Efficient management of pulmonary embolism diagnosis using a two-step interconnected machine learning model based on electronic health records data.

Pulmonary Embolism (PE) is a life-threatening clinical disease with no specific clinical symptoms and Computed Tomography Angiography (CTA) is used for diagnosis. Clinical decision support scoring systems like Wells and rGeneva based on PE risk factors have been developed to estimate the pre-test probability but are underused, leading to continuous overuse of CTA imaging. This diagnostic study aimed to propose a novel approach for efficient management of PE diagnosis using a two-step interconnected machine learning framework directly by analyzing patients' Electronic Health Records data. First, we performed feature importance analysis according to the result of LightGBM superiority for PE prediction, then four state-of-the-art machine learning methods were applied for PE prediction based on the feature importance results, enabling swift and accurate pre-test diagnosis. Throughout the study patients' data from different departments were collected from Sina educational hospital, affiliated with the Tehran University of medical sciences in Iran. Generally, the Ridge classification method obtained the best performance with an F1 score of 0.96. Extensive experimental findings showed the effectiveness and simplicity of this diagnostic process of PE in comparison with the existing scoring systems. The main strength of this approach centered on PE disease management procedures, which would reduce avoidable invasive CTA imaging and be applied as a primary prognosis of PE, hence assisting the healthcare system, clinicians, and patients by reducing costs and promoting treatment quality and patient satisfaction.

Comparing Therapeutic versus Prophylactic Enoxaparin Therapy in Severe COVID-19 Patients: A Randomized Clinical Trial.

Background: Coronavirus disease 2019 (COVID-19) has been associated with a hypercoagulopathy state; however, the efficacy of different anticoagulant regimens in preventing thrombotic events is not clear. We aimed to compare therapeutic versus prophylactic enoxaparin therapy in severe COVID-19 patients. Methods: In this single-center, open-label, randomized controlled trial, adult patients with severe COVID-19 presentations and an increased D-dimer level of more than 4 times the normal upper limit were randomly assigned to receive either prophylactic or therapeutic dose of enoxaparin. All patients were observed for at least 4 months regarding the overall survival as the primary outcome. Hospitalization duration, the need for intensive care unit (ICU) admission, the need for mechanical ventilation, and major adverse events (MAEs) were also analyzed as the secondary outcomes. Survival analysis was done via Kaplan-Meier curves and the Log-rank test. Cox regression was used, adjusting for baseline variables. Results: Overall, 237 patients (152 men and 85 women) were randomized to either arm (121 to prophylactic and 116 to therapeutic groups). The mortality rate was 27 (22.3%) and 52 (44.8%) in prophylactic and therapeutic arms, respectively. Prophylactic enoxaparin was associated with better survival in the log-rank test (P < 0.001; HR, 0.42). Additionally, a significantly lower rate of ICU admission, a lower rate of MAEs, and shorter hospitalization were observed in the prophylactic arm (P < 0.001, P = 0.009, and P = 0.028, respectively). Conclusion: The results of the current study were in favor of anticoagulant treatment with prophylactic doses of enoxaparin. Still, due to the limitations of this paper, we suggest that these findings be treated cautiously.

Rectus Sheath Hematoma in COVID-19 Patients as a Mortal Complication: A Retrospective Report.

Background: Rectus sheath hematoma is a rare self-limited presentation that has become a concern in hospitalized COVID-19 patients receiving anticoagulant therapies. Method: A retrospective multicentric study was conducted in referral hospitals affiliated with the Tehran University of Medical Science, Tehran, Iran, between June and August 2021. Patients with a confirmed diagnosis of COVID-19 that were complicated with rectus sheath hematoma during hospitalization were included. Median (lower quartile to upper quartile) was used to report the distribution of the results. Result: This study was conducted on nine patients with confirmed COVID-19 pneumonia, including eight females and one male. The severity of viral pneumonia was above average in eight patients. The median age and median body mass index were 65 (55.5 to 78) years and 29.38 (23.97 to 31.71) kg/m2. The duration of anticoagulant therapy was 10 (6 to 14) days, and the median length of hospital stay was 20 (10 to 23.5) days. Rectus sheath hematoma occurred after a median reduction of 4 (2.7 to 6.6) units in blood hemoglobin. Although 66.7% received ICU care and all of them were under full observation in well-equipped hospitals, the mortality rate was 55.6%. Conclusion: In summary, increased levels of inflammatory markers such as lactic acid dehydrogenase along with an abrupt decrease in blood hemoglobin in COVID-19 patients should be considered as predisposing factors for rectus sheath hematoma, especially in patients with moderate to severe COVID-19 pneumonia under anticoagulant therapy. This complication had been considered a self-limited condition; however, it seems to be fatal in patients with COVID-19 pneumonia. Further studies in larger sample sizes should be conducted to find out suitable management for this complication.

Prognostic significance of CHADS2 and CHA2DS2-VASc scores to predict unfavorable outcomes in hospitalized patients with COVID-19.

Introduction: Owing to the imposed burden of the coronavirus disease 2019 (COVID-19),the need for stratifying the prognosis of patients has never been timelier. Hence, we aimed to ascertain the value of CHADS2, CHA2DS2-VASc, and CHA2DS2-VASc-M (one point for male instead of female) scores to predict unfavorable outcomes in COVID-19 patients. Methods: We enrolled consecutive patients above 18 years of age with confirmed COVID-19,who were admitted between February 16 and November 1, 2020. The primary endpoint of this study was three-month all-cause mortality. The secondary endpoints were considered four major in-hospital clinical features, including acute respiratory distress syndrome, cardiac injury,acute kidney injury, and mechanical ventilation. Results: A total of 1,406 hospitalized COVID-19 patients were studied, among which 301(21.40%) patients died during the follow-up period. Regarding the risk scores, CHADS 2≥1,CHA2DS2-VASc≥2, and CHA2DS2-VASc-M≥2 were significantly associated with mortality. The performance of all risk scores for predicting mortality was satisfactory (area under the curve:0.668, 0.668, and 0.681, respectively). Appraising secondary endpoints, we found that all three risk scores were associated with increased risk of acute respiratory distress syndrome, cardiac injury, acute kidney injury, and mechanical ventilation. Lastly, we revealed that all risk scores were significantly correlated with serum levels of laboratory biomarkers. Conclusion: Our analysis illustrated that the CHADS2, CHA2DS2-VASc, and CHA2DS2-VASc-Mscores could aid prognostication of unfavorable outcomes in COVID-19 patients. Therefore,these easily calculable methods could be integrated into the overall therapeutic strategy to guide the COVID-19 management more accurately.

Long-Term Impact of the COVID-19 Associated AKI: The Relationship between Kidney Recovery and Mortality in a 10-Month Follow-Up Cohort Study.

INTRODUCTION: Coronavirus-2019 disease (COVID-19)-associated acute kidney injury (AKI) and its short and mid-term effect on kidney has been well established in the previous literature, indicating a high number of AKI in hospitalized patients associated with high rates of mortality, followed by high rates of unresolved kidney injury at the time of discharge. However, the long-term impact of AKI and its resulting lack of recovery at the time of discharge has not been investigated. Herein, we sought to explore the possible relationship between AKI and unresolved kidney injury and post-discharge mortality. METHOD: In this cohort study, patients hospitalized with COVID-19 who survived until discharge were followed for a median of 9.6 months. AKI during hospitalization based on the staging according to Kidney Disease: Improving Global Outcomes (KDIGO) criteria and kidney injury status at discharge and other comorbidities and mortality during the follow-up period were recorded. The desired association was investigated using Cox proportional hazards regression after adjustment for potential confounders. RESULT: Among 1,017 discharged patients, 298 patients (29.3%) experienced AKI during hospitalization according to KDIGO criteria, of whom 178 patients (59.7%) were diagnosed with unresolved kidney injury at the time of discharge. After adjusting for potential confounders, Cox regression indicated that AKI stage 3 (hazard ratio (HR): 4.56, 95% confidence interval (CI): 1.89-10.99, p = 0.001) and unresolved kidney injury at the time of discharge (HR: 2.09, 95% CI: 1.18-3.73, p = 0.011) were significantly associated with mortality during the post-discharge period. Additionally, Kaplan-Meier curves for overall survival indicated an increased risk of mortality in patients with stage 2, stage 3 AKI, and unresolved kidney injury at the time of discharge (p < 0.001). CONCLUSION: Overall, it was shown that patients with COVID-19 who develop AKI, mainly stage 2 and 3, and patients with unresolved kidney injury at the time of discharge, were at an increased risk of mortality, even after hospitalization for an extended period of time.

Association of clinical characteristics, antidiabetic and cardiovascular agents with diabetes mellitus and COVID-19: a 7-month follow-up cohort study.

BACKGROUND: The prognostic factors of long-term outcomes in hospitalized patients with diabetes mellitus and COVID-19 are lacking. METHODS: In this retrospective cohort study, we evaluated patients aged ≥ 18-years-old with the COVID-19 diagnosis who were hospitalized between Feb 20 and Oct 29, 2020, in the Sina Hospital, Tehran, Iran. 1323 patients with COVID-19 entered in the final analysis, of whom 393 (29.7%) patients had diabetes. We followed up patients for incurring in-hospital death, severe COVID-19, in-hospital complications, and 7-month all-cause mortality. By doing univariate analysis, variables with unadjusted P-value < 0.1 in univariate analyses were regarded as the confounders to include in the logistic regression models. We made adjustments for possible clinical (model 1) and both clinical and laboratory (model 2) confounders. RESULTS: After multivariable regression, it was revealed that preadmission use of sulfonylureas was associated with a borderline increased risk of severity in both models [model 1, OR (95% CI):1.83 (0.91-3.71), P-value: 0.092; model 2, 2.05 (0.87-4.79), P-value: 0.099] and major adverse events (MAE: each of the severe COVID-19, multi-organ damage, or in-hospital mortality) in model 1 [OR (95% CI): 1.86 (0.90-3.87), P-value: 0.094]. Preadmission use of ACEIs/ARBs was associated with borderline increased risk of MAE in the only model 1 [OR (95% CI):1.83 (0.96-3.48), P-value: 0.066]. CONCLUSIONS: Preadmission use of sulfonylureas and ACEIs/ARBs were associated with borderline increased risk of in-hospital adverse outcomes. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s40200-021-00901-4.

Predicting Risk Score for Mechanical Ventilation in Hospitalized Adult Patients Suffering from COVID-19.

BACKGROUND: COVID-19 has become a pandemic since December 2019, causing millions of deaths worldwide. It has a wide spectrum of severity, ranging from mild infection to severe illness requiring mechanical ventilation. In the middle of a pandemic, when medical resources (including mechanical ventilators) are scarce, there should be a scoring system to provide the clinicians with the information needed for clinical decision-making and resource allocation. OBJECTIVES: This study aimed to develop a scoring system based on the data obtained on admission, to predict the need for mechanical ventilation in COVID-19 patients. METHODS: This study included COVID-19 patients admitted to Sina Hospital, Tehran University of Medical Sciences from February 20 to May 29, 2020. Patients' data on admission were retrospectively recruited from Sina Hospital COVID-19 Registry (SHCo-19R). Multivariable logistic regression and receiver operating characteristic (ROC) curve analysis were performed to identify the predictive factors for mechanical ventilation. RESULTS: A total of 681 patients were included in the study; 74 patients (10.9%) needed mechanical ventilation during hospitalization, while 607 (89.1%) did not. Multivariate logistic analysis revealed that age (OR,1.049; 95% CI:1.008-1.091), history of diabetes mellitus (OR,3.216; 95% CI:1.134-9.120), respiratory rate (OR,1.051; 95% CI:1.005-1.100), oxygen saturation (OR,0.928; 95% CI:0.872-0.989), CRP (OR,1.013; 95% CI:1.001-1.024) and bicarbonate level (OR,0.886; 95% CI:0.790-0.995) were risk factors for mechanical ventilation during hospitalization. CONCLUSIONS: A risk score has been developed based on the available data within the first hours of hospital admission to predict the need for mechanical ventilation. This risk score should be further validated to determine its applicability in other populations.

Clinical significance of prognostic nutrition index in hospitalized patients with COVID-19: Results from single-center experience with systematic review and meta-analysis.

BACKGROUND: We aimed to ascertain risk indicators of in-hospital mortality and severity as well as to provide a comprehensive systematic review and meta-analysis to investigate the prognostic significance of the prognostic nutrition index (PNI) as a predictor of adverse outcomes in hospitalized coronavirus disease 2019 (COVID-19) patients. METHODS: In this cross-sectional study, we studied patients with COVID-19 who were referred to our hospital from February 16 to November 1, 2020. Patients with either a real-time reverse-transcriptase polymerase chain reaction test that was positive for COVID-19 or high clinical suspicion based on the World Health Organization (WHO) interim guidance were enrolled. A parallel systematic review/meta-analysis (in PubMed, Embase, and Web of Science) was performed. RESULTS: A total of 504 hospitalized COVID-19 patients were included in this study, among which 101 (20.04%) patients died during hospitalization, and 372 (73.81%) patients were categorized as severe cases. At a multivariable level, lower PNI, higher lactate dehydrogenase (LDH), and higher D-dimer levels were independent risk indicators of in-hospital mortality. Additionally, patients with a history of diabetes, lower PNI, and higher LDH levels had a higher tendency to develop severe disease. The meta-analysis indicated the PNI as an independent predictor of in-hospital mortality (odds ratio [OR] = 0.80; P < .001) and disease severity (OR = 0.78; P = .009). CONCLUSION: Our results emphasized the predictive value of the PNI in the prognosis of patients with COVID-19, necessitating the implementation of a risk stratification index based on PNI values in hospitalized patients with COVID-19.

The Risk Factors and Clinical Outcomes Associated with Acute Kidney Injury in Patients with COVID-19: Data from a Large Cohort in Iran.

INTRODUCTION: Kidney involvement, ranging from mild hematuria and proteinuria to acute kidney injury (AKI) in patients with coronavirus disease-2019 (COVID-19), is a recent finding with various incidence rates reported among hospitalized patients with COVID-19. Given the various AKI rates and their associated risk factors, lack of AKI recovery in the majority of patients hospitalized with COVID-19, and limited data regarding AKI in patients with COVID-19 in Iran, we aim to investigate the potential risk factors for AKI development and its incidence in patients hospitalized with COVID-19. METHODS: In this retrospective cohort study, we enrolled adult patients referred to the Sina Hospital, Iran, from February 20 to May 14, 2020, with either a positive PCR test or a highly susceptible chest computed tomography features consistent with COVID-19 diagnosis. AKI was defined according to the kidney disease improving global outcomes criteria, and patients were stratified based on their AKI staging. We evaluated the risk indicators associated with AKI during hospitalization besides in-hospital outcomes and recovery rate at the time of discharge. RESULTS: We evaluated 516 patients with a mean age of 57.6 ± 16.1 years and a male-to-female ratio of 1.69 who were admitted with the COVID-19 diagnosis. AKI development was observed among 194 (37.6%) patients, comprising 61.9% patients in stage 1, 18.0% in stage 2, and 20.1% in stage 3. Out of all patients, AKI occurred in 58 (11.2%) patients during the hospital course, and 136 (26.3%) patients arrived with AKI upon admission. AKI development was positively associated with all of the in-hospital outcomes, including intensive care unit admissions, need for invasive ventilation, acute respiratory distress syndrome (ARDS), acute cardiac injury, acute liver injury, multiorgan damage, and mortality. Patients with stage 3 AKI showed a significantly higher mortality rate, ARDS, and need for invasive ventilation than other stages. After multivariable analysis, male sex (odds ratio [OR]: 11.27), chronic kidney disease (CKD) (OR: 6.89), history of hypertension (OR: 1.69), disease severity (OR: 2.27), and high urea levels (OR: 1.04) on admission were independent risk indicators of AKI development. Among 117 (28.1%) patients who experienced AKI and survived, only 33 (28.2%) patients made a recovery from the AKI, and 84 (71.8%) patients did not exhibit full recovery at the time of discharge. DISCUSSION/CONCLUSION: We found that male sex, history of CKD, hypertension, disease severity, and high serum urea were independent risk factors associated with AKI in patients with COVID-19. Also, higher stages of AKI were associated with increased risk of mortality and in-hospital complications. Our results indicate a necessity for more precise care and monitoring for AKI during hospitalization in patients with COVID-19, and lack of AKI recovery at the time of discharge is a common complication in such patients.

Risk indicators associated with in-hospital mortality and severity in patients with diabetes mellitus and confirmed or clinically suspected COVID-19.

PURPOSE: This study aims to investigate risk indicators of in-hospital mortality and severity of coronavirus disease-2019 (COVID-19) in patients with diabetes mellitus (DM). METHODS: In this retrospective study, we studied patients with COVID-19 referred to Sina Hospital, Tehran, Iran, from February 20 to May 14, 2020. Patients with either a positive real-time reverse-transcriptase polymerase-chain-reaction test of swab specimens or high clinical suspicion according to the World Health Organization interim guidance were included. We accurately divided all patients into two groups based on diabetes affection and followed-up patients with DM based on incurring death, severe COVID-19, and in-hospital complications. RESULTS: We enrolled 574 patients with COVID-19 in the final analysis, of whom 176 (30.7%) patients had DM. In this study, 104 (18.1%) patients deceased, and 380 (66.2%) patients incurred severe COVID-19. We found that COVID-19 patients with DM had a significantly higher mortality rate (P value<0.001), severe disease (P value<0.001), and in-hospital complications (all P values<0.05). Besides that, in patients with DM, admission temperature (odds ratio (OR): 1.69, P value: 0.024), oxygen saturation (OR: 0.92, P value: 0.004), and urea (OR: 1.01, P value: 0.048) were independent risk indicators of in-hospital mortality. In addition, subgroup analysis of diabetic patients based on admission glucose level showed significant differences between these groups regarding acute cardiac injury (P value: 0.044) and acute liver injury (P value: 0.002). CONCLUSIONS: Patients with DM admitted with lower oxygen saturation, elevated temperature, and higher urea are more susceptible to progress to more severe COVID-19 and poor prognosis. This indicates a necessity for more precise care during hospitalization for these patients. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s40200-020-00701-2.

Vitamin D sufficiency, a serum 25-hydroxyvitamin D at least 30 ng/mL reduced risk for adverse clinical outcomes in patients with COVID-19 infection.

BACKGROUND: To investigate the association between serum 25-hydroxyvitamin D levels and its effect on adverse clinical outcomes, and parameters of immune function and mortality due to a SARS-CoV-2 infection. STUDY DESIGN: The hospital data of 235 patients infected with COVID-19 were analyzed. RESULTS: Based on CDC criteria, among our study patients, 74% had severe COVID-19 infection and 32.8% were vitamin D sufficient. After adjusting for confounding factors, there was a significant association between vitamin D sufficiency and reduction in clinical severity, inpatient mortality serum levels of C-reactive protein (CRP) and an increase in lymphocyte percentage. Only 9.7% of patients older than 40 years who were vitamin D sufficient succumbed to the infection compared to 20% who had a circulating level of 25(OH)D< 30 ng/ml. The significant reduction in serum CRP, an inflammatory marker, along with increased lymphocytes percentage suggest that vitamin D sufficiency also may help modulate the immune response possibly by reducing risk for cytokine storm in response to this viral infection. CONCLUSION: Therefore, it is recommended that improving vitamin D status in the general population and in particular hospitalized patients has a potential benefit in reducing the severity of morbidities and mortality associated with acquiring COVID-19.

The frequency of metabolic syndrome in women with rheumatoid arthritis and in controls.

AIM: To compare the frequency of the metabolic syndrome and its components in a sample of patients with rheumatoid arthritis (RA) and controls. METHODS: This case control study was performed on 188 women over 18 years old: 92 RA patients and 96 healthy controls, from 2006 to 2008. Blood pressure, height, weight and waist circumference were measured. Blood was collected for the measurement of fasting glucose, lipid profile and insulin. The frequency of the metabolic syndrome was determined in case and control groups, using both WHO and National Cholesterol Education Program Adult Treatment Panel III (NCEP-ATP III) criteria. RESULTS: According to the NCEP criteria, the frequency of metabolic syndrome in RA patients and controls were 27.2% and 35.4%, respectively (P = 0.22). Based on WHO criteria, 19.6% of RA patients and 21.9% of the control group were subject to metabolic syndrome (P = 0.70). The proportion with hypertension was greater in RA patients than the control group. The duration of RA was significantly higher in patients with metabolic syndrome compared to those without metabolic syndrome using both the WHO and NCEP criteria. CONCLUSIONS: There was no evidence of a greater prevalence of metabolic syndrome in RA patients compared with controls in this study. The duration of RA was associated with metabolic syndrome, implicating the role of inflammation in metabolic syndrome development.