Longitudinal Chest X-ray Scores and their Relations with Clinical Variables and Outcomes in COVID-19 Patients.

Background: This study evaluated the temporal characteristics of lung chest X-ray (CXR) scores in COVID-19 patients during hospitalization and how they relate to other clinical variables and outcomes (alive or dead). Methods: This is a retrospective study of COVID-19 patients. CXR scores of disease severity were analyzed for: (i) survivors (N = 224) versus non-survivors (N = 28) in the general floor group, and (ii) survivors (N = 92) versus non-survivors (N = 56) in the invasive mechanical ventilation (IMV) group. Unpaired t-tests were used to compare survivors and non-survivors and between time points. Comparison across multiple time points used repeated measures ANOVA and corrected for multiple comparisons. Results: For general-floor patients, non-survivor CXR scores were significantly worse at admission compared to those of survivors (p < 0.05), and non-survivor CXR scores deteriorated at outcome (p < 0.05) whereas survivor CXR scores did not (p > 0.05). For IMV patients, survivor and non-survivor CXR scores were similar at intubation (p > 0.05), and both improved at outcome (p < 0.05), with survivor scores showing greater improvement (p < 0.05). Hospitalization and IMV duration were not different between groups (p > 0.05). CXR scores were significantly correlated with lactate dehydrogenase, respiratory rate, D-dimer, C-reactive protein, procalcitonin, ferritin, SpO2, and lymphocyte count (p < 0.05). Conclusions: Longitudinal CXR scores have the potential to provide prognosis, guide treatment, and monitor disease progression.

Deep learning of longitudinal chest X-ray and clinical variables predicts duration on ventilator and mortality in COVID-19 patients.

OBJECTIVES: To use deep learning of serial portable chest X-ray (pCXR) and clinical variables to predict mortality and duration on invasive mechanical ventilation (IMV) for Coronavirus disease 2019 (COVID-19) patients. METHODS: This is a retrospective study. Serial pCXR and serial clinical variables were analyzed for data from day 1, day 5, day 1-3, day 3-5, or day 1-5 on IMV (110 IMV survivors and 76 IMV non-survivors). The outcome variables were duration on IMV and mortality. With fivefold cross-validation, the performance of the proposed deep learning system was evaluated by receiver operating characteristic (ROC) analysis and correlation analysis. RESULTS: Predictive models using 5-consecutive-day data outperformed those using 3-consecutive-day and 1-day data. Prediction using data closer to the outcome was generally better (i.e., day 5 data performed better than day 1 data, and day 3-5 data performed better than day 1-3 data). Prediction performance was generally better for the combined pCXR and non-imaging clinical data than either alone. The combined pCXR and non-imaging data of 5 consecutive days predicted mortality with an accuracy of 85 ± 3.5% (95% confidence interval (CI)) and an area under the curve (AUC) of 0.87 ± 0.05 (95% CI) and predicted the duration needed to be on IMV to within 2.56 ± 0.21 (95% CI) days on the validation dataset. CONCLUSIONS: Deep learning of longitudinal pCXR and clinical data have the potential to accurately predict mortality and duration on IMV in COVID-19 patients. Longitudinal pCXR could have prognostic value if these findings can be validated in a large, multi-institutional cohort.

Survival of COVID-19 Patients With Respiratory Failure is Related to Temporal Changes in Gas Exchange and Mechanical Ventilation.

Background: Respiratory failure due to coronavirus disease of 2019 (COVID-19) often presents with worsening gas exchange over a period of days. Once patients require mechanical ventilation (MV), the temporal change in gas exchange and its relation to clinical outcome is poorly described. We investigated whether gas exchange over the first 5 days of MV is associated with mortality and ventilator-free days at 28 days in COVID-19. Methods: In a cohort of 294 COVID-19 patients, we used data during the first 5 days of MV to calculate 4 daily respiratory scores: PaO2/FiO2 (P/F), oxygenation index (OI), ventilatory ratio (VR), and Murray lung injury score. The association between these scores at early (days 1-3) and late (days 4-5) time points with mortality was evaluated using logistic regression, adjusted for demographics. Correlation with ventilator-free days was assessed (Spearman rank-order coefficients). Results: Overall mortality was 47.6%. Nonsurvivors were older (P < .0001), more male (P = .029), with more preexisting cardiopulmonary disease compared to survivors. Mean PaO2 and PaCO2 were similar during this timeframe. However, by days 4 to 5 values for all airway pressures and FiO2 had diverged, trending lower in survivors and higher in nonsurvivors. The most substantial between-group difference was the temporal change in OI, improving 15% in survivors and worsening 11% in nonsurvivors (P < .05). The adjusted mortality OR was significant for age (1.819, P = .001), OI at days 4 to 5 (2.26, P = .002), and OI percent change (1.90, P = .02). The number of ventilator-free days correlated significantly with late VR (-0.166, P < .05), early and late OI (-0.216, P < .01; -0.278, P < .01, respectively) and early and late P/F (0.158, P < .05; 0.283, P < .01, respectively). Conclusion: Nonsurvivors of COVID-19 needed increasing intensity of MV to sustain gas exchange over the first 5 days, unlike survivors. Temporal change OI, reflecting both PaO2 and the intensity of MV, is a potential marker of outcome in respiratory failure due to COVID-19.

Time-to-Death Longitudinal Characterization of Clinical Variables and Longitudinal Prediction of Mortality in COVID-19 Patients: A Two-Center Study.

Objectives: To characterize the temporal characteristics of clinical variables with time lock to mortality and build a predictive model of mortality associated with COVID-19 using clinical variables. Design: Retrospective cohort study of the temporal characteristics of clinical variables with time lock to mortality. Setting: Stony Brook University Hospital (New York) and Tongji Hospital. Patients: Patients with confirmed positive for severe acute respiratory syndrome coronavirus-2 using polymerase chain reaction testing. Patients from the Stony Brook University Hospital data were used for training (80%, N = 1,002) and testing (20%, N = 250), and 375 patients from the Tongji Hospital (Wuhan, China) data were used for testing. Intervention: None. Measurements and Main Results: Longitudinal clinical variables were analyzed as a function of days from outcome with time-lock-to-day of death (non-survivors) or discharge (survivors). A predictive model using the significant earliest predictors was constructed. Performance was evaluated using receiver operating characteristics area under the curve (AUC). The predictive model found lactate dehydrogenase, lymphocytes, procalcitonin, D-dimer, C-reactive protein, respiratory rate, and white-blood cells to be early predictors of mortality. The AUC for the zero to 9 days prior to outcome were: 0.99, 0.96, 0.94, 0.90, 0.82, 0.75, 0.73, 0.77, 0.79, and 0.73, respectively (Stony Brook Hospital), and 1.0, 0.86, 0.88, 0.96, 0.91, 0.62, 0.67, 0.50, 0.63, and 0.57, respectively (Tongji Hospital). In comparison, prediction performance using hospital admission data was poor (AUC = 0.59). Temporal fluctuations of most clinical variables, indicative of physiological and biochemical instability, were markedly higher in non-survivors compared to survivors (p < 0.001). Conclusion: This study identified several clinical markers that demonstrated a temporal progression associated with mortality. These variables accurately predicted death within a few days prior to outcome, which provides objective indication that closer monitoring and interventions may be needed to prevent deterioration.

Machining learning predicts the need for escalated care and mortality in COVID-19 patients from clinical variables.

Objective: This study aimed to develop a machine learning algorithm to identify key clinical measures to triage patients more effectively to general admission versus intensive care unit (ICU) admission and to predict mortality in COVID-19 pandemic. Materials and methods: This retrospective study consisted of 1874 persons-under-investigation for COVID-19 between February 7, 2020, and May 27, 2020 at Stony Brook University Hospital, New York. Two primary outcomes were ICU admission and mortality compared to COVID-19 positive patients in general hospital admission. Demographic, vitals, symptoms, imaging findings, comorbidities, and laboratory tests at presentation were collected. Predictions of mortality and ICU admission were made using machine learning with 80% training and 20% testing. Performance was evaluated using receiver operating characteristic (ROC) area under the curve (AUC). Results: A total of 635 patients were included in the analysis (age 60±11, 40.2% female). The top 6 mortality predictors were age, procalcitonin, C-creative protein, lactate dehydrogenase, D-dimer and lymphocytes. The top 6 ICU admission predictors are procalcitonin, lactate dehydrogenase, C-creative protein, pulse oxygen saturation, temperature and ferritin. The best machine learning algorithms predicted mortality with 89% AUC and ICU admission with 79% AUC. Conclusion: This study identifies key independent clinical parameters that predict ICU admission and mortality associated with COVID-19 infection. The predictive model is practical, readily enhanced and retrained using additional data. This approach has immediate translation and may prove useful for frontline physicians in clinical decision making under time-sensitive and resource-constrained environment.

Cytokines and their relationship with the severity and prognosis of coronavirus disease 2019 (COVID-19): a retrospective cohort study.

OBJECTIVE: To delineate the characteristics and clinical significance of plasma inflammatory cytokines altered in COVID-19. DESIGN: Retrospective, single-centre cohort study. SETTING: Tongji Hospital in Wuhan, China. PARTICIPANTS: Among a cohort of 308 patients with a diagnosis of COVID-19, 138 patients died while 170 patients recovered and were discharged from the hospital. The data were collected until 27 February 2020. PRIMARY AND SECONDARY OUTCOME MEASURES: Clinical characteristics and laboratory findings were obtained from electronic medical records using data collection forms. RESULTS: The percentage of patients with elevated interleukin 2 receptor (IL-2R), IL-6, IL-8, IL-10 and tumour necrosis factor (TNF) increased with severity of disease (p<0.0001 for all). IL-2R (p<0.0001), IL-6 (p<0.0001), IL-8 (p=0.0001), IL-10 (p<0.0001) and TNF (p<0.0001) were also twofold to 20-fold higher in patients who died compared with those who recovered. Also, IL-6 and IL-10 increased in both the progressive patient groups: moderate (p=0.0026) and severe (p<0.0001). In multivariate analysis, higher levels of IL-2R (OR 1.001, 95% CI 1.000 to 1.002, p=0.031) and IL-6 (OR 1.013, 95% CI 1.003 to 1.024, p=0.015) on admission were associated with increasing odds of in-hospital death, independent of other covariates, including severity of disease and lymphocyte count. CONCLUSION: Increased proinflammatory and anti-inflammatory cytokines, including IL-2R, IL-6, IL-8, TNF and IL-10, showed an obvious association with both COVID-19 severity and in-hospital mortality. Thus, our study indicates that cytokines are valuable in predicting the severity of COVID-19 and helps in distinguishing critically ill patients from the less affected ones.

Machine-learning classification of texture features of portable chest X-ray accurately classifies COVID-19 lung infection.

BACKGROUND: The large volume and suboptimal image quality of portable chest X-rays (CXRs) as a result of the COVID-19 pandemic could post significant challenges for radiologists and frontline physicians. Deep-learning artificial intelligent (AI) methods have the potential to help improve diagnostic efficiency and accuracy for reading portable CXRs. PURPOSE: The study aimed at developing an AI imaging analysis tool to classify COVID-19 lung infection based on portable CXRs. MATERIALS AND METHODS: Public datasets of COVID-19 (N = 130), bacterial pneumonia (N = 145), non-COVID-19 viral pneumonia (N = 145), and normal (N = 138) CXRs were analyzed. Texture and morphological features were extracted. Five supervised machine-learning AI algorithms were used to classify COVID-19 from other conditions. Two-class and multi-class classification were performed. Statistical analysis was done using unpaired two-tailed t tests with unequal variance between groups. Performance of classification models used the receiver-operating characteristic (ROC) curve analysis. RESULTS: For the two-class classification, the accuracy, sensitivity and specificity were, respectively, 100%, 100%, and 100% for COVID-19 vs normal; 96.34%, 95.35% and 97.44% for COVID-19 vs bacterial pneumonia; and 97.56%, 97.44% and 97.67% for COVID-19 vs non-COVID-19 viral pneumonia. For the multi-class classification, the combined accuracy and AUC were 79.52% and 0.87, respectively. CONCLUSION: AI classification of texture and morphological features of portable CXRs accurately distinguishes COVID-19 lung infection in patients in multi-class datasets. Deep-learning methods have the potential to improve diagnostic efficiency and accuracy for portable CXRs.

Deep learning prediction of likelihood of ICU admission and mortality in COVID-19 patients using clinical variables.

BACKGROUND: This study aimed to develop a deep-learning model and a risk-score system using clinical variables to predict intensive care unit (ICU) admission and in-hospital mortality in COVID-19 patients. METHODS: This retrospective study consisted of 5,766 persons-under-investigation for COVID-19 between 7 February 2020 and 4 May 2020. Demographics, chronic comorbidities, vital signs, symptoms and laboratory tests at admission were collected. A deep neural network model and a risk-score system were constructed to predict ICU admission and in-hospital mortality. Prediction performance used the receiver operating characteristic area under the curve (AUC). RESULTS: The top ICU predictors were procalcitonin, lactate dehydrogenase, C-reactive protein, ferritin and oxygen saturation. The top mortality predictors were age, lactate dehydrogenase, procalcitonin, cardiac troponin, C-reactive protein and oxygen saturation. Age and troponin were unique top predictors for mortality but not ICU admission. The deep-learning model predicted ICU admission and mortality with an AUC of 0.780 (95% CI [0.760-0.785]) and 0.844 (95% CI [0.839-0.848]), respectively. The corresponding risk scores yielded an AUC of 0.728 (95% CI [0.726-0.729]) and 0.848 (95% CI [0.847-0.849]), respectively. CONCLUSIONS: Deep learning and the resultant risk score have the potential to provide frontline physicians with quantitative tools to stratify patients more effectively in time-sensitive and resource-constrained circumstances.

Deep-learning convolutional neural networks with transfer learning accurately classify COVID-19 lung infection on portable chest radiographs.

Portable chest X-ray (pCXR) has become an indispensable tool in the management of Coronavirus Disease 2019 (COVID-19) lung infection. This study employed deep-learning convolutional neural networks to classify COVID-19 lung infections on pCXR from normal and related lung infections to potentially enable more timely and accurate diagnosis. This retrospect study employed deep-learning convolutional neural network (CNN) with transfer learning to classify based on pCXRs COVID-19 pneumonia (N = 455) on pCXR from normal (N = 532), bacterial pneumonia (N = 492), and non-COVID viral pneumonia (N = 552). The data was randomly split into 75% training and 25% testing, randomly. A five-fold cross-validation was used for the testing set separately. Performance was evaluated using receiver-operating curve analysis. Comparison was made with CNN operated on the whole pCXR and segmented lungs. CNN accurately classified COVID-19 pCXR from those of normal, bacterial pneumonia, and non-COVID-19 viral pneumonia patients in a multiclass model. The overall sensitivity, specificity, accuracy, and AUC were 0.79, 0.93, and 0.79, 0.85 respectively (whole pCXR), and were 0.91, 0.93, 0.88, and 0.89 (CXR of segmented lung). The performance was generally better using segmented lungs. Heatmaps showed that CNN accurately localized areas of hazy appearance, ground glass opacity and/or consolidation on the pCXR. Deep-learning convolutional neural network with transfer learning accurately classifies COVID-19 on portable chest X-ray against normal, bacterial pneumonia or non-COVID viral pneumonia. This approach has the potential to help radiologists and frontline physicians by providing more timely and accurate diagnosis.

Continued In-Hospital Angiotensin-Converting Enzyme Inhibitor and Angiotensin II Receptor Blocker Use in Hypertensive COVID-19 Patients Is Associated With Positive Clinical Outcome.

BACKGROUND: This study investigated continued and discontinued use of angiotensin-converting enzyme inhibitors (ACEi) or angiotensin II receptor blockers (ARB) during hospitalization of 614 hypertensive laboratory-confirmed COVID-19 patients. METHODS: Demographics, comorbidities, vital signs, laboratory data, and ACEi/ARB usage were analyzed. To account for confounders, patients were substratified by whether they developed hypotension and acute kidney injury (AKI) during the index hospitalization. RESULTS: Mortality (22% vs 17%, P > .05) and intensive care unit (ICU) admission (26% vs 12%, P > .05) rates were not significantly different between non-ACEi/ARB and ACEi/ARB groups. However, patients who continued ACEi/ARBs in the hospital had a markedly lower ICU admission rate (12% vs 26%; P = .001; odds ratio [OR] = 0.347; 95% confidence interval [CI], .187-.643) and mortality rate (6% vs 28%; P = .001; OR = 0.215; 95% CI, .101-.455) compared to patients who discontinued ACEi/ARB. The odds ratio for mortality remained significantly lower after accounting for development of hypotension or AKI. CONCLUSIONS: These findings suggest that continued ACEi/ARB use in hypertensive COVID-19 patients yields better clinical outcomes.

Predicting COVID-19 Pneumonia Severity on Chest X-ray With Deep Learning.

Introduction The need to streamline patient management for coronavirus disease-19 (COVID-19) has become more pressing than ever. Chest X-rays (CXRs) provide a non-invasive (potentially bedside) tool to monitor the progression of the disease. In this study, we present a severity score prediction model for COVID-19 pneumonia for frontal chest X-ray images. Such a tool can gauge the severity of COVID-19 lung infections (and pneumonia in general) that can be used for escalation or de-escalation of care as well as monitoring treatment efficacy, especially in the ICU. Methods Images from a public COVID-19 database were scored retrospectively by three blinded experts in terms of the extent of lung involvement as well as the degree of opacity. A neural network model that was pre-trained on large (non-COVID-19) chest X-ray datasets is used to construct features for COVID-19 images which are predictive for our task. Results This study finds that training a regression model on a subset of the outputs from this pre-trained chest X-ray model predicts our geographic extent score (range 0-8) with 1.14 mean absolute error (MAE) and our lung opacity score (range 0-6) with 0.78 MAE. Conclusions These results indicate that our model's ability to gauge the severity of COVID-19 lung infections could be used for escalation or de-escalation of care as well as monitoring treatment efficacy, especially in the ICU. To enable follow up work, we make our code, labels, and data available online.

Deep transfer learning artificial intelligence accurately stages COVID-19 lung disease severity on portable chest radiographs.

This study employed deep-learning convolutional neural networks to stage lung disease severity of Coronavirus Disease 2019 (COVID-19) infection on portable chest x-ray (CXR) with radiologist score of disease severity as ground truth. This study consisted of 131 portable CXR from 84 COVID-19 patients (51M 55.1±14.9yo; 29F 60.1±14.3yo; 4 missing information). Three expert chest radiologists scored the left and right lung separately based on the degree of opacity (0-3) and geographic extent (0-4). Deep-learning convolutional neural network (CNN) was used to predict lung disease severity scores. Data were split into 80% training and 20% testing datasets. Correlation analysis between AI-predicted versus radiologist scores were analyzed. Comparison was made with traditional and transfer learning. The average opacity score was 2.52 (range: 0-6) with a standard deviation of 0.25 (9.9%) across three readers. The average geographic extent score was 3.42 (range: 0-8) with a standard deviation of 0.57 (16.7%) across three readers. The inter-rater agreement yielded a Fleiss' Kappa of 0.45 for opacity score and 0.71 for extent score. AI-predicted scores strongly correlated with radiologist scores, with the top model yielding a correlation coefficient (R2) of 0.90 (range: 0.73-0.90 for traditional learning and 0.83-0.90 for transfer learning) and a mean absolute error of 8.5% (ranges: 17.2-21.0% and 8.5%-15.5, respectively). Transfer learning generally performed better. In conclusion, deep-learning CNN accurately stages disease severity on portable chest x-ray of COVID-19 lung infection. This approach may prove useful to stage lung disease severity, prognosticate, and predict treatment response and survival, thereby informing risk management and resource allocation.

Prediction model and risk scores of ICU admission and mortality in COVID-19.

This study aimed to develop risk scores based on clinical characteristics at presentation to predict intensive care unit (ICU) admission and mortality in COVID-19 patients. 641 hospitalized patients with laboratory-confirmed COVID-19 were selected from 4997 persons under investigation. We performed a retrospective review of medical records of demographics, comorbidities and laboratory tests at the initial presentation. Primary outcomes were ICU admission and death. Logistic regression was used to identify independent clinical variables predicting the two outcomes. The model was validated by splitting the data into 70% for training and 30% for testing. Performance accuracy was evaluated using area under the curve (AUC) of the receiver operating characteristic analysis (ROC). Five significant variables predicting ICU admission were lactate dehydrogenase, procalcitonin, pulse oxygen saturation, smoking history, and lymphocyte count. Seven significant variables predicting mortality were heart failure, procalcitonin, lactate dehydrogenase, chronic obstructive pulmonary disease, pulse oxygen saturation, heart rate, and age. The mortality group uniquely contained cardiopulmonary variables. The risk score model yielded good accuracy with an AUC of 0.74 ([95% CI, 0.63-0.85], p = 0.001) for predicting ICU admission and 0.83 ([95% CI, 0.73-0.92], p<0.001) for predicting mortality for the testing dataset. This study identified key independent clinical variables that predicted ICU admission and mortality associated with COVID-19. This risk score system may prove useful for frontline physicians in clinical decision-making under time-sensitive and resource-constrained environment.