Novel Survival Features Generated by Clinical Text Information and Radiomics Features May Improve the Prediction of Ischemic Stroke Outcome

被引:10
|
作者
Guo, Yingwei [1 ,2 ]
Yang, Yingjian [1 ,2 ]
Cao, Fengqiu [1 ]
Li, Wei [2 ]
Wang, Mingming [3 ]
Luo, Yu [3 ]
Guo, Jia [4 ]
Zaman, Asim [2 ,5 ]
Zeng, Xueqiang [2 ,5 ]
Miu, Xiaoqiang [1 ,2 ]
Li, Longyu [2 ]
Qiu, Weiyan [2 ]
Kang, Yan [1 ,2 ,5 ,6 ]
机构
[1] Northeastern Univ, Coll Med & Biol Informat Engn, Shenyang 110169, Peoples R China
[2] Shenzhen Technol Univ, Coll Hlth Sci & Environm Engn, Shenzhen 518118, Peoples R China
[3] Tongji Univ, Dept Radiol, Shanghai Peoples Hosp 4, Sch Med, Shanghai 200434, Peoples R China
[4] Columbia Univ, Dept Psychiat, New York, NY 10027 USA
[5] Minist Educ, Engn Res Ctr Med Imaging & Intelligent Anal, Shenyang 110169, Peoples R China
[6] Shenzhen Univ, Sch Appl Technol, Shenzhen 518060, Peoples R China
基金
中国国家自然科学基金;
关键词
ischemic stroke outcome; clinical text information; radiomics features; survival features; machine learning; BLOOD-FLOW; PERFUSION; IDENTIFICATION; DIFFUSION; TRIAL; MORTALITY; EVOLUTION; ADMISSION; INFARCT; LESIONS;
D O I
10.3390/diagnostics12071664
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Background: Accurate outcome prediction is of great clinical significance in customizing personalized treatment plans, reducing the situation of poor recovery, and objectively and accurately evaluating the treatment effect. This study intended to evaluate the performance of clinical text information (CTI), radiomics features, and survival features (SurvF) for predicting functional outcomes of patients with ischemic stroke. Methods: SurvF was constructed based on CTI and mRS radiomics features (mRSRF) to improve the prediction of the functional outcome in 3 months (90-day mRS). Ten machine learning models predicted functional outcomes in three situations (2-category, 4-category, and 7-category) using seven feature groups constructed by CTI, mRSRF, and SurvF. Results: For 2-category, ALL (CTI + mRSRF+ SurvF) performed best, with an mAUC of 0.884, mAcc of 0.864, mPre of 0.877, mF1 of 0.86, and mRecall of 0.864. For 4-category, ALL also achieved the best mAuc of 0.787, while CTI + SurvF achieved the best score with mAcc = 0.611, mPre = 0.622, mF1 = 0.595, and mRe-call = 0.611. For 7-category, CTI + SurvF performed best, with an mAuc of 0.788, mPre of 0.519, mAcc of 0.529, mF1 of 0.495, and mRecall of 0.47. Conclusions: The above results indicate that mRSRF + CTI can accurately predict functional outcomes in ischemic stroke patients with proper machine learning models. Moreover, combining SurvF will improve the prediction effect compared with the original features. However, limited by the small sample size, further validation on larger and more varied datasets is necessary.
引用
收藏
页数:23
相关论文
共 50 条
  • [21] Improved multi-parametric prediction of tissue outcome in acute ischemic stroke patients using spatial features
    Grosser, Malte
    Gellissen, Susanne
    Borchert, Patrick
    Sedlacik, Jan
    Nawabi, Jawed
    Fiehler, Jens
    Forkert, Nils Daniel
    PLOS ONE, 2020, 15 (01):
  • [22] Intravenous Thrombolysis May Not Improve Clinical Outcome of Acute Ischemic Stroke Patients Without a Baseline Vessel Occlusion
    Tian, Huiqiao
    Parsons, Mark W.
    Levi, Christopher R.
    Cheng, Xin
    Aviv, Richard, I
    Spratt, Neil J.
    Kleinig, Timothy J.
    O'Brien, Billy
    Butcher, Kenneth S.
    Lin, Longting
    Zhang, Jingfen
    Dong, Qiang
    Chen, Chushuang
    Bivard, Andrew
    FRONTIERS IN NEUROLOGY, 2018, 9
  • [23] Ischemic stroke outcome prediction with diversity features from whole brain tissue using deep learning network
    Yang, Yingjian
    Guo, Yingwei
    FRONTIERS IN NEUROLOGY, 2024, 15
  • [24] A Machine-Learning Model Based on Clinical Features for the Prediction of Severe Dysphagia After Ischemic Stroke
    Ye, Feng
    Cheng, Liang-Ling
    Li, Wei-Min
    Guo, Ying
    Fan, Xiao-Fang
    INTERNATIONAL JOURNAL OF GENERAL MEDICINE, 2024, 17 : 5623 - 5631
  • [25] Quantitative Serial CT Imaging-Derived Features Improve Prediction of Malignant Cerebral Edema after Ischemic Stroke
    Foroushani, Hossein Mohammadian
    Hamzehloo, Ali
    Kumar, Atul
    Chen, Yasheng
    Heitsch, Laura
    Slowik, Agnieszka
    Strbian, Daniel
    Lee, Jin-Moo
    Marcus, Daniel S.
    Dhar, Rajat
    NEUROCRITICAL CARE, 2020, 33 (03) : 785 - 792
  • [26] Quantitative Serial CT Imaging-Derived Features Improve Prediction of Malignant Cerebral Edema after Ischemic Stroke
    Hossein Mohammadian Foroushani
    Ali Hamzehloo
    Atul Kumar
    Yasheng Chen
    Laura Heitsch
    Agnieszka Slowik
    Daniel Strbian
    Jin-Moo Lee
    Daniel S. Marcus
    Rajat Dhar
    Neurocritical Care, 2020, 33 : 785 - 792
  • [27] Prediction Enhancement of the Post-Stroke Delirium by Adding of the Brain Lesional Characteristics to the Clinical Features in Acute Ischemic Stroke Patients
    Jeong, Hye Seon
    Yang, Hee Won
    Lee, Seo Hyun
    Hyon, Yun Kyong
    Jeon, Kiwan
    Lee, Miji
    Ha, Taeyoung
    Kim, Jeong Lan
    Lee, Sukhoon
    Kim, Jei
    STROKE, 2021, 52
  • [28] Prediction of Functional Outcome After Acute Ischemic Stroke: Comparison of the CT-DRAGON Score and a Reduced Features Set
    Lesenne, Anouk
    Grieten, Jef
    Ernon, Ludovic
    Wibail, Alain
    Stockx, Luc
    Wouters, Patrick F.
    Dreesen, Leentje
    Vandermeulen, Elly
    Van Boxstael, Sam
    Vanelderen, Pascal
    Van Poucke, Sven
    Vundelinckx, Joris
    Van Cauter, Sofie
    Mesotten, Dieter
    FRONTIERS IN NEUROLOGY, 2020, 11
  • [29] Application of novel hybrid machine learning systems and radiomics features for non-motor outcome prediction in Parkinson's disease
    Salmanpour, Mohammad R.
    Bakhtiyari, Mahya
    Hosseinzadeh, Mahdi
    Maghsudi, Mehdi
    Yousefirizi, Fereshteh
    Ghaemi, Mohammad M.
    Rahmim, Arman
    PHYSICS IN MEDICINE AND BIOLOGY, 2023, 68 (03):
  • [30] Rate, Clinical features, Safety Profile and Outcome of Intravenous Thrombolysis for Acute Ischemic Stroke in Patients with Negative Brain Imaging
    Mowla, Ashkan
    Kamal, Haris
    Mehla, Sandhya
    Shirani, Peyman
    Singh, Karanbir
    Farooq, Salman
    Crumlish, Annmarie
    Ching, Marilou
    Sawyer, Robert N.
    STROKE, 2015, 46