Using Machine Learning to Predict Mortality for COVID-19 Patients on Day 0 in the ICU.

Rationale: Given the expanding number of COVID-19 cases and the potential for new waves of infection, there is an urgent need for early prediction of the severity of the disease in intensive care unit (ICU) patients to optimize treatment strategies. Objectives: Early prediction of mortality using machine learning based on typical laboratory results and clinical data registered on the day of ICU admission. Methods: We retrospectively studied 797 patients diagnosed with COVID-19 in Iran and the United Kingdom (U.K.). To find parameters with the highest predictive values, Kolmogorov-Smirnov and Pearson chi-squared tests were used. Several machine learning algorithms, including Random Forest (RF), logistic regression, gradient boosting classifier, support vector machine classifier, and artificial neural network algorithms were utilized to build classification models. The impact of each marker on the RF model predictions was studied by implementing the local interpretable model-agnostic explanation technique (LIME-SP). Results: Among 66 documented parameters, 15 factors with the highest predictive values were identified as follows: gender, age, blood urea nitrogen (BUN), creatinine, international normalized ratio (INR), albumin, mean corpuscular volume (MCV), white blood cell count, segmented neutrophil count, lymphocyte count, red cell distribution width (RDW), and mean cell hemoglobin (MCH) along with a history of neurological, cardiovascular, and respiratory disorders. Our RF model can predict patient outcomes with a sensitivity of 70% and a specificity of 75%. The performance of the models was confirmed by blindly testing the models in an external dataset. Conclusions: Using two independent patient datasets, we designed a machine-learning-based model that could predict the risk of mortality from severe COVID-19 with high accuracy. The most decisive variables in our model were increased levels of BUN, lowered albumin levels, increased creatinine, INR, and RDW, along with gender and age. Considering the importance of early triage decisions, this model can be a useful tool in COVID-19 ICU decision-making.

Rapid identification of Iranian Acinetobacter baumannii strains by single PCR assay using BLA oxa-51 -like carbapenemase and evaluation of the antimicrobial resistance profiles of the isolates.

The rapid identification of relevant bacterial pathogens is of utmost importance in clinical settings. The aim of this study was to test a rapid identification technique for A. baumannii strains from Tehran Hospitals and to determine the antibiotic resistance profiles of the isolates. A hundred strains of Acinetobacter spp. grown from clinical specimens were identified as A. baumannii by conventional methods. Using PCR a bla OXA-51 -like gene was detected in all A. baumannii isolates but not in other species of acinetobacter. More than half of the isolates proved resistant to a variety of antibiotics by the disk diffusion technique. The rate of resistance to gentamicin, imipenem, ampicillin-sulbactam and amikacin was determined to be 45%, 53%, 62% and 62%, respectively. Moreover, most isolates (more than 90%) showed resistance to cephalosporins. This study shows that the demonstration of the bla OXA-51-like gene is a reliable and rapid way for the presumptive identification of A. baumannii and reveals that the rate of antibiotic resistance is high in Iranian A. baumannii isolates to a variety of antibiotics.

Distribution of different carbapenem resistant clones of Acinetobacter baumannii in Tehran hospitals.

The MICs of imipenem, meropenem, piperacillin-tazobactam, cefotaxime, polymixin B and tigecycline against 80 isolates of Acintobacter baumanii from 6 hospitals were determined. A multiplex-PCR was used to detect the genes encoding carbapenemases. Field Inversion Gel Electrophoresis (FIGE) was then used to investigate the genetic relationships among the carbapenem-resistant isolates. Only 7 isolates were resistant to polymixin B and tigecycline (MIC = 16). All isolates were positive for at least 2 carbapenemase genes. At least 10 distinct clones were detected by FIGE. A dominant pattern designated as pulsotype A consisting of 23 isolates was detected from 4 hospitals. The majority of isolates in this pulsotype had a bla(OXA-51/23-like) and bla(OXA-51/24-like) carbapenemase genes and cultured from the patients at burns and ICU. The pan drug resistant isolates belonged to different FIGE patterns. Nosocomial infections with different clones of Acintobacter baumanii occur at Tehran hospitals. However, inter-hospital transmission with certain pulsotypes is likely.