Sonoangiography and logistic regression analysis in the preoperative differentiation of ovarian tumors
Smoleń, A.; Czekierdowski, A.; Daniłoś, J.ła.; Kraczkowski, J.
Ginekologia Polska 73(11): 1053-1060
2002
ISSN/ISBN: 0017-0011 PMID: 12722399 Document Number: 542771
To apply logistic regression analysis for several clinical and sonographic data for the construction of a predictive model that could be helpful in the preoperative differentiation of adnexal masses. Two hundred and eight women with tumors thought to be of adnexal origin were examined preoperatively. Initial analysis included age and menopausal status, ultrasound derived morphological features of adnexal masses (unilateral/bilateral tumors, papillae, septae, tumor size and volume) as well as color Doppler criteria such as PI, RI, Peak Systolic Velocity, PSV assessment. In all examinations we used B&K 2002 ADI (Denmark) and Kretz Voluson V730 (Austria) scanners with transvaginal probes 5-9 MHz. Stepwise logistic regression analysis was used to construct a predictive model that would allow probability of malignancy calculation for individual patient. There were 159 benign and 49 malignant masses. Seven cancers were in FIGO stage one. Statistical analysis revealed that only 5 of initially tested 14 variables had significant influence on the regression equation. These were: age, bilateral mass, presence of septa > 3 mm, papillary projections > 3 mm in the tumor wall and subjective color scale assessment according to Timmerman et al. (1999). Sensitivity and specificity at the 50% probability level of malignancy in the studied tumor were 77.5% and 96.8%, respectively. When 25% cut-off probability level was used, sensitivity increased to 87.7% and specificity dropped to 89.9%. Prospective testing in a new group of 30 patients (5 ovarian cancers) gave sensitivity of 80% and specificity of 100%. The use of logistic regression analysis can help in modeling clinical and sonographic data. Our model had better predictive value than individual tests and allowed to calculate true probability figure of ovarian malignancy for any given patient with adnexal mass.