Literature DB >> 31705256

Prediction of pulmonary pressure after Glenn shunts by computed tomography-based machine learning models.

Lei Huang1,2, Jiahua Li3, Meiping Huang4, Jian Zhuang5, Haiyun Yuan4, Qianjun Jia4, Dewen Zeng6, Lifeng Que3, Yue Xi3, Jijin Lin7,8, Yuhao Dong9.   

Abstract

OBJECTIVES: This study aimed to develop non-invasive machine learning classifiers for predicting post-Glenn shunt patients with low and high risks of a mean pulmonary arterial pressure (mPAP) > 15 mmHg based on preoperative cardiac computed tomography (CT).
METHODS: This retrospective study included 96 patients with functional single ventricle who underwent a bidirectional Glenn procedure between November 1, 2009, and July, 31, 2017. All patients underwent post-procedure CT, followed by cardiac catheterization. Overall, 23 morphologic parameters were manually extracted from cardiac CT images for each patient. The Mann-Whitney U or chi-square test was applied to select the most significant predictors. Six machine learning algorithms including logistic regression, Naive Bayes, random forest (RF), linear discriminant analysis, support vector machine, and K-nearest neighbor were used for modeling. These algorithms were independently trained on 100 train-validation random splits with a 3:1 ratio. Their average performance was evaluated by area under the curve (AUC), accuracy, sensitivity, and specificity.
RESULTS: Seven CT morphologic parameters were selected for modeling. RF obtained the best performance, with mean AUC of 0.840 (confidence interval [CI] 0.832-0.850) and 0.787 (95% CI 0.780-0.794); sensitivity of 0.815 (95% CI 0.797-0.833) and 0.778 (95% CI 0.767-0.788), specificity of 0.766 (95% CI 0.748-0.785) and 0.746 (95% CI 0.735-0.757); and accuracy of 0.782 (95% CI 0.771-0.793) and 0.756 (95% CI 0.748-0.764) in the training and validation cohorts, respectively.
CONCLUSIONS: The CT-based RF model demonstrates a good performance in the prediction of mPAP, which may reduce the need for right heart catheterization in post-Glenn shunt patients with suspected mPAP > 15 mmHg. KEY POINTS: • Twenty-three candidate descriptors were manually extracted from cardiac computed tomography images, and seven of them were selected for subsequent modeling. • The random forest model presents the best predictive performance for pulmonary pressure among all methods. • The computed tomography-based machine learning model could predict post-Glenn shunt pulmonary pressure non-invasively.

Entities:  

Keywords:  Heart diseases; Lung; Machine learning; Multi-detector computed tomography; Pressure

Year:  2019        PMID: 31705256     DOI: 10.1007/s00330-019-06502-3

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   5.315


  40 in total

1.  Machine Learning and the Profession of Medicine.

Authors:  Alison M Darcy; Alan K Louie; Laura Weiss Roberts
Journal:  JAMA       Date:  2016-02-09       Impact factor: 56.272

2.  Radiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma.

Authors:  Bin Zhang; Xin He; Fusheng Ouyang; Dongsheng Gu; Yuhao Dong; Lu Zhang; Xiaokai Mo; Wenhui Huang; Jie Tian; Shuixing Zhang
Journal:  Cancer Lett       Date:  2017-06-10       Impact factor: 8.679

3.  Significant survival advantage of high pulmonary vein index and the presence of native pulmonary artery in pulmonary atresia with ventricular septal defect and major aortopulmonary collateral arteries: results from preoperative computed tomography angiography.

Authors:  Qianjun Jia; Jianzheng Cen; Jian Zhuang; Xiaomei Zhong; Xiaoqing Liu; Jiahua Li; Changhong Liang; Meiping Huang
Journal:  Eur J Cardiothorac Surg       Date:  2017-08-01       Impact factor: 4.191

4.  The assisted bidirectional Glenn: a novel surgical approach for first-stage single-ventricle heart palliation.

Authors:  Mahdi Esmaily-Moghadam; Tain-Yen Hsia; Alison L Marsden
Journal:  J Thorac Cardiovasc Surg       Date:  2014-10-15       Impact factor: 5.209

Review 5.  Artificial Intelligence in Precision Cardiovascular Medicine.

Authors:  Chayakrit Krittanawong; HongJu Zhang; Zhen Wang; Mehmet Aydar; Takeshi Kitai
Journal:  J Am Coll Cardiol       Date:  2017-05-30       Impact factor: 24.094

6.  A comparison of the modified Blalock-Taussig shunt with the right ventricle-to-pulmonary artery conduit.

Authors:  Andrew C Fiore; Courtney Tobin; Saadeh Jureidini; Mohammad Rahimi; Eric S Kim; Kenneth Schowengerdt
Journal:  Ann Thorac Surg       Date:  2011-05       Impact factor: 4.330

7.  Radiomics features on non-contrast-enhanced CT scan can precisely classify AVM-related hematomas from other spontaneous intraparenchymal hematoma types.

Authors:  Yupeng Zhang; Baorui Zhang; Fei Liang; Shikai Liang; Yuxiang Zhang; Peng Yan; Chao Ma; Aihua Liu; Feng Guo; Chuhan Jiang
Journal:  Eur Radiol       Date:  2018-10-10       Impact factor: 5.315

8.  CT features of pulmonary arterial hypertension and its major subtypes: a systematic CT evaluation of 292 patients from the ASPIRE Registry.

Authors:  S Rajaram; A J Swift; R Condliffe; C Johns; C A Elliot; C Hill; C Davies; J Hurdman; I Sabroe; J M Wild; D G Kiely
Journal:  Thorax       Date:  2014-12-18       Impact factor: 9.139

Review 9.  Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges.

Authors:  Benjamin A Goldstein; Ann Marie Navar; Rickey E Carter
Journal:  Eur Heart J       Date:  2017-06-14       Impact factor: 29.983

10.  Random forest-based similarity measures for multi-modal classification of Alzheimer's disease.

Authors:  Katherine R Gray; Paul Aljabar; Rolf A Heckemann; Alexander Hammers; Daniel Rueckert
Journal:  Neuroimage       Date:  2012-10-04       Impact factor: 6.556

View more
  1 in total

Review 1.  The role of machine learning applications in diagnosing and assessing critical and non-critical CHD: a scoping review.

Authors:  Stephanie M Helman; Elizabeth A Herrup; Adam B Christopher; Salah S Al-Zaiti
Journal:  Cardiol Young       Date:  2021-11-02       Impact factor: 1.093

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.