Over the last two months, as oncology specialists, we have frequently been contacted for estimating prognosis for cancer patients affected by COVID-19 infection. Until now, there have been no clear markers to guide decision making regarding the appropriateness of invasive ventilation in cancer patients affected by COVID-19 infection. Therefore, we developed a practical tool encompassing a prognostic score. We aimed at identifying a subgroup of patients likely to have a better outcome and therefore may be potential candidates for invasive ventilation, "The Milano Policlinico ONCOVID-ICU score". The score is composed by three groups of variables: patient’s characteristics such as sex, age, BMI and comorbidities; oncological variables (treatment intent, life expectancy, on or off-treatment status) and clinical parameters in association with laboratory values (SOFA score and D-dimer). The SOFA score includes six different clinical parameters and during the first few days of ICU admissions has an important prognostic role. The oncological history should never represent, per se, a contraindication to intensive care and must be considered together with other variables, such as laboratory values, clinical parameters and patient characteristics, in order to make the hardest but best possible choice. The Milano Policlinico ONCOVID-ICU score, to our knowledge, is the first prognostic score proposed in this setting of patients and may be a useful tool to assess the prognosis of cancer patients being in this critical condition.

Optimizing intensive care resources using predicting modeling is paramount for fighting the COVID-19 pandemic. In this paper, we model the admission of COVID-19 patients in intensive care units (ICU) in Colombia using openly available data gathered from 18 March 2020 to 14 October 2020. After an intensive preprocessing of the data, we trained four different machine learning models using four different strategies for handling the imbalanced features. Our findings show that our best model (XGBoost) effectively predicts an Area Under the Curve (AUC-ROC) of 0.94, in line with the state-of-the-art results obtained in other predictive models obtained with medical data.

OBJETIVES: During the COVID-19 pandemic, the risk of collapse of the health system created great difficulties. We will demonstrate that Intermediate Respiratory Care Units (IRCU) provide adequate management of patients with non-invasive respiratory support, which is particularly important in patients with SARS-CoV-2 pneumonia. METHODS: A prospective observational study of patients with COVID-19 admitted to the ICU of a tertiary hospital. Sociodemographic data, comorbidities, pharmacological, respiratory support, laboratory and blood gas variables were collected. The overall cost of the unit was subsequently analyzed. RESULTS: 991 patients were admitted, 56 to the IRCU (of the 81 a critical care unit). Mean age was 65 years (SD 12.8), Barthel Index 75 (SD 8.3), Charlson 3.1 (SD 2.2), HTN 27%, COPD 89% and obesity 24%. Significant relationship (p <0.05) with higher mortality of the following: fever greater than or equal to 39oC [OR 5.6; 95% CI (1.2-2.7); p = 0.020], protocolized pharmacological treatment [OR 0.3; 95% CI (0.1-0.9); p = 0.023] and IOI [OR 3.7; 95% CI (1.1-12.3); p = 0.025]. NIMV showed less of a negative impact [OR 1.8; 95% CI (0.4-8.4); p = 0.423] than IOI. The total cost of the IRCUs amounted to €66,233. The cost per day of stay in the IRCU was €164 per patient. The total cost avoided was €214,865. CONCLUSION: The pandemic has highlighted the importance of IRCUs in facilitating the management of a high patient volume. The treatment carried out in IRCUs is effective and efficient, reducing both admissions to and stays in the ICU.

Monitoring and measuring magnesium (Mg) values are essential to prevent the development of numerous complications in perioperative medicine and critically ill patients. Although previous studies suggest that measuring free ionized magnesium (iMg) is more useful for estimating Mg status, clinicians currently rely on measurement of total serum magnesium to determine if supplemental magnesium is needed. In this review, we analyzed the recent literature to decide whether it is better to measure ionized serum Mg or total serum Mg when assessing magnesium status, whether iMg predicts clinical outcome, and what are the difficulties in measuring serum iMg levels in intensive care patients and perioperative medicine.

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is an emerging infectious disease with currently a pandemic state. Cardiac function can be involved, affecting prognosis, in addition with lung feature severity, particularly in patients with comorbidities. Since the renin angiotensin aldosterone (RAA) system may interact with SARS-Cov-2, researches are still ongoing to assess the prognostic value of RAA blockers in cardiology.

A 1-year prospective study was carried out on patients in the ICU unit at a tertiary care hospital, Hail, Kingdom of Saudi Arabia. A total of 163 bacterial isolates were obtained from different clinical specimens with a high proportion of bacteria found associated with ventilator-associated pneumoniae (70, 43%), followed by catheter-associated urinary tract infection (39, 24%), central line-associated bloodstream infection (25, 15%), and surgical site infection (14, 8.6%). Klebsiella pneumoniae was the most common isolate (39, 24%), followed by Acinetobacter baumannii (35, 21.47%), Pseudomonas aeruginosa (25, 15%), and Proteus spp (23, 14%). Among the highly prevalent bacterial isolates, extended-spectrum beta-lactamase was predominant (42, 42.4%). Proper use of antibiotics, continuous monitoring of drug sensitivity patterns, and taking all precautionary measures to prevent beta-lactamases-producing organisms in the clinical settings are crucial and significant factors to fend off life-threatening infections and for a better outcome.

Since December 2019, the world is fighting against coronavirus disease (COVID-19). This disease is caused by a novel coronavirus termed as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). This work focuses on the applications of machine learning algorithms in the context of COVID-19. Firstly, regression analysis is performed to model the number of confirmed cases and death cases. Our experiments show that autoregressive integrated moving average (ARIMA) can reliably model the increase in the number of confirmed cases and can predict future cases. Secondly, a number of classifiers are used to predict whether a COVID-19 patient needs to be admitted to an intensive care unit (ICU) or semi-ICU. For this, classification algorithms are applied to a dataset having 5644 samples. Using this dataset, the most significant attributes are selected using features selection by ExtraTrees classifier, and Proteina C reativa (mg/dL) is found to be the highest-ranked feature. In our experiments, random forest, logistic regression, support vector machine, XGBoost, stacking and voting classifiers are applied to the top 10 selected attributes of the dataset. Results show that random forest and hard voting classifiers achieve the highest classification accuracy values near 98%, and the highest recall value of 98% in predicting the need for admission into ICU/semi ICU units.

Introduction. The outbreak of the COVID pandemic was a period of uncer-tainty and tension for healthcare managers, resulting from the lack of knowledge, i.e. about the transmission of the virus, but also from the lack of uniform organisational and treatment procedures. It was the period where the ability to prepare to a crisis situation, to adapt to the existing conditions and to draw conclusion from the situa-tion were critical to keep ICUs operating. The aim of this study was to show the prep-aration of an ICU in Poland to ensure resilience, and also the methods of reacting dur-ing the COVID-19 pandemic on both central and local level. Methods. Based on the EC and WHO guidelines on resilience a matrix of 6 elements and 13 standards as-signed to them was created, with a series of questions from a survey questionnaire. Results. Good management in resilient systems is free access to any resource. A free and transparent flow of information and also well motivated human resources in an appropriate number. Conclusion. Appropriate preparation, adaptation to the existing situation and effective management of crisis situations is an important element of ICU resilience.

We present the AI-discovered aetiology of COVID-19, based on a precise disease model of COVID-19 built under five weeks that best matches the epidemiological characteristics, transmission dynamics, clinical features, and biological properties of COVID-19 and consistently explains the rapidly expanding COVID-19 literature. We present that SARS-CoV-2 implements a unique unbiased survival strategy of balancing viral replication with viral spread by increasing its dependence on (i) ACE2-expressing cells for viral entry and spread, (ii) PI3K signaling in ACE2-expressing cells for viral replication and egress, and (iii) viral-non-structural-and-accessory-protein-dependent immunomodulation to balance viral spread and viral replication. We further propose the combination of irinotecan (an in-market topoisomerase I inhibitor) and etoposide (an in-market topoisomerase IIinhibitor) could potentially be an exceptionally effective treatment to protect critically ill patients from death caused by COVID-19-specific cytokine storms triggered by sepsis, ARDS, and other fatal comorbidities.

A 2-year prospective study carried out on ventilator-associated pneumonia (VAP) patients in the intensive care unit at King Khalid hospital, Hail, Kingdom of Saudi Arabia (KSA), revealed a high prevalence of extremely drug-resistant (XDR) Acinetobacter baumannii. About a 9% increase in the incidence rate of A. baumannii has occurred in the VAP patients between 2019 and 2020 (21.4% to 30.7%). In 2019 the isolates were positive for IMP-1 and VIM-2 (31.1% and 25.7%, respectively) as detected by PCR. In comparison, a higher proportion of isolates produced NDM-1 in 2020. Here, we observed a high resistant proportion of ICU isolates towards the most common antibiotics in use. Colistin sensitivity dropped to 91.4% in the year 2020 as compared to 2019 (100%). Thus, the finding of this study has a highly significant clinical implementation in the clinical management strategies for VAP patients. Furthermore, strict implementation of antibiotic stewardship policies, regular surveillance programs for antimicrobial resistance monitoring, and screening for genes encoding drug resistance phenotypes have become imperative.

Background: Multi-drug resistance organisms (MDRO) often cause increased morbidity, mortality, and length of stays (LOS). However, there is uncertainty whether the infection of MDRO increase the morbidity, mortality, and ICU-LOS. Objective: This study performed to determine the prevalence of MDRO in ICU, site of infection and the association of MDRO or site of infection with mortality. Secondary outcome was determined by ascertaining the association of MDRO or site of infection with (ICU-LOS). Methods: A retrospective cohort study was performed with adult sepsis patients in ICU. Univariate and multivariate (MVA) logistic regression with cox regression modeling were performed to compute the association of MDRO on ICU-mortality. MVA modelling was performed for ICU-LOS predictors. Results: Out of 228 patients, the isolated MDRO was 97 (42.5%) of which 78% were gram-negative bacteria. The mortality rate among those with MDRO was 85 (37.3%). The hospital acquired infection (HAI) was significantly predictor for ICU-LOS in univariate linear regression (R² = 0.034, P=0.005). In MVA linear regression, both Enterococcus faecalis infection and acinetobacter baumannii (AC) -MDRO were predictors for ICU-LOS with (R² = 0.478, P<0.05). In the univariate cox regression, only the infection with AC- MDRO was a risk factor for ICU-mortality with [ HR =1.802 (95% CI: 1.2 – 2.706; P = 0.005)]. Conclusions: Identifying risk factors for MDRO highlight the appropriate administration of empirical antibiotics and effectively control of source of infection which would reduce mortality and ICU-LOS. The usage of broad- spectrum antibiotics should be limited for those having substantial risk factors to acquire MDRO.

(1) Background: Benefits and timing of percutaneous dilatational tracheostomy (PDT) in Intensive Care Unit (ICU) COVID-19 patients are still controversial. PDT is considered a high risk procedure for transmission of SARS CoV-2 to health care workers (HCWs). The present study analyzed optimal timing of PDT, clinical outcomes of patients undergoing PDT and safety of HCWs performing PDT. (2) Methods: 133 COVID-19 patients underwent PDT in our ICU from April 1, 2020 to March 31, 2021, 23 patients were excluded and 110 patients were enrolled. A trained medical team was dedicated to the PDT procedure. Demographic, clinical history and outcome data were collected. Patients who underwent PDT were stratified into two groups: early group, PDT ≤ 12 days from orotracheal-intubation (OTI) and late group, &gt;12 days from OTI; HCW surveillance program was performed. (3) Results: Early group included 57 patients and late group included 53 patients. Early group patients showed shorter ICU length of stay and fewer days of mechanical ventilation than the late group (p&lt;0.001). At day 7 after tracheostomy, early group patients required fewer intravenous anesthetic drugs and experienced an improvement of ventilation parameters, PaO2/FiO2-Ratio, PEEP and FiO2 (p&lt;0.001). No difference in case fatality ratio between the two groups was reported. No SARS-CoV-2 infection was reported in HCWs performing PDT. (4) Conclusions: PDT was safe and effective for COVID-19 patients, since it improved respiratory support parameters, reduced ICU length of stay and duration of mechanical ventilation, and optimized the weaning process. The procedure was safe for all HCWs involved in the dedicated medical team. The development of standardized early PDT protocols should be implemented and PDT procedure could be considered as first line approach in ICU COVID-19 requiring prolonged mechanical ventilation.

The use of Artificial Neural Networks (ANN) is a great contribution to medical studies since the application of forecasting concepts allows the analysis of future diseases propagations. In this context, this paper presents a study of the new coronavirus SARS-COV-2 with a focus on verifying the virus propagation associated with mitigation procedures and massive vaccination campaigns. There were proposed two methodologies to predict 28 days ahead the number of new cases, deaths, and ICU patients of five European countries: Portugal, France, Italy, United Kingdom, and Germany, and a case study of the results of massive immunization in Israel. The data input of cases, deaths, and daily ICU patients was normalized to reduce discrepant numbers due to the countries size, and the cumulative vaccination values by the percentage of population immunized, at least with one dose of vaccine. As a comparative criterion, the calculation of the mean absolute error (MAE) of all predictions presents the best methodology and targets other possibilities of use for the proposed method. The best architecture achieved a general MAE for the 1 to 28 days ahead forecast lower than 30 cases, 0,6 deaths and 2,5 ICU patients by million people.