Clustering of critically ill patients using an individualized learning approach enables dose optimization of mobilization in the ICU.

BACKGROUND: While early mobilization is commonly implemented in intensive care unit treatment guidelines to improve functional outcome, the characterization of the optimal individual dosage (frequency, level or duration) remains unclear. The aim of this study was to demonstrate that artificial intelligence-based clustering of a large ICU cohort can provide individualized mobilization recommendations that have a positive impact on the likelihood of being discharged home. METHODS: This study is an analysis of a prospective observational database of two interdisciplinary intensive care units in Munich, Germany. Dosage of mobilization is determined by sessions per day, mean duration, early mobilization as well as average and maximum level achieved. A k-means cluster analysis was conducted including collected parameters at ICU admission to generate clinically definable clusters. RESULTS: Between April 2017 and May 2019, 948 patients were included. Four different clusters were identified, comprising "Young Trauma," "Severely ill & Frail," "Old non-frail" and "Middle-aged" patients. Early mobilization (< 72 h) was the most important factor to be discharged home in "Young Trauma" patients (ORadj 10.0 [2.8 to 44.0], p < 0.001). In the cluster of "Middle-aged" patients, the likelihood to be discharged home increased with each mobilization level, to a maximum 24-fold increased likelihood for ambulating (ORadj 24.0 [7.4 to 86.1], p < 0.001). The likelihood increased significantly when standing or ambulating was achieved in the older, non-frail cluster (ORadj 4.7 [1.2 to 23.2], p = 0.035 and ORadj 8.1 [1.8 to 45.8], p = 0.010). CONCLUSIONS: An artificial intelligence-based learning approach was able to divide a heterogeneous critical care cohort into four clusters, which differed significantly in their clinical characteristics and in their mobilization parameters. Depending on the cluster, different mobilization strategies supported the likelihood of being discharged home enabling an individualized and resource-optimized mobilization approach. TRIAL REGISTRATION: Clinical Trials NCT03666286, retrospectively registered 04 September 2018.

Comparison of Different Ultrasound Methods to Assess Changes in Muscle Mass in Critically ill Patients.

BACKGROUND: Muscle ultrasound represents a promising approach to aid diagnoses of neuromuscular diseases in critically ill patients. Unfortunately, standardization of ultrasound measurements in clinical research is lacking, making direct comparisons between studies difficult. Protocols are required to assess qualitative muscle changes during an ICU stay in patients at high risk for the development of neuromuscular acquired weakness (ICUAW). METHODS: We conducted a retrospective, observational analysis comprised of three prospective observational studies with the aim of diagnosing muscle changes by ultrasound measurement of the quadriceps muscle. Different protocols were used in each of the three studies. In total, 62 surgical, neurocritical care and trauma intensive care patients were serially assessed by different ultrasound protocols during the first week of critical illness. The relative change in ultrasound measurements was calculated for all possible locations, methods and sides. Comparison was obtained using mixed effect models with the location, the height and the side as influencing variables and patients as fixed effect. The relationship between variables and outcomes was assessed by multivariable regression analysis. RESULTS: Ultrasound methods and measurement sites of the quadriceps muscles from all protocols were equally effective in detecting muscle changes. During the first week of an ICU stay, two groups were identified: patients with decreased muscle mass on ultrasound (n = 42) and a cohort with enlargement (n = 23). Hospital mortality was significantly increased in the cohort with muscle swelling (8 (19%) versus 12 (52%), p = .013). CONCLUSIONS: Different approaches of ultrasound measurement during critical-illness are equally able to detect muscle changes. While some patients have a decrease in muscle mass, others show swelling, which may result in a reduced probability of surviving the hospital stay. Causative reasons for these results still remain unclear.

Perioperative Hemodynamic Optimization in Patients at Risk for Delirium - A Randomized-Controlled Trial.

Background: Post-operative delirium is common in elderly patients and associated with increased morbidity and mortality. We evaluated in this pilot study whether a perioperative goal-directed hemodynamic optimization algorithm improves cerebral oxygenation and can reduce the incidence of delirium. Materials and Methods: Patients older than 70 years with high risk for post-operative delirium undergoing elective non-cardiac surgery were randomized to an intervention or control group. Patients in the intervention group received a perioperative hemodynamic optimization protocol based on uncalibrated pulse-contour analysis. Patients in the control group were managed according to usual standard of care. Incidence of delirium until day seven was assessed with confusion assessment method (CAM) and chart review. Cerebral oxygenation was measured with near-infrared spectroscopy. Results: Delirium was present in 13 of 85 (15%) patients in the intervention group and 18 of 87 (21%) in the control group [risk difference -5.4%; 95% confidence interval, -16.8 to 6.1%; P = 0.47]. Intervention did not influence length of stay in hospital or in-hospital mortality. Amounts of fluids and vasopressors applied, mean arterial pressure, cardiac index, and near-infrared spectroscopy values were comparable between groups. Conclusion: The hemodynamic algorithm applied in high-risk non-cardiac surgery patients did not change hemodynamic interventions, did not improve patient hemodynamics, and failed to increase cerebral oxygenation. An effect on the incidence of post-operative delirium could not be observed. Clinical Trial Registration: [Clinicaltrials.gov], identifier [NCT01827501].

Excessive hospitalization of patients with seizures in the Germany prehospital emergency system: a retrospective cohort study.

Seizures are a common reason for calling emergency medical services. A lack of guidelines on prehospital treatment in Germany leads to high transportation rates and reduced confidence in decision making by professionals. Our aim was to investigate the reasons for hospitalization and evaluate their necessity. A retrospective analysis of all emergency medical services records in Munich, Germany was performed in order to examine the reasons for hospitalization of patients with seizures and to evaluate their trajectory following admission to a university hospital. 8882 records were analyzed with 415 records reporting seizures (4.9%). Primary endpoint was transportation to hospital. In 380 cases (92%) patients were transported, of which 177 patients (47%) had known epilepsy; 35 patients (8%) were left at scene. Older patients and patients with higher amounts of administered medication at the scene were hospitalized significantly more often (p = 0.032 and p = 0.004, respectively). Median hospital length of stay was 1 night [IQR 1-2]. In patients with out-of-hospital seizures, high hospital transportation rates were evident, most of which could be considered as not indicated. One possible reason is the lack of guidelines in Germany, which leads to uncertainty among medical staff. This results in distress for the patients, their caregivers and consequently high costs.

Risk factors for Herpes simplex virus (HSV) and Cytomegalovirus (CMV) infections in critically-ill COVID-19 patients.

Background: To assess the prevalence of Herpes simplex and Cytomegalovirus infection in respiratory samples of critically-ill COVID-19 patients, its role in outcome and mortality and the influence of dexamethasone treatment in the early stage of SARS-CoV-2 infection. Methods: All mechanically ventilated COVID-19 patients treated on ICU between March 2020 and January 2021 were included. Respiratory specimens were tested for Herpes simplex virus (HSV) type 1, 2 and Cytomegalovirus (CMV) by quantitative real-time PCR. Clinical parameters were compared in the cohorts with and without HSV-1- infection. Results: 134 patients with a median age of 72.5 years (73.0% male, n=98) were included. HSV-1 reactivation occurred in 61 patients (45.5%), after median 9 (7-13) days of mechanical ventilation. The main factor for reactivation was length of stay on ICU (24 days vs 13 days, p<0.001) and duration of mechanical ventilation (417 vs 214 hours, p<0.001). Treatment with dexamethasone and a history of immunosuppression did not associate with HSV-infection in the univariate analysis (39 vs 41, p=0.462 and 27.9% vs 23.3%, p=0.561, respectively). Both ICU and hospital mortality were not significantly different in the cohorts with and without HSV-infection (57.4% vs 45.2%, p=0.219). Conclusions: Our study shows a high prevalence of HSV-infection in critically-ill COVID-19 patients which was unexpectedly higher than the prevalence of CMV-infections and unrelated to dexamethasone treatment. The main risk factors for HSV and CMV in the studied cohorts were the length of ICU stay and duration of mechanical ventilation. Therefore, we recommend routine monitoring of critically ill COVID-19 patients for these viral co-infections and consider treatment in those patients.