Prediction of Functional Outcome in Stroke Patients with Proximal Middle Cerebral Artery Occlusions Using Machine Learning Models

被引:10
|
作者
Ozkara, Burak B. [1 ]
Karabacak, Mert [2 ]
Hamam, Omar [3 ]
Wang, Richard [3 ]
Kotha, Apoorva [3 ]
Khalili, Neda [3 ]
Hoseinyazdi, Meisam [3 ]
Chen, Melissa M. [1 ]
Wintermark, Max [1 ]
Yedavalli, Vivek S. [3 ]
机构
[1] MD Anderson Canc Ctr, Dept Neuroradiol, Houston, TX 77030 USA
[2] Mt Sinai Hlth Syst, Dept Neurosurg, New York, NY 10029 USA
[3] Johns Hopkins Univ Hosp, Russell H Morgan Dept Radiol & Radiol Sci, Baltimore, MD 21287 USA
关键词
ischemic stroke; machine learning; medical decision making; middle cerebral artery; artificial intelligence; ACUTE ISCHEMIC-STROKE; MECHANICAL THROMBECTOMY; VESSEL OCCLUSION; SCORE;
D O I
10.3390/jcm12030839
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
At present, clinicians are expected to manage a large volume of complex clinical, laboratory, and imaging data, necessitating sophisticated analytic approaches. Machine learning-based models can use this vast amount of data to create forecasting models. We aimed to predict short- and medium-term functional outcomes in acute ischemic stroke (AIS) patients with proximal middle cerebral artery (MCA) occlusions using machine learning models with clinical, laboratory, and quantitative imaging data as inputs. Included were consecutive AIS patients with MCA M1 and proximal M2 occlusions. The XGBoost, LightGBM, CatBoost, and Random Forest were used to predict the outcome. Minimum redundancy maximum relevancy was used for selecting features. The primary outcomes were the National Institutes of Health Stroke Scale (NIHSS) shift and the modified Rankin Score (mRS) at 90 days. The algorithm with the highest area under the receiver operating characteristic curve (AUROC) for predicting the favorable and unfavorable outcome groups at 90 days was LightGBM. Random Forest had the highest AUROC when predicting the favorable and unfavorable groups based on the NIHSS shift. Using clinical, laboratory, and imaging parameters in conjunction with machine learning, we accurately predicted the functional outcome of AIS patients with proximal MCA occlusions.
引用
收藏
页数:16
相关论文
共 50 条
  • [21] Prediction of stroke thrombolysis outcome using CT brain machine learning
    Bentley, Paul
    Ganesalingam, Jeban
    Jones, Anoma Lalani Carlton
    Mahady, Kate
    Epton, Sarah
    Rinne, Paul
    Sharma, Pankaj
    Halse, Omid
    Mehta, Amrish
    Rueckert, Daniel
    NEUROIMAGE-CLINICAL, 2014, 4 : 635 - 640
  • [22] Prediction of Hidden Coronary Artery Disease Using Machine Learning in Patients With Acute Ischemic Stroke
    Heo, JoonNyung
    Yoo, Joonsang
    Lee, Hyungwoo
    Lee, Il Hyung
    Kim, Jung-Sun
    Park, Eunjeong
    Kim, Young Dae
    Nam, Hyo Suk
    NEUROLOGY, 2022, 99 (01) : E55 - E65
  • [23] Clinical Outcome Prediction Pipeline for Ischemic Stroke Patients Using Radiomics Features and Machine Learning
    Erdogan, Meryem Sahin
    Sumer, Esra
    Villagra, Federico
    Isik, Esin Ozturk
    Akanyeti, Otar
    Saybasili, Hale
    ADVANCES IN COMPUTATIONAL INTELLIGENCE SYSTEMS, UKCI 2023, 2024, 1453 : 504 - 515
  • [24] Dynamic Prediction of Mechanical Thrombectomy Outcome for Acute Ischemic Stroke Patients Using Machine Learning
    Hu, Yixing
    Yang, Tongtong
    Zhang, Juan
    Wang, Xixi
    Cui, Xiaoli
    Chen, Nihong
    Zhou, Junshan
    Jiang, Fuping
    Zhu, Junrong
    Zou, Jianjun
    BRAIN SCIENCES, 2022, 12 (07)
  • [25] Management of minor stroke patients with proximal middle cerebral artery occlusion in the new era of thrombectomy
    Gory, B.
    Labeyrie, P. -E.
    Riva, R.
    Sivan-Hoffmann, R.
    Derex, L.
    Lehot, J. -J.
    Philippeau, F.
    Turjman, F.
    JOURNAL OF NEURORADIOLOGY, 2016, 43 (01) : 55 - 56
  • [26] Endovascular treatment of patients with stroke caused by anterior cerebral artery occlusions
    Vos, Erik M.
    Kappelhof, Manon
    den Hartog, Sanne J.
    Coutinho, Jonathan M.
    Emmer, Bart J.
    Roozenbeek, Bob
    van Zwam, Wim H.
    van Oostenbrugge, Robert J.
    van der Worp, H. Bart
    Uyttenboogaart, Maarten
    van Es, Adriaan C. G. M.
    Majoie, Charles B. L. M.
    Dippel, Diederik W. J.
    Peeters-Scholte, Cacha M. P. C. D.
    van den Wijngaard, Ido R.
    ACTA NEUROLOGICA BELGICA, 2024, 124 (02) : 621 - 630
  • [27] Endovascular treatment of patients with stroke caused by anterior cerebral artery occlusions
    Erik M. Vos
    Manon Kappelhof
    Sanne J. den Hartog
    Jonathan M. Coutinho
    Bart J. Emmer
    Bob Roozenbeek
    Wim H. van Zwam
    Robert J. van Oostenbrugge
    H. Bart van der Worp
    Maarten Uyttenboogaart
    Adriaan C. G. M. van Es
    Charles B. L. M. Majoie
    Diederik W. J. Dippel
    Cacha M. P. C. D. Peeters-Scholte
    Ido R. van den Wijngaard
    Acta Neurologica Belgica, 2024, 124 : 621 - 630
  • [28] Insular involvement in acute middle cerebral artery stroke patients presenting to the emergency department as a window to stroke severity, stroke subtype, functional outcome and survival
    Bhagra, A.
    Vaidyanathan, L.
    Gilmore, R. M.
    De Jesus, R.
    Decker, W. W.
    Kashyap, R.
    Stead, L. G.
    ANNALS OF EMERGENCY MEDICINE, 2006, 48 (04) : S21 - S21
  • [29] Prediction of Motor Function in Stroke Patients Using Machine Learning Algorithm: Development of Practical Models
    Kim, Jeoung Kun
    Choo, Yoo Jin
    Chang, Min Cheol
    JOURNAL OF STROKE & CEREBROVASCULAR DISEASES, 2021, 30 (08):
  • [30] Prediction of perinatal outcome by middle cerebral artery doppler velocimetry
    Alatas, C
    Aksoy, E
    Akarsu, C
    Yakin, K
    Bahceci, M
    ARCHIVES OF GYNECOLOGY AND OBSTETRICS, 1996, 258 (03) : 141 - 146