Investigating the prevalence of and predictive and risk factors for pulmonary embolism in patients with COVID-19 in Nemazee Teaching Hospital

Background@#Pulmonary thromboembolism (PTE) is a significant contributing factor to vascular diseases.This study aimed to determine the prevalence of pulmonary thromboembolism and its predisposing factors in patients with COVID-19. @*Methods@#This cross-sectional study included 284 patients with COVID-19 who were admitted to Nemazee Teaching Hospital (Shiraz, Iran) between June and August 2021. All patients were diagnosed with COVID-19 by a physician based on clinical symptoms or positive polymerase chain reaction (PCR) test results. The collected data included demographic data and laboratory findings. Data were analyzed using the SPSS software. P ≤0.05 was considered statistically significant. @*Results@#There was a significant difference in the mean age between the PTE group and non-PTE group (P=0.037). Moreover, the PTE group had a significantly higher prevalence of hypertension (36.7% vs. 21.8%, P=0.019), myocardial infarction (4.5% vs. 0%, P=0.006), and stroke (23.9% vs. 4.9%, P =0.0001). Direct bilirubin (P =0.03) and albumin (P =0.04) levels significantly differed between the PTE and non-PTE groups. Notably, there was a significant difference in the partial thromboplastin time (P =0.04) between the PTE and non-PTE groups. A regression analysis indicated that age (OR, 1.02; 95% CI, 1.00‒1.004; P =0.005), blood pressure (OR, 2.07; 95% CI, 1.12‒3.85; P=0.02), heart attack (OR, 1.02; 95% CI, 1.28‒6.06; P =0.009), and albumin level (OR, 0.39; 95% CI, 0.16‒0.97; P =0.04) were all independent predictors of PTE development. @*Conclusion@#Regression analysis revealed that age, blood pressure, heart attack, and albumin levels were independent predictors of PTE.

Incidence and pattern of traumatic spine injury in a single level I trauma center of southern Iran / 中华创伤杂志(英文版)

PURPOSE@#Spine injury is one of the leading causes of death and mortality worldwide. The objective of this study was to determine the incidence, pattern and outcome of trauma patients with spine injury referred to the largest trauma center in southern Iran during the last 3 years.@*METHODS@#This is a cross-sectional study conducted between March 2018 and June 2021 in the largest trauma center in the southern Iran. The data collection form included the age, sex, injury location (cervical, thoracic, and lumbar), cause of injury (traffic accidents, falls, and assaults), length of hospital stay, injured segment of spine injury, severity of injury, and outcome. Statistical analyzes were performed using SPSS software version 24.@*RESULTS@#Totally 776 cases of spine injury were identified. The spine injury rate was 17.0%, and the mortality rate was 15.5%. Cervical spine injury (20.4%) more often occulted in motorcycle accident, and thoracic spine injury (20.1%) occulted in falls. The highest and lowest rates of spine injurys were related to lumbar spine injury (30.2%) and cervical spine injury (21.5%), respectively. There was a statistically significant relationship between the mechanism of injury and the location of spine injury (p < 0.001). And patients with lumbar spine injury had the highest mortality rate (16.7%). Injury severity score (OR= 1.041, p < 0.001) and length of stay (OR = 1.018, p < 0.001) were strong predictors of mortality in trauma patients with spine injury.@*CONCLUSION@#The results of the study showed that the incidence of traumatic spine injury rate was approximately 17.0% in southern of Iran. Road traffic injury and falls are the common mechanism of injury to spine. It is important to improve the safety of roads, and passengers, as well as work environment, and improve the quality of cars. Also, paying attention to the pattern of spine injury may assist to prevent the missing diagnosis of spine injury in multiple trauma patients.

Mortality Prediction from Hospital-Acquired Infections in Trauma Patients Using an Unbalanced Dataset / 대한의료정보학회지

Objectives@#Machine learning has been widely used to predict diseases, and it is used to derive impressive knowledge in the healthcare domain. Our objective was to predict in-hospital mortality from hospital-acquired infections in trauma patients on an unbalanced dataset. @*Methods@#Our study was a cross-sectional analysis on trauma patients with hospital-acquired infections who were admitted to Shiraz Trauma Hospital from March 20, 2017, to March 21, 2018. The study data was obtained from the surveillance hospital infection database. The data included sex, age, mechanism of injury, body region injured, severity score, type of intervention, infection day after admission, and microorganism causes of infections. We developed our mortality prediction model by random under-sampling, random over-sampling, clustering (k-mean)-C5.0, SMOTE-C5.0, ADASYN-C5.5, SMOTE-SVM, ADASYN-SVM, SMOTE-ANN, and ADASYN-ANN among hospital-acquired infections in trauma patients. All mortality predictions were conducted by IBM SPSS Modeler 18. @*Results@#We studied 549 individuals with hospital-acquired infections in a trauma hospital in Shiraz during 2017 and 2018. Prediction accuracy before balancing of the dataset was 86.16%. In contrast, the prediction accuracy for the balanced dataset achieved by random under-sampling, random over-sampling, clustering (k-mean)-C5.0, SMOTE-C5.0, ADASYN-C5.5, and SMOTE-SVM was 70.69%, 94.74%, 93.02%, 93.66%, 90.93%, and 100%, respectively. @*Conclusions@#Our findings demonstrate that cleaning an unbalanced dataset increases the accuracy of the classification model. Also, predicting mortality by a clustered under-sampling approach was more precise in comparison to random under-sampling and random over-sampling methods.