Deep Learning-Based Automatic Assessment of Lung Impairment in COVID-19 Pneumonia: Predicting Markers of Hypoxia With Computer Vision.

Background: Hypoxia is a potentially life-threatening condition that can be seen in pneumonia patients. Objective: We aimed to develop and test an automatic assessment of lung impairment in COVID-19 associated pneumonia with machine learning regression models that predict markers of respiratory and cardiovascular functioning from radiograms and lung CT. Materials and Methods: We enrolled a total of 605 COVID-19 cases admitted to Al Ain Hospital from 24 February to 1 July 2020 into the study. The inclusion criteria were as follows: age ≥ 18 years; inpatient admission; PCR positive for SARS-CoV-2; lung CT available at PACS. We designed a CNN-based regression model to predict systemic oxygenation markers from lung CT and 2D diagnostic images of the chest. The 2D images generated by averaging CT scans were analogous to the frontal and lateral view radiograms. The functional (heart and breath rate, blood pressure) and biochemical findings (SpO2, H C O 3 - , K +, Na +, anion gap, C-reactive protein) served as ground truth. Results: Radiologic findings in the lungs of COVID-19 patients provide reliable assessments of functional status with clinical utility. If fed to ML models, the sagittal view radiograms reflect dyspnea more accurately than the coronal view radiograms due to the smaller size and the lower model complexity. Mean absolute error of the models trained on single-projection radiograms was approximately 11÷12% and it dropped by 0.5÷1% if both projections were used (11.97 ± 9.23 vs. 11.43 ± 7.51%; p = 0.70). Thus, the ML regression models based on 2D images acquired in multiple planes had slightly better performance. The data blending approach was as efficient as the voting regression technique: 10.90 ± 6.72 vs. 11.96 ± 8.30%, p = 0.94. The models trained on 3D images were more accurate than those on 2D: 8.27 ± 4.13 and 11.75 ± 8.26%, p = 0.14 before lung extraction; 10.66 ± 5.83 and 7.94 ± 4.13%, p = 0.18 after the extraction. The lung extraction boosts 3D model performance unsubstantially (from 8.27 ± 4.13 to 7.94 ± 4.13%; p = 0.82). However, none of the differences between 3D and 2D were statistically significant. Conclusion: The constructed ML algorithms can serve as models of structure-function association and pathophysiologic changes in COVID-19. The algorithms can improve risk evaluation and disease management especially after oxygen therapy that changes functional findings. Thus, the structural assessment of acute lung injury speaks of disease severity.

Ethnicity-Specific Features of COVID-19 Among Arabs, Africans, South Asians, East Asians, and Caucasians in the United Arab Emirates.

Background: Dubai (United Arab Emirates; UAE) has a multi-national population which makes it exceptionally interesting study sample because of its unique demographic factors. Objective: To stratify the risk factors for the multinational society of the UAE. Methods: A retrospective chart review of 560 patients sequentially admitted to inpatient care with laboratory confirmed COVID-19 was conducted. We studied patients' demographics, clinical features, laboratory results, disease severity, and outcomes. The parameters were compared across different ethnic groups using tree-based estimators to rank the ethnicity-specific disease features. We trained ML classification algorithms to build a model of ethnic specificity of COVID-19 based on clinical presentation and laboratory findings on admission. Results: Out of 560 patients, 43.6% were South Asians, 26.4% Middle Easterns, 16.8% East Asians, 10.7% Caucasians, and 2.5% are under others. UAE nationals represented half of the Middle Eastern patients, and 13% of the entire cohort. Hypertension was the most common comorbidity in COVID-19 patients. Subjective complaint of fever and cough were the chief presenting symptoms. Two-thirds of the patients had either a mild disease or were asymptomatic. Only 20% of the entire cohort needed oxygen therapy, and 12% needed ICU admission. Forty patients (~7%) needed invasive ventilation and fifteen patients died (2.7%). We observed differences in disease severity among different ethnic groups. Caucasian or East-Asian COVID-19 patients tended to have a more severe disease despite a lower risk profile. In contrast to this, Middle Eastern COVID-19 patients had a higher risk factor profile, but they did not differ markedly in disease severity from the other ethnic groups. There was no noticeable difference between the Middle Eastern subethnicities-Arabs and Africans-in disease severity (p = 0.81). However, there were disparities in the SOFA score, D-dimer (p = 0.015), fibrinogen (p = 0.007), and background diseases (hypertension, p = 0.003; diabetes and smoking, p = 0.045) between the subethnicities. Conclusion: We observed variations in disease severity among different ethnic groups. The high accuracy (average AUC = 0.9586) of the ethnicity classification model based on the laboratory and clinical findings suggests the presence of ethnic-specific disease features. Larger studies are needed to explore the role of ethnicity in COVID-19 disease features.

Impact of Age and Sex on COVID-19 Severity Assessed From Radiologic and Clinical Findings.

Background: Data on the epidemiological characteristics and clinical features of COVID-19 in patients of different ages and sex are limited. Existing studies have mainly focused on the pediatric and elderly population. Objective: Assess whether age and sex interact with other risk factors to influence the severity of SARS-CoV-2 infection. Material and Methods: The study sample included all consecutive patients who satisfied the inclusion criteria and who were treated from 24 February to 1 July 2020 in Dubai Mediclinic Parkview (560 cases) and Al Ain Hospital (605 cases), United Arab Emirates. We compared disease severity estimated from the radiological findings among patients of different age groups and sex. To analyze factors associated with an increased risk of severe disease, we conducted uni- and multivariate regression analyses. Specifically, age, sex, laboratory findings, and personal risk factors were used to predict moderate and severe COVID-19 with conventional machine learning methods. Results: Need for O2 supplementation was positively correlated with age. Intensive care was required more often for men of all ages (p < 0.01). Males were more likely to have at least moderate disease severity (p = 0.0083). These findings were aligned with the results of biochemical findings and suggest a direct correlation between older age and male sex with a severe course of the disease. In young males (18-39 years), the percentage of the lung parenchyma covered with consolidation and the density characteristics of lesions were higher than those of other age groups; however, there was no marked sex difference in middle-aged (40-64 years) and older adults (≥65 years). From the univariate analysis, the risk of the non-mild COVID-19 was significantly higher (p < 0.05) in midlife adults and older adults compared to young adults. The multivariate analysis provided similar findings. Conclusion: Age and sex were important predictors of disease severity in the set of data typically collected on admission. Sexual dissimilarities reduced with age. Age disparities were more pronounced if studied with the clinical markers of disease severity than with the radiological markers. The impact of sex on the clinical markers was more evident than that of age in our study.

AI applications in robotics, precision medicine, and medical image analysis: an overview and future trends

Background

Prediction of COVID-19 severity using laboratory findings on admission: informative values, thresholds, ML model performance.

BACKGROUND: Despite the necessity, there is no reliable biomarker to predict disease severity and prognosis of patients with COVID-19. The currently published prediction models are not fully applicable to clinical use. OBJECTIVES: To identify predictive biomarkers of COVID-19 severity and to justify their threshold values for the stratification of the risk of deterioration that would require transferring to the intensive care unit (ICU). METHODS: The study cohort (560 subjects) included all consecutive patients admitted to Dubai Mediclinic Parkview Hospital from February to May 2020 with COVID-19 confirmed by the PCR. The challenge of finding the cut-off thresholds was the unbalanced dataset (eg, the disproportion in the number of 72 patients admitted to ICU vs 488 non-severe cases). Therefore, we customised supervised machine learning (ML) algorithm in terms of threshold value used to predict worsening. RESULTS: With the default thresholds returned by the ML estimator, the performance of the models was low. It was improved by setting the cut-off level to the 25th percentile for lymphocyte count and the 75th percentile for other features. The study justified the following threshold values of the laboratory tests done on admission: lymphocyte count <2.59×109/L, and the upper levels for total bilirubin 11.9 µmol/L, alanine aminotransferase 43 U/L, aspartate aminotransferase 32 U/L, D-dimer 0.7 mg/L, activated partial thromboplastin time (aPTT) 39.9 s, creatine kinase 247 U/L, C reactive protein (CRP) 14.3 mg/L, lactate dehydrogenase 246 U/L, troponin 0.037 ng/mL, ferritin 498 ng/mL and fibrinogen 446 mg/dL. CONCLUSION: The performance of the neural network trained with top valuable tests (aPTT, CRP and fibrinogen) is admissible (area under the curve (AUC) 0.86; 95% CI 0.486 to 0.884; p<0.001) and comparable with the model trained with all the tests (AUC 0.90; 95% CI 0.812 to 0.902; p<0.001). Free online tool at https://med-predict.com illustrates the study results.