The vasoactive inotropic score (VIS) is calculated as a weighted sum of all administered vasopressor and inotropic medications and quantifies the amount of pharmacological cardiovascular support in patients with the most severe combined cardiopulmonary failure supported with extracorporeal membrane oxygenation (ECMO). This study evaluated (1) whether VIS prior to the initiation of ECMO is an independent predictor of survival in these patients and (2) whether VIS might guide the selection of the appropriate extracorporeal cannulation modality (Veno-Venous ‘V-V’ or Veno-VenoArterial ‘V-VA’). In this study, 39 V-VA and 182 V-V ECMO runs were retrospectively analyzed. VIS immediately prior to ECMO initiation (pre-ECMO) was 40 (10/113) in all patients, 30 (10/80) in patients with V-V ECMO and 207 (60/328) in patients with V-VA ECMO. Pre-ECMO VIS was an independent predictor of survival in univariate (AUC = 0.68, p = 0.001) and multi-variable analyses (p = 0.02). Pre-ECMO VIS was clearly associated with mortality (p = 0.001) in V-V ECMO group; however, V-VA ECMO disrupted this association (p = 0.18). Therefore, in conjunction with echocardiography, VIS might assist in selecting the appropriate ECMO cannulation strategy as patients with a pre-ECMO VIS ≥ 61.4 had significantly lower odds of survival compared to those with lower VIS.

Objective The aim of this study was to determine the feasibility of using machine learning to establish the need for preclinical airway management for injured patients based on a standardized emergency dataset.Methods A registry-based, retrospective analysis was conducted of adult trauma patients who were treated by physician-staffed emergency medical services in southwestern Germany between 2018 and 2020. The primary outcome was to assess the feasibility of using the random forest (RF) and Naive Bayes (NB) machine learning algorithms to predict the need for preclinical airway management. The secondary outcome was to use a principal component analysis to determine the attributes that can be used and advanced for future model development.Results In total, 25,556 adults with multiple injuries were identified, including 1,451 patients (5.7%) who required airway management. Key attributes were auscultation, injury pattern, oxygen therapy, thoracic drainage, noninvasive ventilation, catecholamines, pelvic sling, colloid infusion, initial vital signs, preemergency status, and shock index. The area under the receiver operating characteristics curve was between 0.96 (RF; 95% confidence interval [CI], 0.96–0.97) and 0.93 (NB; 95% CI, 0.92–0.93; P<0.01). For the prediction of airway management, RF yielded a higher precision-recall area than NB (0.83 [95% CI, 0.8–0.85] vs. 0.66 [95% CI, 0.61–0.72], respectively; P<0.01).Conclusion To predict the need for preclinical airway management in injured patients, attributes that are commonly recorded in standardized datasets can be used with machine learning. In future models, the RF algorithm could be used because it has robust prediction accuracy.

A common final pathway of pathogenetic mechanisms in septic organ dysfunction and death is a lack or non-utilization of oxygen. Plasma concentrations of lactate serve as surrogates for the oxygen-deficiency-induced imbalance between energy supply and demand. As S-adenosylhomocysteine (SAH) was shown to reflect tissue hypoxia, we compared the ability of SAH versus lactate to predict the progression of inflammatory and septic disease to septic organ dysfunction and death. Using univariate and multiple logistic regression, we found that SAH but not lactate, taken upon patients’ inclusion in the study close to ICU admission, significantly and independently contributed to the prediction of disease progression and death. Due to the stronger increase in SAH in relation to S-adenosylmethionine (SAM), the ratio of SAM to SAH, representing methylation potential, was significantly decreased in patients with septic organ dysfunction and non-survivors compared with SIRS/sepsis patients (2.8 (IQR 2.3–3.9) vs. 8.8 (4.9–13.8); p = 0.003) or survivors (4.9 (2.8–9.5) vs. 8.9 (5.1–14.3); p = 0.026), respectively. Thus, SAH appears to be a better contributor to the prediction of septic organ dysfunction and death than lactate in critically ill patients. As SAH is a potent inhibitor of SAM-dependent methyltransferases involved in numerous vital biochemical processes, the impairment of the SAM-to-SAH ratio in severely critically ill septic patients and non-survivors warrants further studies on the pathogenetic role of SAH in septic multiple organ failure.

Viral pneumonia is frequently complicated by bacterial co- or superinfection (c/s) with adverse effects on patients’ outcomes. However, the incidence of c/s and its impact on the outcomes of patients might be dependent on the type of viral pneumonia. We performed a retrospective observational study in patients with confirmed COVID-19 pneumonia (CP) or influenza pneumonia (IP) from 01/2009 to 04/2022, investigating the incidence of c/s using a competing risk model and its impact on mortality in these patients in a tertiary referral center using multivariate logistic regressions. Co-infection was defined as pulmonary pathogenic bacteria confirmed in tracheal aspirate or bronchoalveolar lavage within 48 h after hospitalization. Superinfection was defined as pulmonary pathogenic bacteria detected in tracheal aspirate or bronchoalveolar lavage 48 h after hospitalization. We examined 114 patients with CP and 76 patients with IP. Pulmonary bacterial co-infection was detected in 15 (13.2%), and superinfection was detected in 50 (43.9%) of CP patients. A total of 5 (6.6%) co-infections (p = 0.2269) and 28 (36.8%) superinfections (p = 0.3687) were detected in IP patients. The overall incidence of c/s did not differ between CP and IP patients, and c/s was not an independent predictor for mortality in a study cohort with a high disease severity. We found a significantly higher probability of superinfection for patients with CP compared to patients with IP (p = 0.0017).

Background: Severe courses and high hospitalization rates were ubiquitous during the first pandemic SARS-CoV-2 waves. Thus, we aimed to examine whether integrative diagnostics may aid in identifying vulnerable patients using crucial data and materials obtained from COVID-19 patients hospitalized between 2020 and 2021 (n = 52). Accordingly, we investigated the potential of laboratory biomarkers, specifically the dynamic cell decay marker cell-free DNA and radiomics features extracted from chest CT. Methods: Separate forward and backward feature selection was conducted for linear regression with the Intensive-Care-Unit (ICU) period as the initial target. Three-fold cross-validation was performed, and collinear parameters were reduced. The model was adapted to a logistic regression approach and verified in a validation naïve subset to avoid overfitting. Results: The adapted integrated model classifying patients into “ICU/no ICU demand” comprises six radiomics and seven laboratory biomarkers. The models’ accuracy was 0.54 for radiomics, 0.47 for cfDNA, 0.74 for routine laboratory, and 0.87 for the combined model with an AUC of 0.91. Conclusion: The combined model performed superior to the individual models. Thus, integrating radiomics and laboratory data shows synergistic potential to aid clinic decision-making in COVID-19 patients. Under the need for evaluation in larger cohorts, including patients with other SARS-CoV-2 variants, the identified parameters might contribute to the triage of COVID-19 patients.