Assessment of the relationship between native thoracic aortic curvature and endoleak formation after TEVAR based on linear discriminant analysis

Kuniyoshi Hayashi, Fumio Ishioka, Bhargav Raman, Daniel Y. Sze, Hiroshi Suito, Takuya Ueda, Koji Kurihara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In the field of surgery treatment, thoracic endovascular aortic repair has recently gained popularity, but this treatment often causes an adverse clinical side effect called endoleak. The risk prediction of endoleak is essential for preoperative planning (Nakatamari et al., J Vasc Interv Radiol 22(7):974–979, 2011). In this study, we focus on a quantitative curvature in the morphology of a patient’s aorta, and predict the risk of endoleak formation through linear discriminant analysis. Here, we objectively evaluate the relationship between the side effect after stent-graft treatment for thoracic aneurysm and a patient’s native thoracic aortic curvature. In addition, based on the sample influence function for the average of discriminant scores in linear discriminant analysis, we also perform statistical diagnostics on the result of the analysis. We detected the influential training samples to be deleted to realize improved prediction accuracy, and made subsets of all of their possible combinations. Furthermore, by considering the minimum misclassification rate based on leave-one-out cross-validation in Hastie et al. (The elements of statistical learning. Springer, New York, 2001, pp. 214–216) and the minimum number of training samples to be deleted, we deduced the subset to be excluded from training data when we develop the target classifier. From this study, we detected an important part of the native thoracic aorta in terms of risk prediction of endoleak occurrence, and identified influential patients for the result of the discrimination.

Original languageEnglish
Title of host publicationStudies in Classification, Data Analysis, and Knowledge Organization
PublisherKluwer Academic Publishers
Pages179-192
Number of pages14
Volume46
ISBN (Print)9783319012636
DOIs
Publication statusPublished - 2014
EventInternational Federation of Classification Societies, IFCS 2013 - Tilburg, Netherlands
Duration: Jul 14 2013Jul 17 2013

Other

OtherInternational Federation of Classification Societies, IFCS 2013
CountryNetherlands
CityTilburg
Period7/14/137/17/13

Fingerprint

Discriminant analysis
Discriminant Analysis
Aorta
Curvature
Training Samples
Prediction
Misclassification Rate
Stent
Aneurysm
Statistical Learning
Influence Function
Stents
Subset
Set theory
Discriminant
Cross-validation
Grafts
Surgery
Discrimination
Repair

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Information Systems and Management
  • Analysis

Cite this

Hayashi, K., Ishioka, F., Raman, B., Sze, D. Y., Suito, H., Ueda, T., & Kurihara, K. (2014). Assessment of the relationship between native thoracic aortic curvature and endoleak formation after TEVAR based on linear discriminant analysis. In Studies in Classification, Data Analysis, and Knowledge Organization (Vol. 46, pp. 179-192). Kluwer Academic Publishers. https://doi.org/10.1007/978-3-319-01264-3_16

Assessment of the relationship between native thoracic aortic curvature and endoleak formation after TEVAR based on linear discriminant analysis. / Hayashi, Kuniyoshi; Ishioka, Fumio; Raman, Bhargav; Sze, Daniel Y.; Suito, Hiroshi; Ueda, Takuya; Kurihara, Koji.

Studies in Classification, Data Analysis, and Knowledge Organization. Vol. 46 Kluwer Academic Publishers, 2014. p. 179-192.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hayashi, K, Ishioka, F, Raman, B, Sze, DY, Suito, H, Ueda, T & Kurihara, K 2014, Assessment of the relationship between native thoracic aortic curvature and endoleak formation after TEVAR based on linear discriminant analysis. in Studies in Classification, Data Analysis, and Knowledge Organization. vol. 46, Kluwer Academic Publishers, pp. 179-192, International Federation of Classification Societies, IFCS 2013, Tilburg, Netherlands, 7/14/13. https://doi.org/10.1007/978-3-319-01264-3_16
Hayashi K, Ishioka F, Raman B, Sze DY, Suito H, Ueda T et al. Assessment of the relationship between native thoracic aortic curvature and endoleak formation after TEVAR based on linear discriminant analysis. In Studies in Classification, Data Analysis, and Knowledge Organization. Vol. 46. Kluwer Academic Publishers. 2014. p. 179-192 https://doi.org/10.1007/978-3-319-01264-3_16
Hayashi, Kuniyoshi ; Ishioka, Fumio ; Raman, Bhargav ; Sze, Daniel Y. ; Suito, Hiroshi ; Ueda, Takuya ; Kurihara, Koji. / Assessment of the relationship between native thoracic aortic curvature and endoleak formation after TEVAR based on linear discriminant analysis. Studies in Classification, Data Analysis, and Knowledge Organization. Vol. 46 Kluwer Academic Publishers, 2014. pp. 179-192
@inproceedings{6128b2ba85c54c17a47f3b66a6762bae,
title = "Assessment of the relationship between native thoracic aortic curvature and endoleak formation after TEVAR based on linear discriminant analysis",
abstract = "In the field of surgery treatment, thoracic endovascular aortic repair has recently gained popularity, but this treatment often causes an adverse clinical side effect called endoleak. The risk prediction of endoleak is essential for preoperative planning (Nakatamari et al., J Vasc Interv Radiol 22(7):974–979, 2011). In this study, we focus on a quantitative curvature in the morphology of a patient’s aorta, and predict the risk of endoleak formation through linear discriminant analysis. Here, we objectively evaluate the relationship between the side effect after stent-graft treatment for thoracic aneurysm and a patient’s native thoracic aortic curvature. In addition, based on the sample influence function for the average of discriminant scores in linear discriminant analysis, we also perform statistical diagnostics on the result of the analysis. We detected the influential training samples to be deleted to realize improved prediction accuracy, and made subsets of all of their possible combinations. Furthermore, by considering the minimum misclassification rate based on leave-one-out cross-validation in Hastie et al. (The elements of statistical learning. Springer, New York, 2001, pp. 214–216) and the minimum number of training samples to be deleted, we deduced the subset to be excluded from training data when we develop the target classifier. From this study, we detected an important part of the native thoracic aorta in terms of risk prediction of endoleak occurrence, and identified influential patients for the result of the discrimination.",
author = "Kuniyoshi Hayashi and Fumio Ishioka and Bhargav Raman and Sze, {Daniel Y.} and Hiroshi Suito and Takuya Ueda and Koji Kurihara",
year = "2014",
doi = "10.1007/978-3-319-01264-3_16",
language = "English",
isbn = "9783319012636",
volume = "46",
pages = "179--192",
booktitle = "Studies in Classification, Data Analysis, and Knowledge Organization",
publisher = "Kluwer Academic Publishers",

}

TY - GEN

T1 - Assessment of the relationship between native thoracic aortic curvature and endoleak formation after TEVAR based on linear discriminant analysis

AU - Hayashi, Kuniyoshi

AU - Ishioka, Fumio

AU - Raman, Bhargav

AU - Sze, Daniel Y.

AU - Suito, Hiroshi

AU - Ueda, Takuya

AU - Kurihara, Koji

PY - 2014

Y1 - 2014

N2 - In the field of surgery treatment, thoracic endovascular aortic repair has recently gained popularity, but this treatment often causes an adverse clinical side effect called endoleak. The risk prediction of endoleak is essential for preoperative planning (Nakatamari et al., J Vasc Interv Radiol 22(7):974–979, 2011). In this study, we focus on a quantitative curvature in the morphology of a patient’s aorta, and predict the risk of endoleak formation through linear discriminant analysis. Here, we objectively evaluate the relationship between the side effect after stent-graft treatment for thoracic aneurysm and a patient’s native thoracic aortic curvature. In addition, based on the sample influence function for the average of discriminant scores in linear discriminant analysis, we also perform statistical diagnostics on the result of the analysis. We detected the influential training samples to be deleted to realize improved prediction accuracy, and made subsets of all of their possible combinations. Furthermore, by considering the minimum misclassification rate based on leave-one-out cross-validation in Hastie et al. (The elements of statistical learning. Springer, New York, 2001, pp. 214–216) and the minimum number of training samples to be deleted, we deduced the subset to be excluded from training data when we develop the target classifier. From this study, we detected an important part of the native thoracic aorta in terms of risk prediction of endoleak occurrence, and identified influential patients for the result of the discrimination.

AB - In the field of surgery treatment, thoracic endovascular aortic repair has recently gained popularity, but this treatment often causes an adverse clinical side effect called endoleak. The risk prediction of endoleak is essential for preoperative planning (Nakatamari et al., J Vasc Interv Radiol 22(7):974–979, 2011). In this study, we focus on a quantitative curvature in the morphology of a patient’s aorta, and predict the risk of endoleak formation through linear discriminant analysis. Here, we objectively evaluate the relationship between the side effect after stent-graft treatment for thoracic aneurysm and a patient’s native thoracic aortic curvature. In addition, based on the sample influence function for the average of discriminant scores in linear discriminant analysis, we also perform statistical diagnostics on the result of the analysis. We detected the influential training samples to be deleted to realize improved prediction accuracy, and made subsets of all of their possible combinations. Furthermore, by considering the minimum misclassification rate based on leave-one-out cross-validation in Hastie et al. (The elements of statistical learning. Springer, New York, 2001, pp. 214–216) and the minimum number of training samples to be deleted, we deduced the subset to be excluded from training data when we develop the target classifier. From this study, we detected an important part of the native thoracic aorta in terms of risk prediction of endoleak occurrence, and identified influential patients for the result of the discrimination.

UR - http://www.scopus.com/inward/record.url?scp=84951839013&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84951839013&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-01264-3_16

DO - 10.1007/978-3-319-01264-3_16

M3 - Conference contribution

SN - 9783319012636

VL - 46

SP - 179

EP - 192

BT - Studies in Classification, Data Analysis, and Knowledge Organization

PB - Kluwer Academic Publishers

ER -