Development and validation of diagnostic prediction model for solitary pulmonary nodules

Kan Yonemori, Ukihide Tateishi, Hajime Uno, Yoko Yonemori, Koji Tsuta, Masahiro Takeuchi, Yoshihiro Matsuno, Yasuhiro Fujiwara, Hisao Asamura, Masahiko Kusumoto

Research output: Contribution to journalArticle

32 Citations (Scopus)

Abstract

Background and objective: The aim of this study was to develop a simple prediction model for the underlying diagnosis of solitary pulmonary nodules (SPN) based on clinical characteristics and thin-section CT findings. Methods: Retrospective analysis was carried out on 452 patients with SPN (113 benign and 339 malignant) smaller than 30 mm, who underwent thin-section CT followed by surgical resection and histological diagnosis. The clinical characteristics were collected from medical records, and radiographic characteristics from thin-section CT findings. The prediction model was determined using multivariate logistic analysis. The prediction model was validated in 148 consecutive patients with undiagnosed SPN, and the diagnostic accuracy of the model was compared with that of an experienced chest radiologist. Results: The prediction model comprised the level of serum CRP, the level of carcinoembryonic antigen, the presence or absence of calcification, spiculation and CT bronchus sign. The areas under the receiver-operating characteristic curve in training and validation sets were 0.966 and 0.840, respectively. The diagnostic accuracies of the prediction model and the experienced chest radiologist for the validation set were 0.858 and 0.905, respectively. Conclusion: The simple prediction model consisted of two biochemical and three radiographic characteristics. The diagnostic accuracy of an experienced chest radiologist was higher compared with the prediction model.

Original languageEnglish
Pages (from-to)856-862
Number of pages7
JournalRespirology
Volume12
Issue number6
DOIs
Publication statusPublished - 2007 Nov
Externally publishedYes

Fingerprint

Solitary Pulmonary Nodule
Thorax
Carcinoembryonic Antigen
Bronchi
ROC Curve
Medical Records
Multivariate Analysis
Serum
Radiologists

Keywords

  • Benign
  • CT
  • Malignant
  • Prediction model
  • Solitary pulmonary nodule

ASJC Scopus subject areas

  • Pulmonary and Respiratory Medicine

Cite this

Yonemori, K., Tateishi, U., Uno, H., Yonemori, Y., Tsuta, K., Takeuchi, M., ... Kusumoto, M. (2007). Development and validation of diagnostic prediction model for solitary pulmonary nodules. Respirology, 12(6), 856-862. https://doi.org/10.1111/j.1440-1843.2007.01158.x

Development and validation of diagnostic prediction model for solitary pulmonary nodules. / Yonemori, Kan; Tateishi, Ukihide; Uno, Hajime; Yonemori, Yoko; Tsuta, Koji; Takeuchi, Masahiro; Matsuno, Yoshihiro; Fujiwara, Yasuhiro; Asamura, Hisao; Kusumoto, Masahiko.

In: Respirology, Vol. 12, No. 6, 11.2007, p. 856-862.

Research output: Contribution to journalArticle

Yonemori, K, Tateishi, U, Uno, H, Yonemori, Y, Tsuta, K, Takeuchi, M, Matsuno, Y, Fujiwara, Y, Asamura, H & Kusumoto, M 2007, 'Development and validation of diagnostic prediction model for solitary pulmonary nodules', Respirology, vol. 12, no. 6, pp. 856-862. https://doi.org/10.1111/j.1440-1843.2007.01158.x
Yonemori K, Tateishi U, Uno H, Yonemori Y, Tsuta K, Takeuchi M et al. Development and validation of diagnostic prediction model for solitary pulmonary nodules. Respirology. 2007 Nov;12(6):856-862. https://doi.org/10.1111/j.1440-1843.2007.01158.x
Yonemori, Kan ; Tateishi, Ukihide ; Uno, Hajime ; Yonemori, Yoko ; Tsuta, Koji ; Takeuchi, Masahiro ; Matsuno, Yoshihiro ; Fujiwara, Yasuhiro ; Asamura, Hisao ; Kusumoto, Masahiko. / Development and validation of diagnostic prediction model for solitary pulmonary nodules. In: Respirology. 2007 ; Vol. 12, No. 6. pp. 856-862.
@article{d3cac2ca823e4d60bbb4a4195a91a433,
title = "Development and validation of diagnostic prediction model for solitary pulmonary nodules",
abstract = "Background and objective: The aim of this study was to develop a simple prediction model for the underlying diagnosis of solitary pulmonary nodules (SPN) based on clinical characteristics and thin-section CT findings. Methods: Retrospective analysis was carried out on 452 patients with SPN (113 benign and 339 malignant) smaller than 30 mm, who underwent thin-section CT followed by surgical resection and histological diagnosis. The clinical characteristics were collected from medical records, and radiographic characteristics from thin-section CT findings. The prediction model was determined using multivariate logistic analysis. The prediction model was validated in 148 consecutive patients with undiagnosed SPN, and the diagnostic accuracy of the model was compared with that of an experienced chest radiologist. Results: The prediction model comprised the level of serum CRP, the level of carcinoembryonic antigen, the presence or absence of calcification, spiculation and CT bronchus sign. The areas under the receiver-operating characteristic curve in training and validation sets were 0.966 and 0.840, respectively. The diagnostic accuracies of the prediction model and the experienced chest radiologist for the validation set were 0.858 and 0.905, respectively. Conclusion: The simple prediction model consisted of two biochemical and three radiographic characteristics. The diagnostic accuracy of an experienced chest radiologist was higher compared with the prediction model.",
keywords = "Benign, CT, Malignant, Prediction model, Solitary pulmonary nodule",
author = "Kan Yonemori and Ukihide Tateishi and Hajime Uno and Yoko Yonemori and Koji Tsuta and Masahiro Takeuchi and Yoshihiro Matsuno and Yasuhiro Fujiwara and Hisao Asamura and Masahiko Kusumoto",
year = "2007",
month = "11",
doi = "10.1111/j.1440-1843.2007.01158.x",
language = "English",
volume = "12",
pages = "856--862",
journal = "Respirology",
issn = "1323-7799",
publisher = "Wiley-Blackwell",
number = "6",

}

TY - JOUR

T1 - Development and validation of diagnostic prediction model for solitary pulmonary nodules

AU - Yonemori, Kan

AU - Tateishi, Ukihide

AU - Uno, Hajime

AU - Yonemori, Yoko

AU - Tsuta, Koji

AU - Takeuchi, Masahiro

AU - Matsuno, Yoshihiro

AU - Fujiwara, Yasuhiro

AU - Asamura, Hisao

AU - Kusumoto, Masahiko

PY - 2007/11

Y1 - 2007/11

N2 - Background and objective: The aim of this study was to develop a simple prediction model for the underlying diagnosis of solitary pulmonary nodules (SPN) based on clinical characteristics and thin-section CT findings. Methods: Retrospective analysis was carried out on 452 patients with SPN (113 benign and 339 malignant) smaller than 30 mm, who underwent thin-section CT followed by surgical resection and histological diagnosis. The clinical characteristics were collected from medical records, and radiographic characteristics from thin-section CT findings. The prediction model was determined using multivariate logistic analysis. The prediction model was validated in 148 consecutive patients with undiagnosed SPN, and the diagnostic accuracy of the model was compared with that of an experienced chest radiologist. Results: The prediction model comprised the level of serum CRP, the level of carcinoembryonic antigen, the presence or absence of calcification, spiculation and CT bronchus sign. The areas under the receiver-operating characteristic curve in training and validation sets were 0.966 and 0.840, respectively. The diagnostic accuracies of the prediction model and the experienced chest radiologist for the validation set were 0.858 and 0.905, respectively. Conclusion: The simple prediction model consisted of two biochemical and three radiographic characteristics. The diagnostic accuracy of an experienced chest radiologist was higher compared with the prediction model.

AB - Background and objective: The aim of this study was to develop a simple prediction model for the underlying diagnosis of solitary pulmonary nodules (SPN) based on clinical characteristics and thin-section CT findings. Methods: Retrospective analysis was carried out on 452 patients with SPN (113 benign and 339 malignant) smaller than 30 mm, who underwent thin-section CT followed by surgical resection and histological diagnosis. The clinical characteristics were collected from medical records, and radiographic characteristics from thin-section CT findings. The prediction model was determined using multivariate logistic analysis. The prediction model was validated in 148 consecutive patients with undiagnosed SPN, and the diagnostic accuracy of the model was compared with that of an experienced chest radiologist. Results: The prediction model comprised the level of serum CRP, the level of carcinoembryonic antigen, the presence or absence of calcification, spiculation and CT bronchus sign. The areas under the receiver-operating characteristic curve in training and validation sets were 0.966 and 0.840, respectively. The diagnostic accuracies of the prediction model and the experienced chest radiologist for the validation set were 0.858 and 0.905, respectively. Conclusion: The simple prediction model consisted of two biochemical and three radiographic characteristics. The diagnostic accuracy of an experienced chest radiologist was higher compared with the prediction model.

KW - Benign

KW - CT

KW - Malignant

KW - Prediction model

KW - Solitary pulmonary nodule

UR - http://www.scopus.com/inward/record.url?scp=35748954022&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35748954022&partnerID=8YFLogxK

U2 - 10.1111/j.1440-1843.2007.01158.x

DO - 10.1111/j.1440-1843.2007.01158.x

M3 - Article

VL - 12

SP - 856

EP - 862

JO - Respirology

JF - Respirology

SN - 1323-7799

IS - 6

ER -