Baptist Health Corbin

Introduction: Unsupervised machine learning (ML) can provide insight into a dataset without significant expert time for annotation and labeling, but was never used to assess the heterogeneous MitraClip population. Hypothesis: We hypothesized that unsupervised k-means ML could identify prognostically-distinct phenogroups in MitraClip patients without a priori knowledge of the dataset. Methods: Patients who underwent MitraClip (June 2014-September 2020) at Mayo Clinic sites were identified from the Mayo institutional NCDR database for baseline and follow-up data. Variables with ≥ 50% missing data were excluded. A k-means algorithm was used for clustering analysis. Input variables were grouped according to 4 distinct k-means determined clusters. Kaplan-Meier survival analysis was used to assess the survival of each cluster. Results: A total of 389 consecutive patients were included in the final analysis, and 95 unique variables were used. The mean age was 80.3±8.7 years; 256 (65.8%) were male. The mean STS MV Replace score was 9.1±5.7. Fifty-five (14.5%) patients died during the mean follow duration (185 days). Kaplan-Meier analysis showed significant survival differences among clusters (Figure 1). The cluster (cluster 2, n=120) with best survival performance (all-cause mortality 3.3%) had features of non-calcified mitral leaflets, nonischemic cardiomyopathy, and less than moderate tricuspid regurgitation. Cluster 3 (n=66) had the worst survival performance (all-cause mortality 27.3%) and opposite features than cluster 2. Conclusions: Unsupervised ML can identify distinct phenotype clusters with prognostic significance in MitraClip patients. Patients with non-calcified mitral leaflets, nonischemic cardiomyopathy, and less than moderate tricuspid regurgitation are intrinsically different from other MitraClip patients and should be considered the potential optimal candidates.

We evaluated transplenic injection of iodinated contrast medium for computed tomography (CT) assessment of the portal vasculature. Specific aims were to: (1) establish a protocol for transplenic transplenic CT portography using a 40-row multidetector scanner; (2) compare transplenic CT portography to dual-phase CT angiography in terms of image quality, opacification of the portal system, and contrast enhancement of the portal vasculature and liver; (3) compare personnel exposure during transplenic CT portography and transplenic portal scintigraphy. Seven juvenile dogs underwent transplenic portal scintigraphy, CT angiography, and transplenic CT portography. Transplenic portal scintigraphy and CT angiography were performed using previously established protocols. For transplenic CT portography, a 20- or 22 gauge needle attached to an extension set was placed into the splenic parenchyma using CT guidance. Iodinated contrast medium (175 mg I/ml) was administered, and CT acquisition was started at the time of the injection. Transplenic CT portography was simple, rapid and provided more intense enhancement of the splenic and portal veins, with a lower contrast medium dose (median dose: 525 mg I for transplenic CT portography, 7700 mg I for CT angiography), but caused inconsistent intrahepatic portal branches and parenchymal opacification due to streamlining and streak artifacts. Despite significantly lower attenuation values in the portal vein, CT angiography provided sufficient enhancement for vessel identification and more consistent parenchymal hepatic enhancement. Personnel radiation exposure rate was higher during transplenic CT portography (0.0725 mSv/min) compared with transplenic portal scintigraphy (0.000125 mSv/min). As transplenic CT portography requires an average injection time of 1 min per study; over 650 [corrected] studies must be performed before reaching the maximum permissible whole body dose of 0.05 [corrected] Sv.