guo D, Zhao P, Lu Y, et al. Precise diagnosis of intracranial hemorrhage and subtypes using a three-dimensional joint convolutional and recurrent neural network. Eur Radiol 2019;29:6191-201. https://doi.org/10.1007/s00330-019-06163-2
  10. Winzeck S, Mocking SJT, Bezerra R, Bouts MJRJ, McIntosh EC, Diwan I, et al. Ensemble of convolutional neural networks improves automated segmentation of acute ischemic lesions using multiparametric diffusion-weighted MRI. AJNR Am J Neuroradiol 2019;40:938-45. https://doi.org/10.3174/ajnr.A6077
  11. Chen L, Bentley P, Rueckert D. Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks. Neuroimage Clin 2017;15:633-43. https://doi.org/10.1016/j.nicl.2017.06.016
  12. Wang J, Gong X, Chen H, Zhong W, Chen Y, Zhou Y, et al. Causative classification of ischemic stroke by the machine learning algorithm random forests. Front Aging Neurosci 2022;14:788637.
  13. Amukotuwa SA, Straka M, Dehkharghani S, Bammer R. Fast automatic detection of large vessel occlusions on CT angiography. Stroke 2019;50:3431-8. https://doi.org/10.1161/STROKEAHA.119.027076
  14. Elijovich L, Dornbos Iii D, Nickele C, Alexandrov A, Inoa-Acosta V, Arthur AS, et al. Automated emergent large vessel occlusion detection by artificial intelligence improves stroke workflow in a hub and spoke stroke system of care. J Neurointerv Surg 2022;14:704-8. https://doi.org/10.1136/neurintsurg-2021-017714
  15. Heo J, Yoon JG, Park H, Kim YD, Nam HS, Heo JH. Machine learning-based model for prediction of outcomes in acute stroke. Stroke 2019;50:1263-5. https://doi.org/10.1161/STROKEAHA.118.024293
  16. Nishi H, Oishi N, Ishii A, Ono I, Ogura T, Sunohara T, et al. Predicting clinical outcomes of large vessel occlusion before mechanical thrombectomy using machine learning. Stroke 2019;50:2379-88. https://doi.org/10.1161/STROKEAHA.119.025411
  17. Rajashekar D, Hill MD, Demchuk AM, Goyal M, Fiehler J, Forkert ND. Prediction of clinical outcomes in acute ischaemic stroke patients: a comparative study. Front Neurol 2021;12:663899.
  18. Lee EJ, Kim YH, Kim N, Kang DW. Deep into the brain: artificial intelligence in stroke imaging. J Stroke 2017;19:277-85. https://doi.org/10.5853/jos.2017.02054
  19. Mokli Y, Pfaff J, Dos Santos DP, Herweh C, Nagel S. Computer-aided imaging analysis in acute ischemic stroke - background and clinical applications. Neurol Res Pract 2019;1:23.
  20. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015; 521:436-44. https://doi.org/10.1038/nature14539
  21. Zhang Y, Kang B, Hooi B, Yan S, Feng J. Deep long-tailed learning: a survey. IEEE Trans Pattern Anal Mach Intell 2023; 45:10795-816. https://doi.org/10.1109/TPAMI.2023.3268118
  22. Geirhos R, Jacobsen JH, Michaelis C, Zemel R, Brendel W, Bethge M, et al. Shortcut learning in deep neural networks. Nat Mach Intell 2020;2:665-73. https://doi.org/10.1038/s42256-020-00257-z
  23. Li H, Li J, Guan X, Liang B, Lai Y, Luo X. Research on overfitting of deep learning. In: 2019 15th International Conference on Computational Intelligence and Security (CIS); 2019 Dec 13-16; Macao, China. Piscataway (NJ): IEEE; c2019. pp. 78-81.
  24. de Hond AAH, Leeuwenberg AM, Hooft L, Kant IMJ, Nijman SWJ, van Os HJA, et al. Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review. NPJ Digit Med 2022;5:2.
  25. Yedavalli VS, Tong E, Martin D, Yeom KW, Forkert ND. Artificial intelligence in stroke imaging: current and future perspectives. Clin Imaging 2021;69:246-54. https://doi.org/10.1016/j.clinimag.2020.09.005
  26. Jenkinson M, Beckmann CF, Behrens TE, Woolrich MW, Smith SM. FSL. Neuroimage 2012;62:782-90. https://doi.org/10.1016/j.neuroimage.2011.09.015
  27. Fischl B. FreeSurfer. Neuroimage 2012;62:774-81. https://doi.org/10.1016/j.neuroimage.2012.01.021
  28. Briard JN, Zewude RT, Kate MP, Rowe BH, Buck B, Butcher K, et al. Stroke mimics transported by emergency medical services to a comprehensive stroke center: the magnitude of the problem. J Stroke Cerebrovasc Dis 2018;27:2738-45. https://doi.org/10.1016/j.jstrokecerebrovasdis.2018.05.046
  29. Goyal N, Male S, Al Wafai A, Bellamkonda S, Zand R. Cost burden of stroke mimics and transient ischemic attack after intravenous tissue plasminogen activator treatment. J Stroke Cerebrovasc Dis 2015;24:828-33. https://doi.org/10.1016/j.jstrokecerebrovasdis.2014.11.023
  30. Lee S, Jeong B, Kim M, Jang R, Paik W, Kang J, et al. Emergency triage of brain computed tomography via anomaly detection with a deep generative model. Nat Commun 2022;13:4251.
  31. Titano JJ, Badgeley M, Schefflein J, Pain M, Su A, Cai M, et al. Automated deep-neural-network surveillance of cranial images for acute neurologic events. Nat Med 2018;24:1337-41. https://doi.org/10.1038/s41591-018-0147-y
  32. Sahoo PK, Mohapatra S, Wu CY, Huang KL, Chang TY, Lee TH. Automatic identification of early ischemic lesions on non-contrast CT with deep learning approach. Sci Rep 2022;12:18054.
  33. Lu J, Zhou Y, Lv W, Zhu H, Tian T, Yan S, et al. Identification of early invisible acute ischemic stroke in non-contrast computed tomography using two-stage deep-learning model. Theranostics 2022;12:5564-73. https://doi.org/10.7150/thno.74125
  34. Kniep HC, Sporns PB, Broocks G, Kemmling A, Nawabi J, Rusche T, et al. Posterior circulation stroke: machine learning-based detection of early ischemic changes in acute non-contrast CT scans. J Neurol 2020;267:2632-41. https://doi.org/10.1007/s00415-020-09859-4
  35. Wu O, Winzeck S, Giese AK, Hancock BL, Etherton MR, Bouts MJRJ, et al. Big data approaches to phenotyping acute ischemic stroke using automated lesion segmentation of multi-center magnetic resonance imaging data. Stroke 2019;50:1734-41. https://doi.org/10.1161/STROKEAHA.119.025373
  36. Jeong HG, Kim BJ, Kim T, Kang J, Kim JY, Kim J, et al. Classification of cardioembolic stroke based on a deep neural network using chest radiographs. EBioMedicine 2021;69:103466.
  37. Serena J, Davalos A, Segura T, Mostacero E, Castillo J. Stroke on awakening: looking for a more rational management. Cerebrovasc Dis 2003;16:128-33. https://doi.org/10.1159/000070592
  38. Lee H, Lee EJ, Ham S, Lee HB, Lee JS, Kwon SU, et al. Machine learning approach to identify stroke within 4.5 hours. Stroke 2020;51:860-6. https://doi.org/10.1161/STROKEAHA.119.027611
  39. Zhu H, Jiang L, Zhang H, Luo L, Chen Y, Chen Y. An automatic machine learning approach for ischemic stroke onset time identification based on DWI and FLAIR imaging. Neuroimage Clin 2021;31:102744.
  40. Zhang YQ, Liu AF, Man FY, Zhang YY, Li C, Liu YE, et al. MRI radiomic features-based machine learning approach to classify ischemic stroke onset time. J Neurol 2022;269:350-60. https://doi.org/10.1007/s00415-021-10638-y
  41. Jiang L, Wang S, Ai Z, Shen T, Zhang H, Duan S, et al. Development and external validation of a stability machine learning model to identify wake-up stroke onset time from MRI. Eur Radiol 2022;32:3661-9. https://doi.org/10.1007/s00330-021-08493-6
  42. Malhotra K, Gornbein J, Saver JL. Ischemic strokes due to large-vessel occlusions contribute disproportionately to stroke-related dependence and death: a review. Front Neurol 2017;8:651.
  43. Dozois A, Hampton L, Kingston CW, Lambert G, Porcelli TJ, Sorenson D, et al. PLUMBER study (prevalence of large vessel occlusion strokes in Mecklenburg County emergency response). Stroke 2017;48:3397-9. https://doi.org/10.1161/STROKEAHA.117.018925
  44. Stib MT, Vasquez J, Dong MP, Kim YH, Subzwari SS, Triedman HJ, et al. Detecting large vessel occlusion at multiphase CT angiography by using a deep convolutional neural network. Radiology 2020;297:640-9. https://doi.org/10.1148/radiol.2020200334
  45. Czap AL, Bahr-Hosseini M, Singh N, Yamal JM, Nour M, Parker S, et al. Machine learning automated detection of large vessel occlusion from mobile stroke unit computed tomography angiography. Stroke 2022;53:1651-6. https://doi.org/10.1161/STROKEAHA.121.036091
  46. Sheth SA, Jahan R, Gralla J, Pereira VM, Nogueira RG, Levy EI, et al. Time to endovascular reperfusion and degree of disability in acute stroke. Ann Neurol 2015;78:584-93. https://doi.org/10.1002/ana.24474
  47. Cimflova P, Golan R, Ospel JM, Sojoudi A, Duszynski C, Elebute I, et al. Validation of a machine learning software tool for automated large vessel occlusion detection in patients with suspected acute stroke. Neuroradiology 2022;64:2245-55. https://doi.org/10.1007/s00234-022-02978-x
  48. Rava RA, Peterson BA, Seymour SE, Snyder KV, Mokin M, Waqas M, et al. Validation of an artificial intelligence-driven large vessel occlusion detection algorithm for acute ischemic stroke patients. Neuroradiol J 2021;34:408-17. https://doi.org/10.1177/1971400921998952
  49. Luijten SPR, Wolff L, Duvekot MHC, van Doormaal PJ, Moudrous W, Kerkhoff H, et al. Diagnostic performance of an algorithm for automated large vessel occlusion detection on CT angiography. J Neurointerv Surg 2022;14:794-8. https://doi.org/10.1136/neurintsurg-2021-017842
  50. Rodrigues G, Barreira CM, Bouslama M, Haussen DC, Al-Bayati A, Pisani L, et al. Automated large artery occlusion detection in stroke: a single-center validation study of an artificial intelligence algorithm. Cerebrovasc Dis 2022;51:259-64. https://doi.org/10.1159/000519125
  51. Seker F, Pfaff JAR, Mokli Y, Berberich A, Namias R, Gerry S, et al. Diagnostic accuracy of automated occlusion detection in CT angiography using e-CTA. Int J Stroke 2022;17:77-82. https://doi.org/10.1177/1747493021992592
  52. Yahav-Dovrat A, Saban M, Merhav G, Lankri I, Abergel E, Eran A, et al. Evaluation of artificial intelligence-powered identification of large-vessel occlusions in a comprehensive stroke center. AJNR Am J Neuroradiol 2021;42:247-54. https://doi.org/10.3174/ajnr.A6923
  53. Morey JR, Zhang X, Yaeger KA, Fiano E, Marayati NF, Kellner CP, et al. Real-world experience with artificial intelligence-based triage in transferred large vessel occlusion stroke patients. Cerebrovasc Dis 2021;50:450-5. https://doi.org/10.1159/000515320
  54. Adhya J, Li C, Eisenmenger L, Cerejo R, Tayal A, Goldberg M, et al. Positive predictive value and stroke workflow outcomes using automated vessel density (RAPID-CTA) in stroke patients: one year experience. Neuroradiol J 2021;34:476-81. https://doi.org/10.1177/19714009211012353
  55. Gao H, Bian Y, Cheng G, Yu H, Cao Y, Zhang H, et al. Identifying patients with acute ischemic stroke within a 6-h window for the treatment of endovascular thrombectomy using deep learning and perfusion imaging. Front Med (Lausanne) 2023;10:1085437.
  56. Kim YC, Seo WK, Baek IY, Lee JE, Song HN, Chung JW, et al. Diffusion-weighted imaging-alone endovascular thrombectomy triage in acute stroke: simulating diffusion-perfusion mismatch using machine learning. J Stroke 2022;24:148-51. https://doi.org/10.5853/jos.2021.02817
  57. Albers GW, Marks MP, Kemp S, Christensen S, Tsai JP, Ortega-Gutierrez S, et al. Thrombectomy for stroke at 6 to 16 hours with selection by perfusion imaging. N Engl J Med 2018;378:708-18. https://doi.org/10.1056/NEJMoa1713973
  58. Nogueira RG, Jadhav AP, Haussen DC, Bonafe A, Budzik RF, Bhuva P, et al. Thrombectomy 6 to 24 hours after stroke with a mismatch between deficit and infarct. N Engl J Med 2018;378:11-21. https://doi.org/10.1056/NEJMoa1706442
  59. Deutschmann H, Hinteregger N, Wiesspeiner U, Kneihsl M, Fandler-Hofler S, Michenthaler M, et al. Automated MRI perfusion-diffusion mismatch estimation may be significantly different in individual patients when using different software packages. Eur Radiol 2021;31:658-65. https://doi.org/10.1007/s00330-020-07150-8
  60. Pistocchi S, Strambo D, Bartolini B, Maeder P, Meuli R, Michel P, et al. MRI software for diffusion-perfusion mismatch analysis may impact on patients' selection and clinical outcome. Eur Radiol 2022;32:1144-53. https://doi.org/10.1007/s00330-021-08211-2
  61. Yu Y, Xie Y, Thamm T, Gong E, Ouyang J, Christensen S, et al. Tissue at risk and ischemic core estimation using deep learning in acute stroke. AJNR Am J Neuroradiol 2021;42:1030-7. https://doi.org/10.3174/ajnr.A7081
  62. Yu Y, Christensen S, Ouyang J, Scalzo F, Liebeskind DS, Lansberg MG, et al. Predicting hypoperfusion lesion and target mismatch in stroke from diffusion-weighted MRI using deep learning. Radiology 2023;307:e220882.
  63. Venema SMU, Dankbaar JW, van der Lugt A, Dippel DWJ, van der Worp HB. Cerebral collateral circulation in the era of reperfusion therapies for acute ischemic stroke. Stroke 2022;53:3222-34. https://doi.org/10.1161/STROKEAHA.121.037869
  64. Wolff L, Venema SMU, Luijten SPR, Hofmeijer J, Martens JM, et al. Diagnostic performance of an algorithm for automated collateral scoring on computed tomography angiography. Eur Radiol 2022;32:5711-8. https://doi.org/10.1007/s00330-022-08627-4
  65. Jabal MS, Kallmes DF, Harston G, Campeau N, Schwartz K, Messina S, et al. Automated CT angiography collateral scoring in anterior large vessel occlusion stroke: a multireader study. Interv Neuroradiol 2023. (Epub ahead of print)
  66. Boers AMM, Barros RS, Jansen IGH, Berkhemer OA, Beenen LFM, Menon BK, et al. Value of quantitative collateral scoring on CT angiography in patients with acute ischemic stroke. AJNR Am J Neuroradiol 2018;39:1074-82. https://doi.org/10.3174/ajnr.A5623
  67. Gupta AC, Schaefer PW, Chaudhry ZA, Leslie-Mazwi TM, Chandra RV, Gonzalez RG, et al. Interobserver reliability of baseline noncontrast CT Alberta stroke program early CT score for intra-arterial stroke treatment selection. AJNR Am J Neuroradiol 2012;33:1046-9. https://doi.org/10.3174/ajnr.A2942
  68. Wardlaw JM, Farrall AJ, Perry D, von Kummer R, Mielke O, Moulin T, et al. Factors influencing the detection of early CT signs of cerebral ischemia: an internet-based, international multiobserver study. Stroke 2007;38:1250-6. https://doi.org/10.1161/01.STR.0000259715.53166.25
  69. Kuang H, Najm M, Chakraborty D, Maraj N, Sohn SI, Goyal M, et al. Automated ASPECTS on noncontrast CT scans in patients with acute ischemic stroke using machine learning. AJNR Am J Neuroradiol 2019;40:33-8. https://doi.org/10.3174/ajnr.A5889
  70. Maegerlein C, Fischer J, Monch S, Berndt M, Wunderlich S, Seifert CL, et al. Automated calculation of the Alberta stroke program early CT score: feasibility and reliability. Radiology 2019;291:141-8. https://doi.org/10.1148/radiol.2019181228
  71. Delio PR, Wong ML, Tsai JP, Hinson HE, McMenamy J, Le TQ, et al. Assistance from automated ASPECTS software improves reader performance. J Stroke Cerebrovasc Dis 2021;30:105829.
  72. Austein F, Wodarg F, Jurgensen N, Huhndorf M, Meyne J, Lindner T, et al. Automated versus manual imaging assessment of early ischemic changes in acute stroke: comparison of two software packages and expert consensus. Eur Radiol 2019;29:6285-92. https://doi.org/10.1007/s00330-019-06252-2
  73. Goebel J, Stenzel E, Guberina N, Wanke I, Koehrmann M, Kleinschnitz C, et al. Automated ASPECT rating: comparison between the frontier ASPECT score software and the Brainomix software. Neuroradiology 2018;60:1267-72. https://doi.org/10.1007/s00234-018-2098-x
  74. Hoelter P, Muehlen I, Goelitz P, Beuscher V, Schwab S, Doerfler A. Automated ASPECT scoring in acute ischemic stroke: comparison of three software tools. Neuroradiology 2020;62:1231-8. https://doi.org/10.1007/s00234-020-02439-3
  75. Chen W, Wu J, Wei R, Wu S, Xia C, Wang D, et al. Improving the diagnosis of acute ischemic stroke on non-contrast CT using deep learning: a multicenter study. Insights Imaging 2022;13:184.
  76. Gauriau R, Bizzo BC, Comeau DS, Hillis JM, Bridge CP, Chin JK, et al. Head CT deep learning model is highly accurate for early infarct estimation. Sci Rep 2023;13:189.
  77. Qiu W, Kuang H, Teleg E, Ospel JM, Sohn SI, Almekhlafi M, et al. Machine learning for detecting early infarction in acute stroke with non-contrast-enhanced CT. Radiology 2020;294:638-44. https://doi.org/10.1148/radiol.2020191193
  78. Purushotham A, Campbell BC, Straka M, Mlynash M, Olivot JM, Bammer R, et al. Apparent diffusion coefficient threshold for delineation of ischemic core. Int J Stroke 2015;10:348-53. https://doi.org/10.1111/ijs.12068
  79. Kim YC, Lee JE, Yu I, Song HN, Baek IY, Seong JK, et al. Evaluation of diffusion lesion volume measurements in acute ischemic stroke using encoder-decoder convolutional network. Stroke 2019;50:1444-51. https://doi.org/10.1161/STROKEAHA.118.024261
  80. Woo I, Lee A, Jung SC, Lee H, Kim N, Cho SJ, et al. Fully automatic segmentation of acute ischemic lesions on diffusion-weighted imaging using convolutional neural networks: comparison with conventional algorithms. Korean J Radiol 2019;20:1275-84. https://doi.org/10.3348/kjr.2018.0615
  81. Wang X, Fan Y, Zhang N, Li J, Duan Y, Yang B. Performance of machine learning for tissue outcome prediction in acute ischemic stroke: a systematic review and meta-analysis. Front Neurol 2022;13:910259.
  82. Goyal M, Ospel JM, Menon B, Almekhlafi M, Jayaraman M, Fiehler J, et al. Challenging the ischemic core concept in acute ischemic stroke imaging. Stroke 2020;51:3147-55. https://doi.org/10.1161/STROKEAHA.120.030620
  83. Liu QC, Jia ZY, Zhao LB, Cao YZ, Ma G, Shi HB, et al. Agreement and accuracy of ischemic core volume evaluated by three CT perfusion software packages in acute ischemic stroke. J Stroke Cerebrovasc Dis 2021;30:105872.
  84. Lu Q, Fu J, Lv K, Han Y, Pan Y, Xu Y, et al. Agreement of three CT perfusion software packages in patients with acute ischemic stroke: a comparison with RAPID. Eur J Radiol 2022;156:110500.
  85. Rava RA, Snyder KV, Mokin M, Waqas M, Zhang X, Podgorsak AR, et al. Assessment of computed tomography perfusion software in predicting spatial location and volume of infarct in acute ischemic stroke patients: a comparison of Sphere, Vitrea, and RAPID. J Neurointerv Surg 2021;13:130-5. https://doi.org/10.1136/neurintsurg-2020-015966
  86. Campbell BC, Mitchell PJ, Kleinig TJ, Dewey HM, Churilov L, Yassi N, et al. Endovascular therapy for ischemic stroke with perfusion-imaging selection. N Engl J Med 2015;372:1009-18. https://doi.org/10.1056/NEJMoa1414792
  87. Saver JL, Goyal M, Diener HC; SWIFT PRIME Investigators. Stent-Retriever thrombectomy for stroke. N Engl J Med 2015;373:1077.
  88. Hakim A, Christensen S, Winzeck S, Lansberg MG, Parsons MW, Lucas C, et al. Predicting infarct core from computed tomography perfusion in acute ischemia with machine learning: lessons from the ISLES challenge. Stroke 2021;52:2328-37. https://doi.org/10.1161/STROKEAHA.120.030696
  89. Kuang H, Qiu W, Boers AM, Brown S, Muir K, Majoie CBLM, et al. Computed tomography perfusion-based machine learning model better predicts follow-up infarction in patients with acute ischemic stroke. Stroke 2021;52:223-31. https://doi.org/10.1161/STROKEAHA.120.030092
  90. Robben D, Boers AMM, Marquering HA, Langezaal LLCM, Roos YBWEM, van Oostenbrugge RJ, et al. Prediction of final infarct volume from native CT perfusion and treatment parameters using deep learning. Med Image Anal 2020;59:101589.
  91. Winder AJ, Wilms M, Amador K, Flottmann F, Fiehler J, Forkert ND. Predicting the tissue outcome of acute ischemic stroke from acute 4D computed tomography perfusion imaging using temporal features and deep learning. Front Neurosci 2022;16:1009654.
  92. Wouters A, Robben D, Christensen S, Marquering HA, Roos YBWEM, van Oostenbrugge RJ, et al. Prediction of stroke infarct growth rates by baseline perfusion imaging. Stroke 2022;53:569-77. https://doi.org/10.1161/STROKEAHA.121.034444
  93. Nazari-Farsani S, Yu Y, Armindo RD, Lansberg M, Liebeskind DS, Albers G, et al. Predicting final ischemic stroke lesions from initial diffusion-weighted images using a deep neural network. Neuroimage Clin 2023;37:103278.
  94. Yu Y, Xie Y, Thamm T, Gong E, Ouyang J, Huang C, et al. Use of deep learning to predict final ischemic stroke lesions from initial magnetic resonance imaging. JAMA Netw Open 2020;3:e200772.
  95. Hong L, Hsu TM, Zhang Y, Cheng X. Neuroimaging prediction of hemorrhagic transformation for acute ischemic stroke. Cerebrovasc Dis 2022;51:542-52. https://doi.org/10.1159/000521150
  96. Xu J, Dai F, Wang B, Wang Y, Li J, Pan L, et al. Predictive value of CT perfusion in hemorrhagic transformation after acute ischemic stroke: a systematic review and meta-analysis. Brain Sci 2023;13:156.
  97. Yu Y, Guo D, Lou M, Liebeskind D, Scalzo F. Prediction of hemorrhagic transformation severity in acute stroke from source perfusion MRI. IEEE Trans Biomed Eng 2018;65:2058-65. https://doi.org/10.1109/TBME.2017.2783241
  98. Meng Y, Wang H, Wu C, Liu X, Qu L, Shi Y. Prediction model of hemorrhage transformation in patient with acute ischemic stroke based on multiparametric MRI radiomics and machine learning. Brain Sci 2022;12:858.
  99. Jiang L, Zhou L, Yong W, Cui J, Geng W, Chen H, et al. A deep learning-based model for prediction of hemorrhagic transformation after stroke. Brain Pathol 2023;33:e13023. 
  100. Dragos HM, Stan A, Pintican R, Feier D, Lebovici A, Panaitescu Ps, et al. MRI radiomics and predictive models in assessing ischemic stroke outcome-a systematic review. Diagnostics (Basel) 2023;13:857. 
  101. Garg R, Oh E, Naidech A, Kording K, Prabhakaran S. Automating ischemic stroke subtype classification using machine learning and natural language processing. J Stroke Cerebrovasc Dis 2019;28:2045-51.  https://doi.org/10.1016/j.jstrokecerebrovasdis.2019.02.004
  102. Guan W, Ko D, Khurshid S, Lipsanopoulos ATT, Ashburner JM, Harrington LX, et al. Automated electronic phenotyping of cardioembolic stroke. Stroke 2021;52:181-9.  https://doi.org/10.1161/STROKEAHA.120.030663
  103. Abedi V, Goyal N, Tsivgoulis G, Hosseinichimeh N, Hontecillas R, Bassaganya-Riera J, et al. Novel screening tool for stroke using artificial neural network. Stroke 2017;48:1678-81.  https://doi.org/10.1161/STROKEAHA.117.017033
  104. Stanciu A, Banciu M, Sadighi A, Marshall KA, Holland NR, Abedi V, et al. A predictive analytics model for differentiating between transient ischemic attacks (TIA) and its mimics. BMC Med Inform Decis Mak 2020;20:112. 
  105. Abedi V, Khan A, Chaudhary D, Misra D, Avula V, Mathrawala D, et al. Using artificial intelligence for improving stroke diagnosis in emergency departments: a practical framework. Ther Adv Neurol Disord 2020;13:1756286420938962. 
  106. Kamel H, Navi BB, Parikh NS, Merkler AE, Okin PM, Devereux RB, et al. Machine learning prediction of stroke mechanism in embolic strokes of undetermined source. Stroke 2020;51:e203-10.  https://doi.org/10.1161/STROKEAHA.120.029305
  107. Martin MC, Sichtermann T, Schurmann K, Habib P, Wiesmann M, Schulz JB, et al. Classification of patients with embolic stroke of undetermined source into cardioembolic and non-cardioembolic profile subgroups. Eur J Neurol 2022;29:2275-82.  https://doi.org/10.1111/ene.15356
  108. Ntaios G, Faouzi M, Ferrari J, Lang W, Vemmos K, Michel P. An integer-based score to predict functional outcome in acute ischemic stroke: the ASTRAL score. Neurology 2012;78:1916-22.  https://doi.org/10.1212/WNL.0b013e318259e221
  109. Saposnik G, Kapral MK, Liu Y, Hall R, O'Donnell M, Raptis S, et al. IScore: a risk score to predict death early after hospitalization for an acute ischemic stroke. Circulation 2011;123:739-49. https://doi.org/10.1161/CIRCULATIONAHA.110.983353
  110. Kim SH, Jeon ET, Yu S, Oh K, Kim CK, Song TJ, et al. Interpretable machine learning for early neurological deterioration prediction in atrial fibrillation-related stroke. Sci Rep 2021;11:20610.
  111. Xu Y, Yang X, Huang H, Peng C, Ge Y, Wu H, et al. Extreme gradient boosting model has a better performance in predicting the risk of 90-day readmissions in patients with ischaemic stroke. J Stroke Cerebrovasc Dis 2019;28:104441.
  112. Meinel T, Lerch C, Fischer U, Beyeler M, Mujanovic A, Kurmann C, et al. Multivariable prediction model for futile recanalization therapies in patients with acute ischemic stroke. Neurology 2022;99:e1009-18. https://doi.org/10.1212/WNL.0000000000200815
  113. Zeng W, Li W, Huang K, Lin Z, Dai H, He Z, et al. Predicting futile recanalization, malignant cerebral edema, and cerebral herniation using intelligible ensemble machine learning following mechanical thrombectomy for acute ischemic stroke. Front Neurol 2022;13:982783.
  114. Sung SF, Chen CH, Pan RC, Hu YH, Jeng JS. Natural language processing enhances prediction of functional outcome after acute ischemic stroke. J Am Heart Assoc 2021;10:e023486.
  115. Philbrick KA, Yoshida K, Inoue D, Akkus Z, Kline TL, Weston AD, et al. What does deep learning see? Insights from a classifier trained to predict contrast enhancement phase from CT images. AJR Am J Roentgenol 2018;211:1184-93. https://doi.org/10.2214/AJR.18.20331
  116. van der Velden BHM, Kuijf HJ, Gilhuijs KGA, Viergever MA. Explainable artificial intelligence (XAI) in deep learning-based medical image analysis. Med Image Anal 2022;79:102470.
  117. Sveding JJ. Unsupervised image-to-image translation: taking inspiration from human perception [Master's thesis]. Vaxjo (SE): Linnaeus University; 2021.
  118. Tuladhar A, Schimert S, Rajashekar D, Kniep HC, Fiehler J, Forkert ND. Automatic segmentation of stroke lesions in non-contrast computed tomography datasets with convolutional neural networks. IEEE Access 2020;8:94871-9. https://doi.org/10.1109/ACCESS.2020.2995632
  119. Brugnara G, Neuberger U, Mahmutoglu MA, Foltyn M, Herweh C, Nagel S, et al. Multimodal predictive modeling of endovascular treatment outcome for acute ischemic stroke using machine-learning. Stroke 2020;51:3541-51. https://doi.org/10.1161/STROKEAHA.120.030287
  120. Quan G, Ban R, Ren JL, Liu Y, Wang W, Dai S, et al. FLAIR and ADC image-based radiomics features as predictive biomarkers of unfavorable outcome in patients with acute ischemic stroke. Front Neurosci 2021;15:730879.
  121. Moulton E, Valabregue R, Piotin M, Marnat G, Saleme S, Lapergue B, et al. Interpretable deep learning for the prognosis of long-term functional outcome post-stroke using acute diffusion weighted imaging. J Cereb Blood Flow Metab 2023;43:198-209.
  122. Ntaios G, Sagris D, Kallipolitis A, Karagkiozi E, Korompoki E, Manios E, et al. Machine-learning-derived model for the stratification of cardiovascular risk in patients with ischemic stroke. J Stroke Cerebrovasc Dis 2021;30:106018.
  123. Wang H, Sun Y, Zhu J, Zhuang Y, Song B. Diffusion-weighted imaging-based radiomics for predicting 1-year ischemic stroke recurrence. Front Neurol 2022;13:1012896.