Advanced

Prospective Internal Validation of Mathematical Models to Predict Malignancy in Adnexal Masses: Results from the International Ovarian Tumor Analysis Study

Van Holsbeke, Caroline; Van Calster, Ben; Testa, Antonia C.; Domali, Ekaterini; Lu, Chuan; Van Huffel, Sabine; Valentin, Lil LU and Timmerman, Dirk (2009) In Clinical Cancer Research 15(2). p.684-691
Abstract
Purpose: To prospectively test the mathematical models for calculation of the risk of malignancy in adnexal masses that were developed on the International Ovarian Tumor Analysis (IOTA) phase 1 data set on a new data set and to compare their performance with that of pattern recognition, our standard method. Methods: Three IOTA centers included 507 new patients who all underwent a transvaginal ultrasound using the standardized IOTA protocol. The outcome measure was the histologic classification of excised tissue. The diagnostic performance of 11 mathematical models that had been developed on the phase 1 data set and of pattern recognition was expressed as area under the receiver operating characteristic curve (AUC) and as sensitivity and... (More)
Purpose: To prospectively test the mathematical models for calculation of the risk of malignancy in adnexal masses that were developed on the International Ovarian Tumor Analysis (IOTA) phase 1 data set on a new data set and to compare their performance with that of pattern recognition, our standard method. Methods: Three IOTA centers included 507 new patients who all underwent a transvaginal ultrasound using the standardized IOTA protocol. The outcome measure was the histologic classification of excised tissue. The diagnostic performance of 11 mathematical models that had been developed on the phase 1 data set and of pattern recognition was expressed as area under the receiver operating characteristic curve (AUC) and as sensitivity and specificity when using the cutoffs recommended in the studies where the models had been created. For pattern recognition, an AUC was made based on level of diagnostic confidence, Results: All IOTA models performed very well and quite similarly, with sensitivity and specificity ranging between 92% and 96% and 74% and 84%, respectively, and AUCs between 0.945 and 0.950. A least squares support vector machine with linear kernel and a logistic regression model had the largest AUCs. For pattern recognition, the AUC was 0.963, sensitivity was 90.2%, and specificity was 92.9%. Conclusion: This internal validation of mathematical models to estimate the malignancy risk in adnexal tumors shows that the IOTA models had a diagnostic performance similar to that in the original data set. Pattern recognition used by an expert sonologist remains the best method, although the difference in performance between the best mathematical model is not large. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Clinical Cancer Research
volume
15
issue
2
pages
684 - 691
publisher
American Association for Cancer Research
external identifiers
  • wos:000262689300032
  • scopus:59449107079
ISSN
1078-0432
DOI
10.1158/1078-0432.CCR-08-0113
language
English
LU publication?
yes
id
d288e581-0b79-4002-a772-7a5bab300892 (old id 1312278)
date added to LUP
2009-03-18 08:53:21
date last changed
2017-11-19 03:37:24
@article{d288e581-0b79-4002-a772-7a5bab300892,
  abstract     = {Purpose: To prospectively test the mathematical models for calculation of the risk of malignancy in adnexal masses that were developed on the International Ovarian Tumor Analysis (IOTA) phase 1 data set on a new data set and to compare their performance with that of pattern recognition, our standard method. Methods: Three IOTA centers included 507 new patients who all underwent a transvaginal ultrasound using the standardized IOTA protocol. The outcome measure was the histologic classification of excised tissue. The diagnostic performance of 11 mathematical models that had been developed on the phase 1 data set and of pattern recognition was expressed as area under the receiver operating characteristic curve (AUC) and as sensitivity and specificity when using the cutoffs recommended in the studies where the models had been created. For pattern recognition, an AUC was made based on level of diagnostic confidence, Results: All IOTA models performed very well and quite similarly, with sensitivity and specificity ranging between 92% and 96% and 74% and 84%, respectively, and AUCs between 0.945 and 0.950. A least squares support vector machine with linear kernel and a logistic regression model had the largest AUCs. For pattern recognition, the AUC was 0.963, sensitivity was 90.2%, and specificity was 92.9%. Conclusion: This internal validation of mathematical models to estimate the malignancy risk in adnexal tumors shows that the IOTA models had a diagnostic performance similar to that in the original data set. Pattern recognition used by an expert sonologist remains the best method, although the difference in performance between the best mathematical model is not large.},
  author       = {Van Holsbeke, Caroline and Van Calster, Ben and Testa, Antonia C. and Domali, Ekaterini and Lu, Chuan and Van Huffel, Sabine and Valentin, Lil and Timmerman, Dirk},
  issn         = {1078-0432},
  language     = {eng},
  number       = {2},
  pages        = {684--691},
  publisher    = {American Association for Cancer Research},
  series       = {Clinical Cancer Research},
  title        = {Prospective Internal Validation of Mathematical Models to Predict Malignancy in Adnexal Masses: Results from the International Ovarian Tumor Analysis Study},
  url          = {http://dx.doi.org/10.1158/1078-0432.CCR-08-0113},
  volume       = {15},
  year         = {2009},
}