Comparing machine learning algorithms to predict COVID­19 mortality using a dataset including chest computed tomography severity score data.

Since the beginning of the COVID-19 pandemic, new and non-invasive digital technologies such as artificial intelligence (AI) had been introduced for mortality prediction of COVID-19 patients. The prognostic performances of the machine learning (ML)-based models for predicting clinical outcomes of COVID-19 patients had been mainly evaluated using demographics, risk factors, clinical manifestations, and laboratory results. There is a lack of information about the prognostic role of imaging manifestations in combination with demographics, clinical manifestations, and laboratory predictors. The purpose of the present study is to develop an efficient ML prognostic model based on a more comprehensive dataset including chest CT severity score (CT-SS). Fifty-five primary features in six main classes were retrospectively reviewed for 6854 suspected cases. The independence test of Chi-square was used to determine the most important features in the mortality prediction of COVID-19 patients. The most relevant predictors were used to train and test ML algorithms. The predictive models were developed using eight ML algorithms including the J48 decision tree (J48), support vector machine (SVM), multi-layer perceptron (MLP), k-nearest neighbourhood (k-NN), Naïve Bayes (NB), logistic regression (LR), random forest (RF), and eXtreme gradient boosting (XGBoost). The performances of the predictive models were evaluated using accuracy, precision, sensitivity, specificity, and area under the ROC curve (AUC) metrics. After applying the exclusion criteria, a total of 815 positive RT-PCR patients were the final sample size, where 54.85% of the patients were male and the mean age of the study population was 57.22 ± 16.76 years. The RF algorithm with an accuracy of 97.2%, the sensitivity of 100%, a precision of 94.8%, specificity of 94.5%, F1-score of 97.3%, and AUC of 99.9% had the best performance. Other ML algorithms with AUC ranging from 81.2 to 93.9% had also good prediction performances in predicting COVID-19 mortality. Results showed that timely and accurate risk stratification of COVID-19 patients could be performed using ML-based predictive models fed by routine data. The proposed algorithm with the more comprehensive dataset including CT-SS could efficiently predict the mortality of COVID-19 patients. This could lead to promptly targeting high-risk patients on admission, the optimal use of hospital resources, and an increased probability of survival of patients.

How long is too long: A retrospective study evaluating the impact of the duration of noninvasive oxygenation support strategies (high flow nasal cannula & BiPAP) on mortality in invasive mechanically ventilated patients with COVID-19.

BACKGROUND/AIM: We investigated the association of noninvasive oxygenation support [high flow nasal cannula (HFNC) and BiPAP], timing of invasive mechanical ventilation (IMV), and inpatient mortality among patients hospitalized with COVID-19. METHODS: Retrospective chart review study of patients hospitalized with COVID-19 (ICD-10 code U07.1) and received IMV from March 2020-October 2021. Charlson comorbidity index (CCI) was calculated; Obesity defined as body mass index (BMI) ≥ 30 kg/m2; morbid obesity was BMI ≥ 40 kg/m2. Clinical parameters/vital signs recorded at time of admission. RESULTS: 709 COVID-19 patients underwent IMV, predominantly admitted from March-May 2020 (45%), average age 62±15 years, 67% male, 37% Hispanic, and 9% from group living settings. 44% had obesity, 11% had morbid obesity, 55% had type II diabetes, 75% had hypertension, and average CCI was 3.65 (SD = 3.11). Crude mortality rate was 56%. Close linear association of age with inpatient-mortality risk was found [OR (95% CI) = 1.35 (1.27-1.44) per 5 years, p<0.0001)]. Patients who died after IMV received noninvasive oxygenation support significantly longer: 5.3 (8.0) vs. 2.7 (SD 4.6) days; longer use was also independently associated with a higher risk of inpatient-mortality: OR = 3.1 (1.8-5.4) for 3-7 days, 7.2 (3.8-13.7) for ≥8 days (reference: 1-2 days) (p<0.0001). The association magnitude varied between age groups: 3-7 days duration (ref: 1-2 days), OR = 4.8 (1.9-12.1) in ≥65 years old vs. 2.1 (1.0-4.6) in <65 years old. Higher mortality risk was associated with higher CCI in patients ≥65 (P = 0.0082); among younger patients, obesity (OR = 1.8 (1.0-3.2) or morbid obesity (OR = 2.8;1.4-5.9) (p<0.05) were associated. No mortality association was found for sex or race. CONCLUSION: Time spent on noninvasive oxygenation support [as defined by high flow nasal cannula (HFNC) and BiPAP] prior to IMV increased mortality risk. Research for the generalizability of our findings to other respiratory failure patient populations is needed.

Association of chest CT severity score with mortality of COVID-19 patients: a systematic review and meta-analysis.

Purpose: Chest computed tomography (CT) is a high-sensitivity diagnostic tool for depicting interstitial pneumonia and may lay a critical role in the evaluation of the severity and extent of pulmonary involvement. In this study, we aimed to evaluate the association of chest CT severity score (CT-SS) with the mortality of COVID-19 patients using systematic review and meta-analysis. Methods: Web of Science, PubMed, Embase, Scopus, and Google Scholar were used to search for primary articles. The meta-analysis was performed using the random-effects model, and odds ratios (ORs) with 95% confidence intervals (95%CIs) were calculated as the effect sizes. Results: This meta-analysis retrieved a total number of 7106 COVID-19 patients. The pooled estimate for the association of CT-SS with mortality of COVID-19 patients was calculated as 1.244 (95% CI 1.157-1.337). The pooled estimate for the association of CT-SS with an optimal cutoff and mortality of COVID-19 patients was calculated as 7.124 (95% CI 5.307-9.563). There was no publication bias in the results of included studies. Radiologist experiences and study locations were not potential sources of between-study heterogeneity (both P > 0.2). The shapes of Begg's funnel plots seemed symmetrical for studies evaluating the association of CT-SS with/without the optimal cutoffs and mortality of COVID-19 patients (Begg's test P = 0.945 and 0.356, respectively). Conclusions: The results of this study point to an association between CT-SS and mortality of COVID-19 patients. The odds of mortality for COVID-19 patients could be accurately predicted using an optimal CT-SS cutoff in visual scoring of lung involvement.

Hypoxic Respiratory Failure Further Complicated During Airway Exchange Catheter Placement.

INTRODUCTION: An airway exchange catheter is a hollow-lumen tube able to deliver oxygen and maintain access to a difficult endotracheal airway. This case report demonstrates an undocumented complication associated with an airway exchange catheter and jet ventilation, particularly in a patient with reduced airway diameter due to thick endotracheal secretions. Due to the frequent use of airway exchange catheters in the intensive care unit, this report highlights an adverse event of bilateral pneumothoraces that can be encountered by clinicians. CASE PRESENTATION: This case report describes a 24-year-old female with severe adult respiratory distress syndrome and thick endotra-cheal secretions whose hospital course was complicated by bilateral pneumothoraces resulting from the use of an airway exchange catheter connected to jet ventilation. During the exchange, the catheter occluded the narrowed endotracheal tube to create a one-way valve that led to excessive lung inflation. CONCLUSION: Airway exchange catheters used with jet ventilation in a patient with a narrowed endotracheal tube and reduced lung compliance have the potential risk of causing a pneumothorax. Clinicians should avoid temporary concomitant oxygenation via jet ventilation in patients with these findings and reserve the use of airway exchange catheters for difficult airways.

The Protective Role of Gallic Acid Pretreatment On Renal Ischemia-reperfusion Injury in Rats.

BACKGROUND: Renal ischemia-reperfusion injury (RIR) occurs when there is a temporary restriction of blood flow to the kidneys followed by an influx of blood, re-oxygenating the tissues. This occurs as a severe complication of major surgery. This process causes significant damage to the tissues and is responsible for the development of acute kidney injury (AKI), a life-threatening condition with high mortality rates. Here, we evaluated the potential protective effects of the antioxidant, gallic acid (GA), on RIR in an in vivo rat model. METHODS: Adult male Sprague Dawley rats were randomly divided into three groups: group 1 (control, n = 8), group 2 (Ischemia-reperfusion (IR) with no-treatment, n = 7), and group 3 (IR + daily GA 100 mg/kg i.p, n = 7). The abdomens of the rats in the control group were opened during the surgical procedure, then sutured closed. GA pretreatment began daily 15 days prior to inducing RIR. To induce RIR, the umbilical arteries were obstructed on both sides and clamped with mild pressure for 45 min. Following the 45 min ischemia, the clamps were removed to allow for the induction of reperfusion. The reperfusion phase was 24 hours. RESULTS: Following IR, the serum levels of urea and creatinine significantly increased compared to the controls. Pretreatment with GA was observed to reduce urea and creatinine levels following IR. However, this decrease was not statistically significant. The serum and renal levels of malondialdehyde (MDA) in the IR group was significantly elevated compared to the control group. Conversely, glutathione (GSH) levels and the activity of glutathione peroxidase (GPX) significantly decreased in the IR group compared to controls. Our findings show GA pretreatment to significantly improve the levels of renal MDA, serum GSH, and GPX activity following RIR. CONCLUSION: Our findings highlight the protective role for GA in mitigating the damage caused by RIR and its applications as a potential treatment.