Axial and Reformatted Four-Chamber Right Ventricle-to-Left Ventricle Diameter Ratios on Pulmonary CT Angiography as Predictors of Death After Acute Pulmonary Embolism
ABSTRACT The purpose of this article is to retrospectively compare right ventricular-to-left ventricular (RV/LV) diameter ratios measured on the standard axial view versus the reformatted four-chamber view as predictors of mortality after acute pulmonary embolism (PE).
Six hundred seventy-four consecutive patients (mean age, 58 years; 372 women) with a diagnosis of acute PE on pulmonary CT angiography were considered. The axial and reformatted four-chamber RV/LV diameter ratios were compared as predictors of 30-day all-cause and PE-related mortality.
Ninety-seven patients (14%) died within 30 days; 39 deaths were PE related. There was no significant difference in the univariate hazard ratios (HRs) of axial and four-chamber RV/LV diameter ratios greater than 0.9 for both all-cause (HR, 2.13 [95% CI, 1.29-3.51] vs HR, 1.95 [95% CI, 1.22-3.14]; p = 0.74) and PE-related (HR, 19.6 [95% CI, 2.70-143] vs HR, 21.8 [95% CI, 2.99-158]; p = 1.0) mortality. Axial and four-chamber multivariate HRs accounting for potential confounders such as age and cancer were also similar for all-cause (HR, 1.79 [95% CI, 1.07-2.99] vs HR, 1.54 [95% CI, 0.95-2.49]; p = 0.62) and PE-related (HR, 16.3 [95% CI, 2.22-119] vs HR, 17.7 [95% CI, 2.43-130]; p = 1.0) mortality. There was no significant difference in sensitivity, specificity, negative predictive value, or positive predictive value. Axial and four-chamber measurements were well correlated (correlation coefficient, 0.857), and there was no significant difference in overall accuracy for predicting all-cause (area under the curve [AUC], 0.582 vs 0.577; p = 0.72) and PE-related (AUC, 0.743 vs 0.744; p = 1.0) mortality.
The axial RV/LV diameter ratio is no less accurate than the reformatted four-chamber RV/LV diameter ratio for predicting 30-day mortality after PE.
- SourceAvailable from: Arash Bedayat[Show abstract] [Hide abstract]
ABSTRACT: In this paper we describe an efficient tool based on natural language processing for classifying the detail state of pulmonary embolism (PE) recorded in CT pulmonary angiography reports. The classification tasks include: PE present vs. absent, acute PE vs. others, central PE vs. others, and subsegmental PE vs. others. Statistical learning algorithms were trained with features extracted using the NLP tool and gold standard labels obtained via chart review from two radiologists. The areas under the receiver operating characteristic curves (AUC) for the four tasks were 0.998, 0.945, 0.987, and 0.986, respectively. We compared our classifiers with bag-of-words Naive Bayes classifiers, a standard text mining technology, which gave AUC 0.942, 0.765, 0.766, and 0.712, respectively.Journal of Biomedical Informatics 08/2014; 52. DOI:10.1016/j.jbi.2014.08.001
- American Journal of Roentgenology 06/2012; 198(6):1313-9. DOI:10.2214/AJR.11.8461
- [Show abstract] [Hide abstract]
ABSTRACT: Enlargement and dysfunction of the right ventricle (RV) is a sign and outcome predictor of many cardiopulmonary diseases. Due to the complex geometry of the RV exact volumetry is cumbersome and time-consuming. We evaluated the performance of prototype software for fully automated RV segmentation and volumetry from cardiac CT data. In 50 retrospectively ECG-gated coronary CT angiography scans the endsystolic (RVVmin) and enddiastolic (RVVmax) volume of the right ventricle was calculated fully automatically by prototype software. Manual slice segmentation by two independent radiologists served as the reference standard. Measurement periods were compared for both methods. RV volumes calculated with the software were in strong agreement with the results from manual slice segmentation (Bland-Altman r = 0.95-0.98; p < 0.001; Lin's correlation Rho = 0.87-0.96, p < 0.001) for RVVmax and RVVmin with excellent interobserver agreement between both radiologists (r = 0.97; p < 0.001). The measurement period was significantly shorter with the software (153 ± 9 s) than with manual slice segmentation (658 ± 211 s). The prototype software demonstrated very good performance in comparison to the reference standard. It promises robust RV volume results and minimizes postprocessing time.The international journal of cardiovascular imaging 08/2012; 29(2). DOI:10.1007/s10554-012-0109-2