Predicting transient ischemic attack risk in patients with mild carotid stenosis using machine learning and CT radiomics
ObjectiveThis study aims to establish a radiomics-based machine learning model that predicts the risk of transient ischemic attack in patients with mild carotid stenosis (30–50% North American Symptomatic Carotid Endarterectomy Trial) using extracted computed tomography radiomics features and clinic...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-02-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2023.1105616/full |
| _version_ | 1828039522427863040 |
|---|---|
| author | Hai Xia Lei Yuan Wei Zhao Chenglei Zhang Lingfeng Zhao Jialin Hou Yancheng Luan Yuxin Bi Yaoyu Feng |
| author_facet | Hai Xia Lei Yuan Wei Zhao Chenglei Zhang Lingfeng Zhao Jialin Hou Yancheng Luan Yuxin Bi Yaoyu Feng |
| author_sort | Hai Xia |
| collection | DOAJ |
| description | ObjectiveThis study aims to establish a radiomics-based machine learning model that predicts the risk of transient ischemic attack in patients with mild carotid stenosis (30–50% North American Symptomatic Carotid Endarterectomy Trial) using extracted computed tomography radiomics features and clinical information.MethodsA total of 179 patients underwent carotid computed tomography angiography (CTA), and 219 carotid arteries with a plaque at the carotid bifurcation or proximal to the internal carotid artery were selected. The patients were divided into two groups; patients with symptoms of transient ischemic attack after CTA and patients without symptoms of transient ischemic attack after CTA. Then we performed random sampling methods stratified by the predictive outcome to obtain the training set (N = 165) and testing set (N = 66). 3D Slicer was employed to select the site of plaque on the computed tomography image as the volume of interest. An open-source package PyRadiomics in Python was used to extract radiomics features from the volume of interests. The random forest and logistic regression models were used to screen feature variables, and five classification algorithms were used, including random forest, eXtreme Gradient Boosting, logistic regression, support vector machine, and k-nearest neighbors. Data on radiomic feature information, clinical information, and the combination of these pieces of information were used to generate the model that predicts the risk of transient ischemic attack in patients with mild carotid artery stenosis (30–50% North American Symptomatic Carotid Endarterectomy Trial).ResultsThe random forest model that was built based on the radiomics and clinical feature information had the highest accuracy (area under curve = 0.879; 95% confidence interval, 0.787–0.979). The combined model outperformed the clinical model, whereas the combined model showed no significant difference from the radiomics model.ConclusionThe random forest model constructed with both radiomics and clinical information can accurately predict and improve discriminative power of computed tomography angiography in identifying ischemic symptoms in patients with carotid atherosclerosis. This model can aid in guiding the follow-up treatment of patients at high risk. |
| first_indexed | 2024-04-10T16:42:18Z |
| format | Article |
| id | doaj.art-8ff1a5eb2e1946f28ec92abc1d12f113 |
| institution | Directory Open Access Journal |
| issn | 1664-2295 |
| language | English |
| last_indexed | 2024-04-10T16:42:18Z |
| publishDate | 2023-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj.art-8ff1a5eb2e1946f28ec92abc1d12f1132023-02-08T06:01:26ZengFrontiers Media S.A.Frontiers in Neurology1664-22952023-02-011410.3389/fneur.2023.11056161105616Predicting transient ischemic attack risk in patients with mild carotid stenosis using machine learning and CT radiomicsHai Xia0Lei Yuan1Wei Zhao2Chenglei Zhang3Lingfeng Zhao4Jialin Hou5Yancheng Luan6Yuxin Bi7Yaoyu Feng8Department of Vascular Surgery, The First Affiliated Hospital of Kunming Medical University, Kunming, ChinaDepartment of Orthopedics, The First Affiliated Hospital of Kunming Medical University, Kunming, ChinaImaging Intervention Center, The First Affiliated Hospital of Kunming Medical University, Kunming, ChinaDepartment of Vascular Surgery, The First Affiliated Hospital of Kunming Medical University, Kunming, ChinaDepartment of Vascular Surgery, The First Affiliated Hospital of Kunming Medical University, Kunming, ChinaImaging Intervention Center, The First Affiliated Hospital of Kunming Medical University, Kunming, ChinaDepartment of Vascular Surgery, The First Affiliated Hospital of Kunming Medical University, Kunming, ChinaDepartment of Vascular Surgery, The First Affiliated Hospital of Kunming Medical University, Kunming, ChinaDepartment of Vascular Surgery, The First Affiliated Hospital of Kunming Medical University, Kunming, ChinaObjectiveThis study aims to establish a radiomics-based machine learning model that predicts the risk of transient ischemic attack in patients with mild carotid stenosis (30–50% North American Symptomatic Carotid Endarterectomy Trial) using extracted computed tomography radiomics features and clinical information.MethodsA total of 179 patients underwent carotid computed tomography angiography (CTA), and 219 carotid arteries with a plaque at the carotid bifurcation or proximal to the internal carotid artery were selected. The patients were divided into two groups; patients with symptoms of transient ischemic attack after CTA and patients without symptoms of transient ischemic attack after CTA. Then we performed random sampling methods stratified by the predictive outcome to obtain the training set (N = 165) and testing set (N = 66). 3D Slicer was employed to select the site of plaque on the computed tomography image as the volume of interest. An open-source package PyRadiomics in Python was used to extract radiomics features from the volume of interests. The random forest and logistic regression models were used to screen feature variables, and five classification algorithms were used, including random forest, eXtreme Gradient Boosting, logistic regression, support vector machine, and k-nearest neighbors. Data on radiomic feature information, clinical information, and the combination of these pieces of information were used to generate the model that predicts the risk of transient ischemic attack in patients with mild carotid artery stenosis (30–50% North American Symptomatic Carotid Endarterectomy Trial).ResultsThe random forest model that was built based on the radiomics and clinical feature information had the highest accuracy (area under curve = 0.879; 95% confidence interval, 0.787–0.979). The combined model outperformed the clinical model, whereas the combined model showed no significant difference from the radiomics model.ConclusionThe random forest model constructed with both radiomics and clinical information can accurately predict and improve discriminative power of computed tomography angiography in identifying ischemic symptoms in patients with carotid atherosclerosis. This model can aid in guiding the follow-up treatment of patients at high risk.https://www.frontiersin.org/articles/10.3389/fneur.2023.1105616/fullCT angiographycarotid arterymachine learningprediction modeltransient ischemic attack |
| spellingShingle | Hai Xia Lei Yuan Wei Zhao Chenglei Zhang Lingfeng Zhao Jialin Hou Yancheng Luan Yuxin Bi Yaoyu Feng Predicting transient ischemic attack risk in patients with mild carotid stenosis using machine learning and CT radiomics Frontiers in Neurology CT angiography carotid artery machine learning prediction model transient ischemic attack |
| title | Predicting transient ischemic attack risk in patients with mild carotid stenosis using machine learning and CT radiomics |
| title_full | Predicting transient ischemic attack risk in patients with mild carotid stenosis using machine learning and CT radiomics |
| title_fullStr | Predicting transient ischemic attack risk in patients with mild carotid stenosis using machine learning and CT radiomics |
| title_full_unstemmed | Predicting transient ischemic attack risk in patients with mild carotid stenosis using machine learning and CT radiomics |
| title_short | Predicting transient ischemic attack risk in patients with mild carotid stenosis using machine learning and CT radiomics |
| title_sort | predicting transient ischemic attack risk in patients with mild carotid stenosis using machine learning and ct radiomics |
| topic | CT angiography carotid artery machine learning prediction model transient ischemic attack |
| url | https://www.frontiersin.org/articles/10.3389/fneur.2023.1105616/full |
| work_keys_str_mv | AT haixia predictingtransientischemicattackriskinpatientswithmildcarotidstenosisusingmachinelearningandctradiomics AT leiyuan predictingtransientischemicattackriskinpatientswithmildcarotidstenosisusingmachinelearningandctradiomics AT weizhao predictingtransientischemicattackriskinpatientswithmildcarotidstenosisusingmachinelearningandctradiomics AT chengleizhang predictingtransientischemicattackriskinpatientswithmildcarotidstenosisusingmachinelearningandctradiomics AT lingfengzhao predictingtransientischemicattackriskinpatientswithmildcarotidstenosisusingmachinelearningandctradiomics AT jialinhou predictingtransientischemicattackriskinpatientswithmildcarotidstenosisusingmachinelearningandctradiomics AT yanchengluan predictingtransientischemicattackriskinpatientswithmildcarotidstenosisusingmachinelearningandctradiomics AT yuxinbi predictingtransientischemicattackriskinpatientswithmildcarotidstenosisusingmachinelearningandctradiomics AT yaoyufeng predictingtransientischemicattackriskinpatientswithmildcarotidstenosisusingmachinelearningandctradiomics |