Search

In this study, we assess image quality in computed tomography scans reconstructed via DLIR (Deep Learning Image Reconstruction) and compare it with iterative reconstruction ASIR-V (Adaptive Statistical Iterative Reconstruction) in CT (computed tomography) scans of the head. The CT scans of 109 patients were subjected to both objective and subjective evaluation of image quality. The objective evaluation was based on the SNR (signal-to-noise ratio) and CNR (contrast-to-noise ratio) of the brain’s gray and white matter. The regions of interest for our study were set in the BGA (basal ganglia area) and PCF (posterior cranial fossa). Simultaneously, a subjective assessment of image quality, based on brain structure visibility, was conducted by experienced radiologists. In the assessed scans, we obtained up to a 54% increase in SNR for gray matter and a 60% increase for white matter using DLIR in comparison to ASIR-V. Moreover, we achieved a CNR increment of 58% in the BGA structures and 50% in the PCF. In the subjective assessment of the obtained images, DLIR had a mean rating score of 2.8, compared to the mean score of 2.6 for ASIR-V images. In conclusion, DLIR shows improved image quality compared to the standard iterative reconstruction of CT images of the head.

Neurohormone activation plays an important role in Acute Heart Failure (AHF) pathophysiology. Serum osmolarity can affect this activation causing vasopressin excretion. The role of serum osmolarity and vasopressin concentration and its interaction remain still unexplored in AHF. The objective of our study was to evaluate the relationship of serum osmolarity with clinical parameters, vasopressin concentration, in-hospital course, and outcomes in AHF patients. The study group consisted of 338 AHF patients (male (76.3%), mean age of 68 ± 13 years) with serum osmolarity calculated by the equation: 1.86 × sodium [mmol/L] + (glucose [mg/dL]/18) + (urea [mg/dL]/2.8) + 9 and divided into osmolarity quartiles marked as: low: 304 mOsm/L. There was an increasing age gradient in the groups and patients differed in the occurrence of comorbidities and baseline clinical and laboratory parameters. Importantly, analysis revealed that vasopressin presented a linear correlation with osmolarity (r = −0.221, p = 0.003) and its concentration decreased with quartiles (61.6 [44.0–81.0] vs. 57.8 [50.0–77.3] vs. 52.7 [43.1–69.2] vs. 45.0 [30.7–60.7] pg/mL, respectively, p = 0.034). This association across quartiles was observed among de novo AHF (63.6 [55.3–94.5] vs. 58.0 [50.7–78.6] vs. 52.0 [46.0–58.0] vs. 38.0 [27.0–57.0] pg/mL, respectively, p = 0.022) and was not statistically significant in patients with acute decompensated heart failure (ADHF) (59.5 [37.4–80.0] vs. 52.0 [38.0–74.5] vs. 57.0 [38.0–79.0] vs. 50.0 [33.0–84.0] pg/mL, respectively, p = 0.849). The worsening of renal function episodes were more frequent in quartiles with higher osmolarity (4 vs. 2 vs. 13 vs. 11%, respectively, p = 0.018) and patients that belonged to the quartiles with low and high osmolarity were characterized more often by incidence of worsening heart failure (20 vs. 9 vs. 10 vs. 22%, respectively, p = 0.032). There was also a U-shape distribution in relation to one-year mortality (31 vs. 19 vs. 23 vs. 37%, respectively, p = 0.022). In conclusion, there was an association of serum osmolarity with clinical status and both in-hospital and out-of-hospital outcomes. Moreover, the linear dependence between vasopressin concentration and serum osmolarity in the AHF population was identified and was driven mainly by patients with de novo AHF which suggests different pathophysiological paths in ADHF and AHF de novo.

Acute heart failure (AHF) is a life-threatening, heterogeneous disease requiring urgent diagnosis and treatment. The clinical severity and medical procedures differ according to a complex interplay between the deterioration cause, underlying cardiac substrate, and comorbidities. This study aimed to analyze the natural phenotypic heterogeneity of the AHF population and evaluate the possibilities offered by clustering (unsupervised machine-learning technique) in a medical data assessment. We evaluated data from 381 AHF patients. Sixty-three clinical and biochemical features were assessed at the admission of the patients and were included in the analysis after the preprocessing. The K-medoids algorithm was implemented to create the clusters, and optimization, based on the Davies-Bouldin index, was used. The clustering was performed while blinded to the outcome. The outcome associations were evaluated using the Kaplan-Meier curves and Cox proportional-hazards regressions. The algorithm distinguished six clusters that differed significantly in 58 variables concerning i.e., etiology, clinical status, comorbidities, laboratory parameters and lifestyle factors. The clusters differed in terms of the one-year mortality (p = 0.002). Using the clustering techniques, we extracted six phenotypes from AHF patients with distinct clinical characteristics and outcomes. Our results can be valuable for future trial constructions and customized treatment.