Predictive determinants of overall survival among re-infected COVID-19 patients using the elastic-net regularized Cox proportional hazards model: a machine-learning algorithm.

BACKGROUND: Narrowing a large set of features to a smaller one can improve our understanding of the main risk factors for in-hospital mortality in patients with COVID-19. This study aimed to derive a parsimonious model for predicting overall survival (OS) among re-infected COVID-19 patients using machine-learning algorithms. METHODS: The retrospective data of 283 re-infected COVID-19 patients admitted to twenty-six medical centers (affiliated with Shiraz University of Medical Sciences) from 10 June to 26 December 2020 were reviewed and analyzed. An elastic-net regularized Cox proportional hazards (PH) regression and model approximation via backward elimination were utilized to optimize a predictive model of time to in-hospital death. The model was further reduced to its core features to maximize simplicity and generalizability. RESULTS: The empirical in-hospital mortality rate among the re-infected COVID-19 patients was 9.5%. In addition, the mortality rate among the intubated patients was 83.5%. Using the Kaplan-Meier approach, the OS (95% CI) rates for days 7, 14, and 21 were 87.5% (81.6-91.6%), 78.3% (65.0-87.0%), and 52.2% (20.3-76.7%), respectively. The elastic-net Cox PH regression retained 8 out of 35 candidate features of death. Transfer by Emergency Medical Services (EMS) (HR=3.90, 95% CI: 1.63-9.48), SpO2≤85% (HR=8.10, 95% CI: 2.97-22.00), increased serum creatinine (HR=1.85, 95% CI: 1.48-2.30), and increased white blood cells (WBC) count (HR=1.10, 95% CI: 1.03-1.15) were associated with higher in-hospital mortality rates in the re-infected COVID-19 patients. CONCLUSION: The results of the machine-learning analysis demonstrated that transfer by EMS, profound hypoxemia (SpO2≤85%), increased serum creatinine (more than 1.6 mg/dL), and increased WBC count (more than 8.5 (×109 cells/L)) reduced the OS of the re-infected COVID-19 patients. We recommend that future machine-learning studies should further investigate these relationships and the associated factors in these patients for a better prediction of OS.

Transferred Patients by Fars Province's Helicopter Emergency Medical Service (HEMS); A 2-Years Cross-Sectional Study in Southern Iran.

OBJECTIVE: To investigate the patients transferred by helicopters, as well as an emergent medical services that were performed for them. METHODS: In this retrospective cross-sectional study, all patients who were transferred by Fars province of Helicopter Emergency Medical Services (HEMS) to Shiraz hospitals, southern Iran (March 2017-March 2019) were investigated. Patients' information was collected and analyzed includes age, gender, dispatch reason, trauma mechanisms, take hold of emergent medical services, as well as the air transportation time, time between dispatch from the origin hospital and starting the procedures, and patients' outcome. RESULTS: Eighty-three patients were enrolled with the mean±SD age of 36.9±19.47 years that 75.9% had trauma (p<0.0001). Mental status deterioration (25.3%) was the most dispatched indications. The mortality rate was 13.25% totally (11.11% in traumatic vs. 10% in non-traumatic). The mean±SD of air transportation time was significantly lower than ground transportation in both traumatic (p=0.0013) and non-traumatic (p<0.0001) patients. Also, the mean±SD of time between dispatch from the origin hospital and starting the procedures was statistically lower in air transportation in both traumatic (p=0.0028) and non-traumatic (p=0.0017) patients. CONCLUSION: Most of the patients transferred by HEMS were traumatic. The air transportation time as well as the time between dispatches from the origin hospital to the starting of the procedures were significantly lower in HEMS in comparison with ground transportation for both traumatic and non-traumatic patients.

Diagnosing skull fracture in children with closed head injury using point-of-care ultrasound vs. computed tomography scan.

Diagnostic and therapeutic interventions in children for traumatic brain injury, which is known as the most important complication in trauma, require special attention. This study aimed to evaluate the accuracy of point-of-care ultrasound (POCUS) in diagnosing skull fracture in children with closed head injury in comparison with computed tomography (CT) scan. The current prospective cross-sectional study was conducted on children (0-14 years old), who were referred to the emergency department of a general teaching hospital in Shiraz, southern Iran (January-March 2018), with close head injury and were suspected of bone fracture. The participants were selected using a convenience sampling. The results of POCUS performed by emergency medicine (EM) residents were compared with the results of CT scan, which was reported by radiologists and considered a gold standard. Then, diagnostic tests were calculated. A total of 168 children were enrolled, with the mean ± standard deviation age of 6.21 ± 3.99. The most affected areas in the skull were the frontal (34.5%) and occipital areas (33.3%). POCUS had a sensitivity and specificity of 81.8% (95%CI, 48.2-97.7%) and 100% (95%CI, 97.7-100%), respectively. Positive and negative predictive values were 100% and 98.7%, with an accuracy of 98.8% in comparison with CT scan in the diagnosis of skull fracture.Conclusion: The results showed that POCUS with a portable ultrasonography machine, performed by the EM's physicians, have high diagnostic precision and can be considered a tool in the management of patients with closed head injury. What is Known: • Some studies have investigated the accuracy of ultrasound in diagnosing skull bone fractures in children with closed head injury, but before conducting this survey, no definite evidence recommended POCUS for skull fracture in children with closed head trauma in the ED. What is New: • POCUS with a portable ultrasonography machine, performed by the EM's physicians, has high diagnostic precision and can be considered a tool in the management of patients with closed head injury.

Accuracy of three-point compression ultrasound for the diagnosis of proximal deep-vein thrombosis in emergency department.

BACKGROUND: This study aimed to assess the accuracy of three-point compression ultrasonography (3PCUS) performed for the diagnosis of proximal deep-vein thrombosis (DVT) in Emergency Department (ED) compared with the results of duplex US (DUS) (whole-leg compression ultrasound). MATERIALS AND METHODS: The current prospective cross-sectional study with diagnostic test assessment was conducted on adult patients who were referred to the ED of a general teaching hospital in Shiraz, southern part of Iran (September 2016-May 2017), suspected of lower-extremity DVT, using a convenience sampling. The results of 3PCUS performed by ED residents were compared with the results of DUS performed by the radiology residents, which was considered as a criterion standard. RESULTS: A total of 240 patients were enrolled, with a mean (standard deviation) age of 59.46 (16.58). 3PCUS has a sensitivity and a specificity of 100% (95% confidence interval [CI], 96.55%-100%) and 93.33% (95% CI, 87.72%-96.91%), respectively, in comparison with DUS (whole-leg compression ultrasound). Negative predictive value and positive predictive value were 100% and 92.11% (95% CI, 86.12%-95.64%), respectively, with an accuracy of 96.25% (95% CI, 93%-98.27%). CONCLUSION: The results of this study showed that 3PCUS of the lower extremities with a portable US machine, performed by the ED's residents, can accurately identify the presence or absence of lower-extremity DVT.

Lung and cardiac ultrasound (LuCUS) protocol in diagnosing acute heart failure in patients with acute dyspnea.

OBJECTIVE: To investigate the accuracy of lung and cardiac ultrasound (LuCUS) protocol in diagnosing Acute Heart Failure (AHF) in patients who refer to Emergency Department (ED) with acute dyspnea. METHODS: This was an interventional study on adult patients, who were referred with chief complaint of undifferentiated acute dyspnea to the ED of Namazi hospital, the largest referral center in southern Iran. The intervention was LuCUS protocol, which was performed by Emergency Physicians (EPs) at the bedside. All patients' files were reviewed separately by two independent specialists, who were blinded to LuCUS results for final diagnosis as gold standard, then the results of LuCUS were compared with it. All data were analyzed and diagnostic tests were calculated (α = 0.05). RESULTS: In 100 patients enrolled in the study, 28% had the final diagnosis as AHF. The LuCUS protocol had the sensitivity of 64% (95%CI, 44%-81%), specificity of 97% (95%CI, 90%-100%), positive predicative value of 90% (95%CI, 69%-97%), negative predicative value of 88% (95%CI, 81%-92%), positive likelihood ratio of 23.14 (95%CI, 5.74-93.3), negative likelihood ratio of 0.37 (95%CI, 0.22-0.6), and accuracy of 88% (95%CI, 80%-94%). CONCLUSION: LuCUS protocol can be used by EPs as a practical tool to differentiate the cardiac and non-cardiac etiologies of acute dyspnea, specifically AHF, as it is more accurate than clinical diagnosis by itself. Hence, it is recommend that while conducting further studies in order to achieve more generalizable results, EPs can employ it alongside their clinical evaluations to have a faster and more accurate diagnosis.

The role of routine chest radiography in initial evaluation of stable blunt trauma patients.

BACKGROUND: Radiology plays an important role in evaluation of a trauma patient. Although chest radiography is recommended for initial evaluation of the trauma patient by the Advanced Trauma Life Support course, we hypothesized that precise physical examinations and history taking accurately identify those blunt trauma patients at low risk for chest injury, making routine radiographs unnecessary. Thus, this study was performed to investigate the role of chest radiography in initial evaluation of those trauma patients with normal physical examination. METHODS: In this prospective cross-sectional study, all the hemodynamically stable blunt trauma patients with negative physical examination result referred to our trauma center during a 4-month period (March-June 2009) were included. Chest radiographies were performed and reviewed for abnormalities. RESULTS: During the study period, 5091 blunt trauma patients referred to our center, out of which, 1008 were hemodynamically stable and had negative physical examination result. Only 1 (0.1%) patient had abnormal chest radiography that showed perihilar lymphadenopathy, unrelated to trauma. CONCLUSION: Performing routine chest radiography in stable blunt trauma patients is of low clinical value. Thus, decision making for performing chest radiography in blunt trauma patients based on clinical findings would be efficacious and resource saving.