Machine-learning algorithm in acute stroke: real-world experience

被引:7
|
作者
Chan, N. [1 ,2 ]
Sibtain, N. [1 ]
Booth, T. [1 ,3 ]
de Souza, P. [4 ]
Bibby, S. [1 ]
Mah, Y. -h. [5 ]
Teo, J. [5 ]
U-King-Im, J. M. [1 ]
机构
[1] Kings Coll Hosp London, Dept Neuroradiol, London, England
[2] Royal London Hosp, Dept Intervent Neuroradiol, Whitechapel Rd, London E1 1BB, England
[3] Kings Coll London, Sch Biomed Engn & Imaging Sci, London, England
[4] Royal London Hosp, Dept Neuroradiol, London, England
[5] Kings Coll Hosp London, Dept Neurol, London, England
关键词
ENDOVASCULAR THROMBECTOMY; ISCHEMIC-STROKE;
D O I
10.1016/j.crad.2022.10.007
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
AIM: To assess the clinical performance of a commercially available machine learning (ML) algorithm in acute stroke.MATERIALS AND METHODS: CT and CT angiography (CTA) studies of 104 consecutive pa-tients (43 females, age range 19-93, median age 62) performed for suspected acute stroke at a single tertiary institution with real-time ML software analysis (RAPIDTM ASPECTS and CTA) were included. Studies were retrospectively reviewed independently by two neuroradiologists in a blinded manner. RESULTS: The cohort included 24 acute infarcts and 16 large vessel occlusions (LVO). RAPIDTM ASPECTS interpretation demonstrated high sensitivity (87.5%) and NPV (87.5%) but very poor specificity (30.9%) and PPV (30.9%) for detection of acute ischaemic parenchymal changes. There was a high percentage of false positives (51.1%). In cases of proven LVO, RAPIDTM ASPECTS showed good correlation with neuroradiologists' blinded independent interpretation, Pearson correlation coefficient = 0.96 (both readers), 0.63 (RAPIDTM vs reader 1), 0.69 (RAPIDTM vs reader 2).RAPIDTM CTA interpretation demonstrated high sensitivity (92.3%), specificity (85.3%), and negative predictive (NPV) (98.5%) with moderate positive predictive value (PPV) (52.2%) for detection of LVO (N=13). False positives accounted for 12.5% of cases, of which 27.3% were attributed to arterial stenosis.CONCLUSION: RAPIDTM CTA was robust and reliable in detection of LVO. Although demon-strating high sensitivity and NPV, RAPIDTM ASPECTS interpretation was associated with a high number of false positives, which decreased clinicians' confidence in the algorithm. However, in cases of proven LVO, RAPIDTM ASPECTS performed well and had good correlation with neu-roradiologists' blinded interpretation. (c) 2022 The Royal College of Radiologists. Published by Elsevier Ltd. All rights reserved.
引用
收藏
页码:E45 / E51
页数:7
相关论文
共 50 条
  • [41] Real-world experience of apremilast
    Fremlin, G. A.
    Bedlow, A.
    BRITISH JOURNAL OF DERMATOLOGY, 2017, 177 : 63 - 63
  • [42] Real-World Experience with Ocrelizumab
    Moss, Brandon
    Parrotta, Erica
    Baldassari, Laura
    Cohen, Jeffrey
    Ontaneda, Daniel
    NEUROLOGY, 2019, 92 (15)
  • [43] REAL-WORLD EXPERIENCE IN CHEMISTRY
    MELTON, LA
    SCIENCE, 1994, 266 (5183) : 203 - 204
  • [44] Real-world experience with abiraterone
    Dahut, William L.
    Madan, Ravi A.
    LANCET ONCOLOGY, 2014, 15 (11): : 1188 - 1190
  • [45] A real-world experience: Really?
    Mitchell, R. Scott
    JOURNAL OF THORACIC AND CARDIOVASCULAR SURGERY, 2018, 156 (06): : 2074 - 2075
  • [46] Education for Real-World Experience
    Sisson, Patrick
    ARCHITECT, 2020, 109 (09): : 66 - 68
  • [47] Real-World Experience with Ocrelizumab
    Moss, Brandon
    Utigard, Erica
    Baldassari, Laura
    Cohen, Jeffrey
    Ontaneda, Daniel
    NEUROLOGY, 2018, 90
  • [48] Real-world ice experience
    Backman, Anders
    Marine Technology, 2013, 50 (01) : 8 - 9
  • [49] A clinical prediction model based on interpretable machine learning algorithms for prolonged hospital stay in acute ischemic stroke patients: a real-world study
    Wang, Kai
    Jiang, Qianmei
    Gao, Murong
    Wei, Xiu'e
    Xu, Chan
    Yin, Chengliang
    Liu, Haiyan
    Gu, Renjun
    Wang, Haosheng
    Li, Wenle
    Rong, Liangqun
    FRONTIERS IN ENDOCRINOLOGY, 2023, 14
  • [50] REAL-WORLD OUTCOMES OF ACUTE ISCHEMIC STROKE PATIENTS IN THE MEDICARE POPULATION
    Watson, C.
    Burudpakdee, C.
    Noone, J.
    Seetasith, A.
    Nyandege, A.
    VALUE IN HEALTH, 2015, 18 (03) : A143 - A144