Single-Site Experience with an Automated Artificial Intelligence Application for Left Ventricular Ejection Fraction Measurement in Echocardiography.

Left ventricular ejection fraction (LVEF) is a key parameter in evaluating left ventricular (LV) function using echocardiography (Echo), but its manual measurement by the modified biplane Simpson (MBS) method is time consuming and operator dependent. We investigated the feasibility of a server-based, commercially available and ready-to use-artificial intelligence (AI) application based on convolutional neural network methods that integrate fully automatic view selection and measurement of LVEF from an entire Echo exam into a single workflow. We prospectively enrolled 1083 consecutive patients who had been referred to Echo for diagnostic or therapeutic purposes. LVEF was measured independently using MBS and AI. Test-retest variability was assessed in 40 patients. The reliability, repeatability, and time efficiency of LVEF measurements were compared between the two methods. Overall, 889 Echos were analyzed by cardiologists with the MBS method and by the AI. Over the study period of 10 weeks, the feasibility of both automatic view classification and seamlessly measured LVEF rose to 81% without user involvement. LVEF, LV end-diastolic and end-systolic volumes correlated strongly between MBS and AI (R = 0.87, 0.89 and 0.93, p < 0.001 for all) with a mean bias of +4.5% EF, -12 mL and -11 mL, respectively, due to impaired image quality and the extent of LV function. Repeatability and reliability of LVEF measurement (n = 40, test-retest) by AI was excellent compared to MBS (coefficient of variation: 3.2% vs. 5.9%), although the median analysis time of the AI was longer than that of the operator-dependent MBS method (258 s vs. 171 s). This AI has succeeded in identifying apical LV views and measuring EF in one workflow with comparable results to the MBS method and shows excellent reproducibility. It offers realistic perspectives for fully automated AI-based measurement of LVEF in routine clinical settings.

An All-Dielectric Metasurface Polarimeter.

The polarization state of light is a key parameter in many imaging systems. For example, it can image mechanical stress and other physical properties that are not seen with conventional imaging and can also play a central role in quantum sensing. However, polarization is more difficult to image, and polarimetry typically involves several independent measurements with moving parts in the measurement device. Metasurfaces with interleaved designs have demonstrated sensitivity to either linear or circular/elliptical polarization states. Here, we present an all-dielectric meta-polarimeter for direct measurement of any arbitrary polarization state from a single-unit-cell design. By engineering a completely asymmetric design, we obtained a metasurface that can excite eigenmodes of the nanoresonators, thus displaying a unique diffraction pattern for not only any linear polarization state but all elliptical polarization states (and handedness) as well. The unique diffraction patterns are quantified into Stokes parameters with a resolution of 5° and with a polarization state fidelity of up to 99 ± 1%. This holds promise for applications in polarization imaging and quantum state tomography.

Data for validation and adjustment of APACHE II score in cardiogenic shock patients treated with a percutaneous left ventricular assist device.

A precise prognosis is of imminent importance in intensive care medicine. This article provides data showing the overestimation of intrahospital mortality by APACHE II score in various subgroups of cardiogenic shock patients treated with a percutaneous left ventricular assist device. The data set includes additional baseline characteristics regarding age, pre-existing diseases, characteristics of coronary artery disease, characteristics of cardiopulmonary resuscitation, and hemodynamic parameter not included in the APACHE II score. Further data were provided which characterize derivation and validation group. Both groups were used for adjustment of the APACHE II approach. The data are supplemental to our original research article titled "Predictive value of the APACHE II score in cardiogenic shock patients treated with a percutaneous left ventricular assist device" (Mierke et al., IJC Heart & Vasculature. 40 (2022) 101013. https://doi.org/10.1016/j.ijcha.2022.101013).

Predictive value of the APACHE II score in cardiogenic shock patients treated with a percutaneous left ventricular assist device.

Background: The APACHE II score assesses patient prognosis in intensive care units. Different disease entities are predictable by using a specific factor called Diagnostic Category Weight (DCW). We aimed to validate the prognostic value of the APACHE II score in patients treated with a percutaneous left ventricular assist device because of refractory cardiogenic shock (CS). Methods: From the Dresden Impella Registry, we analyzed 180 patients receiving an Impella CP®. The main outcome was the observed intrahospital mortality ( S ^ ( t h o s p ) ), which was compared to the predicted mortality estimated by the APACHE II score. Results: The APACHE II score, which was 33.5 ± 0.6, significantly overestimated intrahospital mortality ( S ^ ( t h o s p ) 54.4 ± 3.7% vs. APACHE II 74.6 ± 1.6%; p < 0.001). Nevertheless, the APACHE II score showed an acceptable accuracy to predict intrahospital mortality (ROC AUC 0.70; 95% CI 0.62-0.78). Thus, we adapted the formula for calculation of predicted mortality by adjusting DCW. The total registry cohort was randomly divided into derivation group for calculation of adjusted DCW and validation group for testing. Intrahospital mortality was much more precisely predicted using the adjusted DCW compared to the conventional DCW (difference of predicted and observed mortality: -4.7 ± 2.4% vs. -23.2 ± 2.3%; p < 0.001). The new calculated DCW was -1.183 for the total cohort. Conclusion: The APACHE II score has an acceptable accuracy for the prediction of intrahospital mortality but overestimates its total amount in CS patients. Adjustment of the DCW can lead to a much more precise prediction of prognosis.

The predictive role of early CRP values for one-year mortality in the first 2 d after acute myocardial infarction.

BACKGROUND: An excessive inflammatory reaction after acute myocardial infarction (AMI) is known to be harmful. New anti-inflammatory therapies are required. PURPOSE: This study assessed the predictive role of early CRP in patients with STEMI. METHODS: A total of 1003 patients with STEMI were analysed. A total of 180 patients with proven infection were excluded. CRP after 12, 24 and 48 h after pain onset were evaluated. RESULTS: Of 823 patients, 103 (12.5%) died within one year after AMI. The deceased patients showed higher CRP, even after already 12 h (6 vs. 13 mg/l, p < .001), 24 h (13 vs. 25 mg/l, p < .001) and after 48 h (40 vs. 92 mg/l, p < .001). A CRP of ≥8 mg/l, 12 h after AMI, was found in 45% and was independently associated with long-term mortality (OR: 2.7, p = .03), after 24 h: CRP ≥ 18 mg/l in 44% (OR: 2.5, p = .03), after 48 h: CRP ≥ 53 mg/l in 44% (OR 1.9, p = .03). Early CRP values correlated strongly with the later maximum value of CRP (p < .001). CONCLUSIONS: Already early CRP values are accurate for risk-prediction following AMI. By identifying patients who are beginning to develop an excessive inflammatory response, it may be possible to identify those who benefit from anti-inflammatory therapies.

Comparative effects of proportional assist and variable pressure support ventilation on lung function and damage in experimental lung injury.

OBJECTIVE: To investigate the effects of proportional assist ventilation, variable pressure support, and conventional pressure support ventilation on lung function and damage in experimental acute lung injury. DESIGN: : Randomized experimental study. SETTING: University hospital research facility. SUBJECTS: : Twenty-four juvenile pigs. INTERVENTIONS: Pigs were anesthetized, intubated, and mechanically ventilated. Acute lung injury was induced by saline lung lavage. After resuming of spontaneous breathing, animals were randomly assigned to 6 hrs of assisted ventilation with pressure support ventilation, proportional assist ventilation, or variable pressure support (n = 8 per group). Mean tidal volume was kept at ≈6 mL/kg in all modes. MEASUREMENTS AND MAIN RESULTS: Lung functional parameters, distribution of ventilation by electrical impedance tomography, and breathing patterns were analyzed. Histological lung damage and pulmonary inflammatory response were determined postmortem. Variable -pressure support and proportional assist ventilation improved oxygenation and venous admixture compared with pressure support ventilation. Proportional assist ventilation led to higher esophageal pressure time product than variable pressure support and pressure support ventilation, and redistributed ventilation from central to dorsal lung regions compared to pressure support ventilation. Variable pressure support and proportional assist ventilation yielded higher tidal volume variability than pressure support ventilation. Such pattern was deterministic (self-organized) during proportional assist ventilation and stochastic (random) during variable pressure support. Subject-ventilator synchrony as well as pulmonary inflammatory response and damage did not differ among groups. CONCLUSIONS: In a lung lavage model of acute lung injury, both variable pressure support and proportional assist ventilation increased the variability of tidal volume and improved oxygenation and venous admixture, without influencing subject-ventilator synchrony or affecting lung injury compared with pressure support ventilation. However, variable pressure support yielded less inspiratory effort than proportional assist ventilation at comparable mean tidal volumes of 6 mL/kg.