ABSTRACT
Background: Radiomics has shown promise in improving malignancy risk stratification of indeterminate pulmonary nodules (IPNs) with many platforms available, but with no head-to-head comparisons. This study aimed to evaluate transportability of radiomic models across platforms by comparing performances of a commercial radiomic feature extractor (HealthMyne) with an open-source extractor (PyRadiomics) on diagnosis of lung cancer in IPNs. Methods: A commercial radiomic feature extractor was used to segment IPNs from computed tomography (CT) scans, and a previously validated radiomic model based on commercial features was used as baseline (ComRad). Using same segmentation masks, PyRadiomics, an open-source feature extractor was used to build three open-source radiomic models (OpenRad) using different methods: de novo open-source model derived using least absolute shrinkage and selection operator (LASSO) for feature selection, selecting open-source features matched to ComRad features based upon Imaging Biomarker Standardization Initiative (IBSI) nomenclature, and selecting open-source features most highly correlated to ComRad features. Radiomic models were trained on an internal cohort (n=161) and externally validated on 3 cohorts (n=278). We added Mayo clinical risk score to OpenRad and ComRad models, creating integrated clinical radiomic (ClinRad) models. All models were compared using area under the curve (AUC) and evaluated for clinical improvement using bias-corrected clinical net reclassification indices (cNRIs). Results: ComRad AUC was 0.76 [95% confidence interval (CI): 0.71-0.82], and OpenRad AUC was 0.75 (95% CI: 0.69-0.81) for LASSO model, 0.74 (95% CI: 0.68-0.79) for Spearman's correlation, and 0.71 (95% CI: 0.65-0.77) for IBSI. Mayo scores were added to OpenRad LASSO model, which performed best, forming open-source ClinRad model with AUC of 0.80 (95% CI: 0.74-0.86), identical to commercial ClinRad's AUC. Both ClinRad models showed clinical improvement compared to Mayo alone, with commercial ClinRad achieving cNRI of 0.09 (95% CI: 0.02-0.15) for benign and 0.07 (95% CI: 0.00-0.13) for malignant, and open-source ClinRad achieving cNRI of 0.09 (95% CI: 0.02-0.15) for benign and 0.06 (95% CI: 0.00-0.12) for malignant. Conclusions: Transportability of radiomic models across platforms directly does not conserve performance, but radiomic platforms can provide equivalent results when building de novo models allowing for flexibility in feature selection to maximize prediction accuracy.
ABSTRACT
OBJECTIVE: There is a paucity of data on outcomes after isolated tricuspid valve surgery. This meta-analysis aims to compile available data on isolated tricuspid valve surgery and compare isolated tricuspid valve repair (iTVr) with isolated tricuspid valve replacement (iTVR) to elucidate outcomes after tricuspid valve surgery. METHODS: A literature search of 6 databases was performed. The primary outcomes was 30-day mortality. Secondary outcomes were early stroke, post-op pacemaker placement, and tricuspid reoperation within 5 years. Publication bias was explored using the funnel plot. RESULTS: Ten retrospective studies involving 1407 patients (iTVr group = 779 patients and iTVR group = 628 patients) were included. A cumulative analysis demonstrated a significant difference favoring iTVr for 30-day mortality (odds ratio [OR]: 10 studies [95% confidence interval [CI]]: 0.34 [0.18-0.66]); 4.7% versus 12.6%, for iTVr and iTVR, respectively. Post-op pacemaker placement favored iTVr (OR: 6 studies [95% CI]: 0.37 [0.18-0.77]). Although stroke rates and TV reoperation favored iTVr, they did not reach statistical significance. No publication bias was identified. CONCLUSIONS: This meta-analysis demonstrates that iTVr has better 30-day mortality and fewer permanent pacemaker placements. Etiology and severity of TR, as well as careful patient selection remain the most important factors for optimal outcomes.