A machine learning approach for predicting descending thoracic aortic diameter
BackgroundTo establish models for predicting descending thoracic aortic diameters and provide evidence for selecting the size of the stent graft for TBAD patients.MethodsA total of 200 candidates without severe deformation of aorta were included. CTA information was collected and 3D reconstructed. I...
Main Authors: | , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-02-01
|
Series: | Frontiers in Cardiovascular Medicine |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fcvm.2023.1097116/full |
_version_ | 1811165277803511808 |
---|---|
author | Ronghuang Yu Min Jin Min Jin Yaohui Wang Xiujuan Cai Keyin Zhang Jian Shi Zeyi Zhou Fudong Fan Jun Pan Qing Zhou Xinlong Tang Xinlong Tang Dongjin Wang Dongjin Wang Dongjin Wang |
author_facet | Ronghuang Yu Min Jin Min Jin Yaohui Wang Xiujuan Cai Keyin Zhang Jian Shi Zeyi Zhou Fudong Fan Jun Pan Qing Zhou Xinlong Tang Xinlong Tang Dongjin Wang Dongjin Wang Dongjin Wang |
author_sort | Ronghuang Yu |
collection | DOAJ |
description | BackgroundTo establish models for predicting descending thoracic aortic diameters and provide evidence for selecting the size of the stent graft for TBAD patients.MethodsA total of 200 candidates without severe deformation of aorta were included. CTA information was collected and 3D reconstructed. In the reconstructed CTA, a total of 12 cross-sections of peripheral vessels were made perpendicular to the axis of flow of the aorta. Parameters of the cross sections and basic clinical characteristics were used for prediction. The data was randomly split into the training set and the test set in an 8:2 ratio. To fully describe diameters of descending thoracic aorta, three predicted points were set based quadrisection, and a total of 12 models at three predicted points were established using four algorithms included linear regression (LR), support vector machine (SVM), Extra-Tree regression (ETR) and random forest regression (RFR). The performance of models was evaluated by mean square error (MSE) of the prediction value, and the ranking of feature importance was given by Shapley value. After modeling, prognosis of five TEVAR cases and stent oversizing were compared.ResultsWe identified a series of parameters which affect the diameter of descending thoracic aorta, including age, hypertension, the area of proximal edge of superior mesenteric artery, etc. Among four predictive models, all the MSEs of SVM models at three different predicted position were less than 2 mm2, with approximately 90% predicted diameters error less than 2 mm in the test sets. In patients with dSINE, stent oversizing was about 3 mm, while only 1 mm in patients without complications.ConclusionThe predictive models established by machine learning revealed the relationship between basic characteristics and diameters of different segment of descending aorta, which help to provide evidence for selecting the matching distal size of the stent for TBAD patients, thereby reducing the incidence of TEVAR complications. |
first_indexed | 2024-04-10T15:34:38Z |
format | Article |
id | doaj.art-91470194066246ee940016179d9f1c65 |
institution | Directory Open Access Journal |
issn | 2297-055X |
language | English |
last_indexed | 2024-04-10T15:34:38Z |
publishDate | 2023-02-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Cardiovascular Medicine |
spelling | doaj.art-91470194066246ee940016179d9f1c652023-02-13T07:59:46ZengFrontiers Media S.A.Frontiers in Cardiovascular Medicine2297-055X2023-02-011010.3389/fcvm.2023.10971161097116A machine learning approach for predicting descending thoracic aortic diameterRonghuang Yu0Min Jin1Min Jin2Yaohui Wang3Xiujuan Cai4Keyin Zhang5Jian Shi6Zeyi Zhou7Fudong Fan8Jun Pan9Qing Zhou10Xinlong Tang11Xinlong Tang12Dongjin Wang13Dongjin Wang14Dongjin Wang15Medical School, Department of Cardio-Thoracic Surgery, Affiliated Drum Tower Hospital, Nanjing University, Nanjing, ChinaMedical School, Department of Cardio-Thoracic Surgery, Affiliated Drum Tower Hospital, Nanjing University, Nanjing, ChinaNanjing Drum Tower Hospital, Clinical College of Nanjing Medical University, Nanjing, ChinaShanghai Artificial Intelligence Laboratory, Shanghai, ChinaNanjing Drum Tower Hospital, Clinical College of Nanjing University of Chinese Medicine, Nanjing, ChinaMedical School, Department of Cardio-Thoracic Surgery, Affiliated Drum Tower Hospital, Nanjing University, Nanjing, ChinaMedical School, Department of Cardio-Thoracic Surgery, Affiliated Drum Tower Hospital, Nanjing University, Nanjing, ChinaMedical School, Department of Cardio-Thoracic Surgery, Affiliated Drum Tower Hospital, Nanjing University, Nanjing, ChinaMedical School, Department of Cardio-Thoracic Surgery, Affiliated Drum Tower Hospital, Nanjing University, Nanjing, ChinaMedical School, Department of Cardio-Thoracic Surgery, Affiliated Drum Tower Hospital, Nanjing University, Nanjing, ChinaMedical School, Department of Cardio-Thoracic Surgery, Affiliated Drum Tower Hospital, Nanjing University, Nanjing, ChinaMedical School, Department of Cardio-Thoracic Surgery, Affiliated Drum Tower Hospital, Nanjing University, Nanjing, ChinaNanjing Drum Tower Hospital, Clinical College of Nanjing Medical University, Nanjing, ChinaMedical School, Department of Cardio-Thoracic Surgery, Affiliated Drum Tower Hospital, Nanjing University, Nanjing, ChinaNanjing Drum Tower Hospital, Clinical College of Nanjing Medical University, Nanjing, ChinaNanjing Drum Tower Hospital, Clinical College of Nanjing University of Chinese Medicine, Nanjing, ChinaBackgroundTo establish models for predicting descending thoracic aortic diameters and provide evidence for selecting the size of the stent graft for TBAD patients.MethodsA total of 200 candidates without severe deformation of aorta were included. CTA information was collected and 3D reconstructed. In the reconstructed CTA, a total of 12 cross-sections of peripheral vessels were made perpendicular to the axis of flow of the aorta. Parameters of the cross sections and basic clinical characteristics were used for prediction. The data was randomly split into the training set and the test set in an 8:2 ratio. To fully describe diameters of descending thoracic aorta, three predicted points were set based quadrisection, and a total of 12 models at three predicted points were established using four algorithms included linear regression (LR), support vector machine (SVM), Extra-Tree regression (ETR) and random forest regression (RFR). The performance of models was evaluated by mean square error (MSE) of the prediction value, and the ranking of feature importance was given by Shapley value. After modeling, prognosis of five TEVAR cases and stent oversizing were compared.ResultsWe identified a series of parameters which affect the diameter of descending thoracic aorta, including age, hypertension, the area of proximal edge of superior mesenteric artery, etc. Among four predictive models, all the MSEs of SVM models at three different predicted position were less than 2 mm2, with approximately 90% predicted diameters error less than 2 mm in the test sets. In patients with dSINE, stent oversizing was about 3 mm, while only 1 mm in patients without complications.ConclusionThe predictive models established by machine learning revealed the relationship between basic characteristics and diameters of different segment of descending aorta, which help to provide evidence for selecting the matching distal size of the stent for TBAD patients, thereby reducing the incidence of TEVAR complications.https://www.frontiersin.org/articles/10.3389/fcvm.2023.1097116/fullmachine learningaortic diameterTEVARCTApredictive model |
spellingShingle | Ronghuang Yu Min Jin Min Jin Yaohui Wang Xiujuan Cai Keyin Zhang Jian Shi Zeyi Zhou Fudong Fan Jun Pan Qing Zhou Xinlong Tang Xinlong Tang Dongjin Wang Dongjin Wang Dongjin Wang A machine learning approach for predicting descending thoracic aortic diameter Frontiers in Cardiovascular Medicine machine learning aortic diameter TEVAR CTA predictive model |
title | A machine learning approach for predicting descending thoracic aortic diameter |
title_full | A machine learning approach for predicting descending thoracic aortic diameter |
title_fullStr | A machine learning approach for predicting descending thoracic aortic diameter |
title_full_unstemmed | A machine learning approach for predicting descending thoracic aortic diameter |
title_short | A machine learning approach for predicting descending thoracic aortic diameter |
title_sort | machine learning approach for predicting descending thoracic aortic diameter |
topic | machine learning aortic diameter TEVAR CTA predictive model |
url | https://www.frontiersin.org/articles/10.3389/fcvm.2023.1097116/full |
work_keys_str_mv | AT ronghuangyu amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT minjin amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT minjin amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT yaohuiwang amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT xiujuancai amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT keyinzhang amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT jianshi amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT zeyizhou amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT fudongfan amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT junpan amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT qingzhou amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT xinlongtang amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT xinlongtang amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT dongjinwang amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT dongjinwang amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT dongjinwang amachinelearningapproachforpredictingdescendingthoracicaorticdiameter AT ronghuangyu machinelearningapproachforpredictingdescendingthoracicaorticdiameter AT minjin machinelearningapproachforpredictingdescendingthoracicaorticdiameter AT minjin machinelearningapproachforpredictingdescendingthoracicaorticdiameter AT yaohuiwang machinelearningapproachforpredictingdescendingthoracicaorticdiameter AT xiujuancai machinelearningapproachforpredictingdescendingthoracicaorticdiameter AT keyinzhang machinelearningapproachforpredictingdescendingthoracicaorticdiameter AT jianshi machinelearningapproachforpredictingdescendingthoracicaorticdiameter AT zeyizhou machinelearningapproachforpredictingdescendingthoracicaorticdiameter AT fudongfan machinelearningapproachforpredictingdescendingthoracicaorticdiameter AT junpan machinelearningapproachforpredictingdescendingthoracicaorticdiameter AT qingzhou machinelearningapproachforpredictingdescendingthoracicaorticdiameter AT xinlongtang machinelearningapproachforpredictingdescendingthoracicaorticdiameter AT xinlongtang machinelearningapproachforpredictingdescendingthoracicaorticdiameter AT dongjinwang machinelearningapproachforpredictingdescendingthoracicaorticdiameter AT dongjinwang machinelearningapproachforpredictingdescendingthoracicaorticdiameter AT dongjinwang machinelearningapproachforpredictingdescendingthoracicaorticdiameter |