Artificial intelligence matches subjective severity assessment of pneumonia for prediction of patient outcome and need for mechanical ventilation: a cohort study

Development of a new prognostic model to predict pneumonia outcome using artificial intelligence-based chest radiograph results

This study aimed to develop a new simple and effective prognostic model using artificial intelligence (AI)-based chest radiograph (CXR) results to predict the outcomes of pneumonia. Patients aged > 18 years, admitted the treatment of pneumonia between March 2020 and August 2021 were included. We developed prognostic models, including an AI-based consolidation score in addition to the conventional CURB-65 (confusion, urea, respiratory rate, blood pressure, and age ≥ 65) and pneumonia severity index (PSI) for predicting pneumonia outcomes, defined as 30-day mortality during admission. A total of 489 patients, including 310 and 179 patients in training and test sets, were included. In the training set, the AI-based consolidation score on CXR was a significant variable for predicting the outcome (hazard ratio 1.016, 95% confidence interval [CI] 1.001-1.031). The model that combined CURB-65, initial O2 requirement, intubation, and the AI-based consolidation score showed a significantly high C-index of 0.692 (95% CI 0.628-0.757) compared to other models. In the test set, this model also demonstrated a significantly high C-index of 0.726 (95% CI 0.644-0.809) compared to the conventional CURB-65 and PSI (p < 0.001 and 0.017, respectively). Therefore, a new prognostic model incorporating AI-based CXR results along with traditional pneumonia severity score could be a simple and useful tool for predicting pneumonia outcomes in clinical practice.

Applied Artificial Intelligence in Healthcare: A Review of Computer Vision Technology Application in Hospital Settings

Computer vision (CV), a type of artificial intelligence (AI) that uses digital videos or a sequence of images to recognize content, has been used extensively across industries in recent years. However, in the healthcare industry, its applications are limited by factors like privacy, safety, and ethical concerns. Despite this, CV has the potential to improve patient monitoring, and system efficiencies, while reducing workload. In contrast to previous reviews, we focus on the end-user applications of CV. First, we briefly review and categorize CV applications in other industries (job enhancement, surveillance and monitoring, automation, and augmented reality). We then review the developments of CV in the hospital setting, outpatient, and community settings. The recent advances in monitoring delirium, pain and sedation, patient deterioration, mechanical ventilation, mobility, patient safety, surgical applications, quantification of workload in the hospital, and monitoring for patient events outside the hospital are highlighted. To identify opportunities for future applications, we also completed journey mapping at different system levels. Lastly, we discuss the privacy, safety, and ethical considerations associated with CV and outline processes in algorithm development and testing that limit CV expansion in healthcare. This comprehensive review highlights CV applications and ideas for its expanded use in healthcare.

Accuracy of artificial intelligence CT quantification in predicting COVID-19 subjects' prognosis

BACKGROUND

Artificial intelligence (AI)-aided analysis of chest CT expedites the quantification of abnormalities and may facilitate the diagnosis and assessment of the prognosis of subjects with COVID-19.

OBJECTIVES

This study investigates the performance of an AI-aided quantification model in predicting the clinical outcomes of hospitalized subjects with COVID-19 and compares it with radiologists' performance.

SUBJECTS AND METHODS

A total of 90 subjects with COVID-19 (men, n = 59 [65.6%]; age, 52.9±16.7 years) were recruited in this cross-sectional study. Quantification of the total and compromised lung parenchyma was performed by two expert radiologists using a volumetric image analysis software and compared against an AI-assisted package consisting of a modified U-Net model for segmenting COVID-19 lesions and an off-the-shelf U-Net model augmented with COVID-19 data for segmenting lung volume. The fraction of compromised lung parenchyma (%CL) was calculated. Based on clinical results, the subjects were divided into two categories: critical (n = 45) and noncritical (n = 45). All admission data were compared between the two groups.

RESULTS

There was an excellent agreement between the radiologist-obtained and AI-assisted measurements (intraclass correlation coefficient = 0.88, P < 0.001). Both the AI-assisted and radiologist-obtained %CLs were significantly higher in the critical subjects (P = 0.009 and 0.02, respectively) than in the noncritical subjects. In the multivariate logistic regression analysis to distinguish the critical subjects, an AI-assisted %CL ≥35% (odds ratio [OR] = 17.0), oxygen saturation level of <88% (OR = 33.6), immunocompromised condition (OR = 8.1), and other comorbidities (OR = 15.2) independently remained as significant variables in the models. Our proposed model obtained an accuracy of 83.9%, a sensitivity of 79.1%, and a specificity of 88.6% in predicting critical outcomes.

CONCLUSIONS

AI-assisted measurements are similar to quantitative radiologist-obtained measurements in determining lung involvement in COVID-19 subjects.

Clinical Implication and Prognostic Value of Artificial-Intelligence-Based Results of Chest Radiographs for Assessing Clinical Outcomes of COVID-19 Patients

This study aimed to investigate the clinical implications and prognostic value of artificial intelligence (AI)-based results for chest radiographs (CXR) in coronavirus disease 2019 (COVID-19) patients. Patients who were admitted due to COVID-19 from September 2021 to March 2022 were retrospectively included. A commercial AI-based software was used to assess CXR data for consolidation and pleural effusion scores. Clinical data, including laboratory results, were analyzed for possible prognostic factors. Total O₂ supply period, the last SpO₂ result, and deterioration were evaluated as prognostic indicators of treatment outcome. Generalized linear mixed model and regression tests were used to examine the prognostic value of CXR results. Among a total of 228 patients (mean 59.9 ± 18.8 years old), consolidation scores had a significant association with erythrocyte sedimentation rate and C-reactive protein changes, and initial consolidation scores were associated with the last SpO₂ result (estimate -0.018, p = 0.024). All consolidation scores during admission showed significant association with the total O₂ supply period and the last SpO₂ result. Early changing degree of consolidation score showed an association with deterioration (odds ratio 1.017, 95% confidence interval 1.005-1.03). In conclusion, AI-based CXR results for consolidation have potential prognostic value for predicting treatment outcomes in COVID-19 patients.

Generative adversarial network for automatic quantification of Coronavirus disease 2019 pneumonia on chest radiographs

PURPOSE

To develop a generative adversarial network (GAN) to quantify COVID-19 pneumonia on chest radiographs automatically.

MATERIALS AND METHODS

This retrospective study included 50,000 consecutive non-COVID-19 chest CT scans in 2015-2017 for training. Anteroposterior virtual chest, lung, and pneumonia radiographs were generated from whole, segmented lung, and pneumonia pixels from each CT scan. Two GANs were sequentially trained to generate lung images from radiographs and to generate pneumonia images from lung images. GAN-driven pneumonia extent (pneumonia area/lung area) was expressed from 0% to 100%. We examined the correlation of GAN-driven pneumonia extent with semi-quantitative Brixia X-ray severity score (one dataset, n = 4707) and quantitative CT-driven pneumonia extent (four datasets, n = 54-375), along with analyzing a measurement difference between the GAN and CT extents. Three datasets (n = 243-1481), where unfavorable outcomes (respiratory failure, intensive care unit admission, and death) occurred in 10%, 38%, and 78%, respectively, were used to examine the predictive power of GAN-driven pneumonia extent.

RESULTS

GAN-driven radiographic pneumonia was correlated with the severity score (0.611) and CT-driven extent (0.640). 95% limits of agreements between GAN and CT-driven extents were -27.1% to 17.4%. GAN-driven pneumonia extent provided odds ratios of 1.05-1.18 per percent for unfavorable outcomes in the three datasets, with areas under the receiver operating characteristic curve (AUCs) of 0.614-0.842. When combined with demographic information only and with both demographic and laboratory information, the prediction models yielded AUCs of 0.643-0.841 and 0.688-0.877, respectively.

CONCLUSION

The generative adversarial network automatically quantified COVID-19 pneumonia on chest radiographs and identified patients with unfavorable outcomes.

Enhancing physicians' radiology diagnostics of COVID-19's effects on lung health by leveraging artificial intelligence

Introduction: This study aimed to develop an individualized artificial intelligence model to help radiologists assess the severity of COVID-19's effects on patients' lung health. Methods: Data was collected from medical records of 1103 patients diagnosed with COVID-19 using RT- qPCR between March and June 2020, in Hospital Madrid-Group (HM-Group, Spain). By using Convolutional Neural Networks, we determine the effects of COVID-19 in terms of lung area, opacities, and pulmonary air density. We then combine these variables with age and sex in a regression model to assess the severity of these conditions with respect to fatality risk (death or ICU). Results: Our model can predict high effect with an AUC of 0.736. Finally, we compare the performance of the model with respect to six physicians' diagnosis, and test for improvements on physicians' performance when using the prediction algorithm. Discussion: We find that the algorithm outperforms physicians (39.5% less error), and thus, physicians can significantly benefit from the information provided by the algorithm by reducing error by almost 30%.

AI-Based CXR First Reading: Current Limitations to Ensure Practical Value

We performed a multicenter external evaluation of the practical and clinical efficacy of a commercial AI algorithm for chest X-ray (CXR) analysis (Lunit INSIGHT CXR). A retrospective evaluation was performed with a multi-reader study. For a prospective evaluation, the AI model was run on CXR studies; the results were compared to the reports of 226 radiologists. In the multi-reader study, the area under the curve (AUC), sensitivity, and specificity of the AI were 0.94 (CI95%: 0.87-1.0), 0.9 (CI95%: 0.79-1.0), and 0.89 (CI95%: 0.79-0.98); the AUC, sensitivity, and specificity of the radiologists were 0.97 (CI95%: 0.94-1.0), 0.9 (CI95%: 0.79-1.0), and 0.95 (CI95%: 0.89-1.0). In most regions of the ROC curve, the AI performed a little worse or at the same level as an average human reader. The McNemar test showed no statistically significant differences between AI and radiologists. In the prospective study with 4752 cases, the AUC, sensitivity, and specificity of the AI were 0.84 (CI95%: 0.82-0.86), 0.77 (CI95%: 0.73-0.80), and 0.81 (CI95%: 0.80-0.82). Lower accuracy values obtained during the prospective validation were mainly associated with false-positive findings considered by experts to be clinically insignificant and the false-negative omission of human-reported "opacity", "nodule", and calcification. In a large-scale prospective validation of the commercial AI algorithm in clinical practice, lower sensitivity and specificity values were obtained compared to the prior retrospective evaluation of the data of the same population.

Chest radiograph classification and severity of suspected COVID-19 by different radiologist groups and attending clinicians: multi-reader, multi-case study

OBJECTIVES

To quantify reader agreement for the British Society of Thoracic Imaging (BSTI) diagnostic and severity classification for COVID-19 on chest radiographs (CXR), in particular agreement for an indeterminate CXR that could instigate CT imaging, from single and paired images.

METHODS

Twenty readers (four groups of five individuals)-consultant chest (CCR), general consultant (GCR), and specialist registrar (RSR) radiologists, and infectious diseases clinicians (IDR)-assigned BSTI categories and severity in addition to modified Covid-Radiographic Assessment of Lung Edema Score (Covid-RALES), to 305 CXRs (129 paired; 2 time points) from 176 guideline-defined COVID-19 patients. Percentage agreement with a consensus of two chest radiologists was calculated for (1) categorisation to those needing CT (indeterminate) versus those that did not (classic/probable, non-COVID-19); (2) severity; and (3) severity change on paired CXRs using the two scoring systems.

RESULTS

Agreement with consensus for the indeterminate category was low across all groups (28-37%). Agreement for other BSTI categories was highest for classic/probable for the other three reader groups (66-76%) compared to GCR (49%). Agreement for normal was similar across all radiologists (54-61%) but lower for IDR (31%). Agreement for a severe CXR was lower for GCR (65%), compared to the other three reader groups (84-95%). For all groups, agreement for changes across paired CXRs was modest.

CONCLUSION

Agreement for the indeterminate BSTI COVID-19 CXR category is low, and generally moderate for the other BSTI categories and for severity change, suggesting that the test, rather than readers, is limited in utility for both deciding disposition and serial monitoring.

KEY POINTS

• Across different reader groups, agreement for COVID-19 diagnostic categorisation on CXR varies widely. • Agreement varies to a degree that may render CXR alone ineffective for triage, especially for indeterminate cases. • Agreement for serial CXR change is moderate, limiting utility in guiding management.

An Integrated Radiologic-Pathologic Understanding of COVID-19 Pneumonia

This article reviews the radiologic and pathologic findings of the epithelial and endothelial injuries in COVID-19 pneumonia to help radiologists understand the fundamental nature of the disease. The radiologic and pathologic manifestations of COVID-19 pneumonia result from epithelial and endothelial injuries based on viral toxicity and immunopathologic effects. The pathologic features of mild and reversible COVID-19 pneumonia involve nonspecific pneumonia or an organizing pneumonia pattern, while the pathologic features of potentially fatal and irreversible COVID-19 pneumonia are characterized by diffuse alveolar damage followed by fibrosis or acute fibrinous organizing pneumonia. These pathologic responses of epithelial injuries observed in COVID-19 pneumonia are not specific to SARS-CoV-2 but rather constitute universal responses to viral pneumonia. Endothelial injury in COVID-19 pneumonia is a prominent feature compared with other types of viral pneumonia and encompasses various vascular abnormalities at different levels, including pulmonary thromboembolism, vascular engorgement, peripheral vascular reduction, a vascular tree-in-bud pattern, and lung perfusion abnormality. Chest CT with different imaging techniques (eg, CT quantification, dual-energy CT perfusion) can fully capture the various manifestations of epithelial and endothelial injuries. CT can thus aid in establishing prognosis and identifying patients at risk for deterioration.

Inter-rater reliability and prognostic value of baseline Radiographic Assessment of Lung Edema (RALE) scores in observational cohort studies of inpatients with COVID-19

OBJECTIVES

To reliably quantify the radiographic severity of COVID-19 pneumonia with the Radiographic Assessment of Lung Edema (RALE) score on clinical chest X-rays among inpatients and examine the prognostic value of baseline RALE scores on COVID-19 clinical outcomes.

SETTING

Hospitalised patients with COVID-19 in dedicated wards and intensive care units from two different hospital systems.

PARTICIPANTS

425 patients with COVID-19 in a discovery data set and 415 patients in a validation data set.

PRIMARY AND SECONDARY OUTCOMES

We measured inter-rater reliability for RALE score annotations by different reviewers and examined for associations of consensus RALE scores with the level of respiratory support, demographics, physiologic variables, applied therapies, plasma host-response biomarkers, SARS-CoV-2 RNA load and clinical outcomes.

RESULTS

Inter-rater agreement for RALE scores improved from fair to excellent following reviewer training and feedback (intraclass correlation coefficient of 0.85 vs 0.93, respectively). In the discovery cohort, the required level of respiratory support at the time of CXR acquisition (supplemental oxygen or non-invasive ventilation (n=178); invasive-mechanical ventilation (n=234), extracorporeal membrane oxygenation (n=13)) was significantly associated with RALE scores (median (IQR): 20.0 (14.1-26.7), 26.0 (20.5-34.0) and 44.5 (34.5-48.0), respectively, p<0.0001). Among invasively ventilated patients, RALE scores were significantly associated with worse respiratory mechanics (plateau and driving pressure) and gas exchange metrics (PaO2/FiO2 and ventilatory ratio), as well as higher plasma levels of IL-6, soluble receptor of advanced glycation end-products and soluble tumour necrosis factor receptor 1 (p<0.05). RALE scores were independently associated with 90-day survival in a multivariate Cox proportional hazards model (adjusted HR 1.04 (1.02-1.07), p=0.002). We replicated the significant associations of RALE scores with baseline disease severity and mortality in the independent validation data set.

CONCLUSIONS

With a reproducible method to measure radiographic severity in COVID-19, we found significant associations with clinical and physiologic severity, host inflammation and clinical outcomes. The incorporation of radiographic severity assessments in clinical decision-making may provide important guidance for prognostication and treatment allocation in COVID-19.

Role of an Automated Deep Learning Algorithm for Reliable Screening of Abnormality in Chest Radiographs: A Prospective Multicenter Quality Improvement Study

In medical practice, chest X-rays are the most ubiquitous diagnostic imaging tests. However, the current workload in extensive health care facilities and lack of well-trained radiologists is a significant challenge in the patient care pathway. Therefore, an accurate, reliable, and fast computer-aided diagnosis (CAD) system capable of detecting abnormalities in chest X-rays is crucial in improving the radiological workflow. In this prospective multicenter quality-improvement study, we have evaluated whether artificial intelligence (AI) can be used as a chest X-ray screening tool in real clinical settings. Methods: A team of radiologists used the AI-based chest X-ray screening tool (qXR) as a part of their daily reporting routine to report consecutive chest X-rays for this prospective multicentre study. This study took place in a large radiology network in India between June 2021 and March 2022. Results: A total of 65,604 chest X-rays were processed during the study period. The overall performance of AI achieved in detecting normal and abnormal chest X-rays was good. The high negatively predicted value (NPV) of 98.9% was achieved. The AI performance in terms of area under the curve (AUC), NPV for the corresponding subabnormalities obtained were blunted CP angle (0.97, 99.5%), hilar dysmorphism (0.86, 99.9%), cardiomegaly (0.96, 99.7%), reticulonodular pattern (0.91, 99.9%), rib fracture (0.98, 99.9%), scoliosis (0.98, 99.9%), atelectasis (0.96, 99.9%), calcification (0.96, 99.7%), consolidation (0.95, 99.6%), emphysema (0.96, 99.9%), fibrosis (0.95, 99.7%), nodule (0.91, 99.8%), opacity (0.92, 99.2%), pleural effusion (0.97, 99.7%), and pneumothorax (0.99, 99.9%). Additionally, the turnaround time (TAT) decreased by about 40.63% from pre-qXR period to post-qXR period. Conclusions: The AI-based chest X-ray solution (qXR) screened chest X-rays and assisted in ruling out normal patients with high confidence, thus allowing the radiologists to focus more on assessing pathology on abnormal chest X-rays and treatment pathways.

The impact of reduction in intensity of mechanical ventilation upon venovenous ECMO initiation on radiographically assessed lung edema scores: A retrospective observational study

Background

Patients with severe acute respiratory distress syndrome (ARDS) typically receive ultra-protective ventilation after extracorporeal membrane oxygenation (ECMO) is initiated. While the benefit of ECMO appears to derive from supporting “lung rest”, reductions in the intensity of mechanical ventilation, principally tidal volume limitation, may manifest radiologically. This study evaluated the relative changes in radiographic assessment of lung edema (RALE) score upon venovenous ECMO initiation in patients with severe ARDS.

Methods

Digital chest x-rays (CXR) performed at baseline immediately before initiation of ECMO, and at intervals post (median 1.1, 2.1, and 9.6 days) were reviewed in 39 Adult ARDS patients. One hundred fifty-six digital images were scored by two independent, blinded radiologists according to the RALE (Radiographic Assessment of Lung Edema) scoring criteria. Ventilatory data, ECMO parameters and fluid balance were recorded at corresponding time points. Multivariable analysis was performed analyzing the change in RALE score over time relative to baseline.

Results

The RALE score demonstrated excellent inter-rater agreement in this novel application in an ECMO cohort. Mean RALE scores increased from 28 (22–37) at baseline to 35 (26–42) (p < 0.001) on D1 of ECMO; increasing RALE was associated with higher baseline APACHE III scores [ß value +0.19 (0.08, 0.30) p = 0.001], and greater reductions in tidal volume [ß value −2.08 (−3.07, −1.10) p < 0.001] after ECMO initiation. Duration of mechanical ventilation, and ECMO support did not differ between survivors and non-survivors.

Conclusions

The magnitude of reductions in delivered tidal volumes correlated with increasing RALE scores (radiographic worsening) in ARDS patients receiving ECMO. Implications for patient centered outcomes remain unclear. There is a need to define appropriate ventilator settings on venovenous ECMO, counterbalancing the risks vs. benefits of optimal “lung rest” against potential atelectrauma.

The RALE Score Versus the CT Severity Score in Invasively Ventilated COVID-19 Patients-A Retrospective Study Comparing Their Prognostic Capacities

BACKGROUND

Quantitative radiological scores for the extent and severity of pulmonary infiltrates based on chest radiography (CXR) and computed tomography (CT) scan are increasingly used in critically ill invasively ventilated patients. This study aimed to determine and compare the prognostic capacity of the Radiographic Assessment of Lung Edema (RALE) score and the chest CT Severity Score (CTSS) in a cohort of invasively ventilated patients with acute respiratory distress syndrome (ARDS) due to COVID-19.

METHODS

Two-center retrospective observational study, including consecutive invasively ventilated COVID-19 patients. Trained scorers calculated the RALE score of first available CXR and the CTSS of the first available CT scan. The primary outcome was ICU mortality; secondary outcomes were duration of ventilation in survivors, length of stay in ICU, and hospital-, 28-, and 90-day mortality. Prognostic accuracy for ICU death was expressed using odds ratios and Area Under the Receiver Operating Characteristic curves (AUROC).

RESULTS

A total of 82 patients were enrolled. The median RALE score (22 [15-37] vs. 26 [20-39]; p = 0.34) and the median CTSS (18 [16-21] vs. 21 [18-23]; p = 0.022) were both lower in ICU survivors compared to ICU non-survivors, although only the difference in CTSS reached statistical significance. While no association was observed between ICU mortality and RALE score (OR 1.35 [95%CI 0.64-2.84]; p = 0.417; AUC 0.50 [0.44-0.56], this was noticed with the CTSS (OR, 2.31 [1.22-4.38]; p = 0.010) although with poor prognostic capacity (AUC 0.64 [0.57-0.69]). The correlation between the RALE score and CTSS was weak (r2 = 0.075; p = 0.012).

CONCLUSIONS

Despite poor prognostic capacity, only CTSS was associated with ICU mortality in our cohort of COVID-19 patients.

Association of Artificial Intelligence-Aided Chest Radiograph Interpretation With Reader Performance and Efficiency

IMPORTANCE

The efficient and accurate interpretation of radiologic images is paramount.

OBJECTIVE

To evaluate whether a deep learning-based artificial intelligence (AI) engine used concurrently can improve reader performance and efficiency in interpreting chest radiograph abnormalities.

DESIGN, SETTING, AND PARTICIPANTS

This multicenter cohort study was conducted from April to November 2021 and involved radiologists, including attending radiologists, thoracic radiology fellows, and residents, who independently participated in 2 observer performance test sessions. The sessions included a reading session with AI and a session without AI, in a randomized crossover manner with a 4-week washout period in between. The AI produced a heat map and the image-level probability of the presence of the referrable lesion. The data used were collected at 2 quaternary academic hospitals in Boston, Massachusetts: Beth Israel Deaconess Medical Center (The Medical Information Mart for Intensive Care Chest X-Ray [MIMIC-CXR]) and Massachusetts General Hospital (MGH).

MAIN OUTCOMES AND MEASURES

The ground truths for the labels were created via consensual reading by 2 thoracic radiologists. Each reader documented their findings in a customized report template, in which the 4 target chest radiograph findings and the reader confidence of the presence of each finding was recorded. The time taken for reporting each chest radiograph was also recorded. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) were calculated for each target finding.

RESULTS

A total of 6 radiologists (2 attending radiologists, 2 thoracic radiology fellows, and 2 residents) participated in the study. The study involved a total of 497 frontal chest radiographs-247 from the MIMIC-CXR data set (demographic data for patients were not available) and 250 chest radiographs from MGH (mean [SD] age, 63 [16] years; 133 men [53.2%])-from adult patients with and without 4 target findings (pneumonia, nodule, pneumothorax, and pleural effusion). The target findings were found in 351 of 497 chest radiographs. The AI was associated with higher sensitivity for all findings compared with the readers (nodule, 0.816 [95% CI, 0.732-0.882] vs 0.567 [95% CI, 0.524-0.611]; pneumonia, 0.887 [95% CI, 0.834-0.928] vs 0.673 [95% CI, 0.632-0.714]; pleural effusion, 0.872 [95% CI, 0.808-0.921] vs 0.889 [95% CI, 0.862-0.917]; pneumothorax, 0.988 [95% CI, 0.932-1.000] vs 0.792 [95% CI, 0.756-0.827]). AI-aided interpretation was associated with significantly improved reader sensitivities for all target findings, without negative impacts on the specificity. Overall, the AUROCs of readers improved for all 4 target findings, with significant improvements in detection of pneumothorax and nodule. The reporting time with AI was 10% lower than without AI (40.8 vs 36.9 seconds; difference, 3.9 seconds; 95% CI, 2.9-5.2 seconds; P < .001).

CONCLUSIONS AND RELEVANCE

These findings suggest that AI-aided interpretation was associated with improved reader performance and efficiency for identifying major thoracic findings on a chest radiograph.

Automatic scoring of COVID-19 severity in X-ray imaging based on a novel deep learning workflow

In this study, we propose a two-stage workflow used for the segmentation and scoring of lung diseases. The workflow inherits quantification, qualification, and visual assessment of lung diseases on X-ray images estimated by radiologists and clinicians. It requires the fulfillment of two core stages devoted to lung and disease segmentation as well as an additional post-processing stage devoted to scoring. The latter integrated block is utilized, mainly, for the estimation of segment scores and computes the overall severity score of a patient. The models of the proposed workflow were trained and tested on four publicly available X-ray datasets of COVID-19 patients and two X-ray datasets of patients with no pulmonary pathology. Based on a combined dataset consisting of 580 COVID-19 patients and 784 patients with no disorders, our best-performing algorithm is based on a combination of DeepLabV3 + , for lung segmentation, and MA-Net, for disease segmentation. The proposed algorithms' mean absolute error (MAE) of 0.30 is significantly reduced in comparison to established COVID-19 algorithms; BS-net and COVID-Net-S, possessing MAEs of 2.52 and 1.83 respectively. Moreover, the proposed two-stage workflow was not only more accurate but also computationally efficient, it was approximately 11 times faster than the mentioned methods. In summary, we proposed an accurate, time-efficient, and versatile approach for segmentation and scoring of lung diseases illustrated for COVID-19 and with broader future applications for pneumonia, tuberculosis, pneumothorax, amongst others.

Radiographic Assessment of Lung Edema (RALE) Scores are Highly Reproducible and Prognostic of Clinical Outcomes for Inpatients with COVID-19

INTRODUCTION

Chest imaging is necessary for diagnosis of COVID-19 pneumonia, but current risk stratification tools do not consider radiographic severity. We quantified radiographic heterogeneity among inpatients with COVID-19 with the Radiographic Assessment of Lung Edema (RALE) score on Chest X-rays (CXRs).

METHODS

We performed independent RALE scoring by ≥2 reviewers on baseline CXRs from 425 inpatients with COVID-19 (discovery dataset), we recorded clinical variables and outcomes, and measured plasma host-response biomarkers and SARS-CoV-2 RNA load from subjects with available biospecimens.

RESULTS

We found excellent inter-rater agreement for RALE scores (intraclass correlation co-efficient=0.93). The required level of respiratory support at the time of baseline CXRs (supplemental oxygen or non-invasive ventilation [n=178]; invasive-mechanical ventilation [n=234], extracorporeal membrane oxygenation [n=13]) was significantly associated with RALE scores (median [interquartile range]: 20.0[14.1-26.7], 26.0[20.5-34.0] and 44.5[34.5-48.0], respectively, p<0.0001). Among invasively-ventilated patients, RALE scores were significantly associated with worse respiratory mechanics (plateau and driving pressure) and gas exchange metrics (PaO2/FiO2 and ventilatory ratio), as well as higher plasma levels of IL-6, sRAGE and TNFR1 levels (p<0.05). RALE scores were independently associated with 90-day survival in a multivariate Cox proportional hazards model (adjusted hazard ratio 1.04[1.02-1.07], p=0.002). We validated significant associations of RALE scores with baseline severity and mortality in an independent dataset of 415 COVID-19 inpatients.

CONCLUSION

Reproducible assessment of radiographic severity revealed significant associations with clinical and physiologic severity, host-response biomarkers and clinical outcome in COVID-19 pneumonia. Incorporation of radiographic severity assessments may provide prognostic and treatment allocation guidance in patients hospitalized with COVID-19.

Chest Radiograph Severity Scores, Comorbidity Prevalence, and Outcomes of Patients with Coronavirus Disease Treated at the King Abdullah University Hospital in Jordan: A Retrospective Study

Introduction

Hospitalized patients with coronavirus disease (COVID-19) often undergo chest x-ray (CXR). Utilizing CXR findings could reduce the cost of COVID-19 treatment and the resultant pressure on the Jordanian healthcare system.

Methods

We evaluated the association between the CXR severity score, based on the Radiographic Assessment of Lung Edema (RALE) scoring system, and outcomes of patients with COVID-19. The main objective of this work is to assess the role of the RALE scoring system in predicting in-hospital mortality and clinical outcomes of patients with COVID-19. Adults with a positive severe acute respiratory syndrome COVID-19 two reverse-transcription polymerase chain reaction test results and a baseline CXR image, obtained in November 2020, were included. The RALE severity scores were calculated by expert radiologists and categorized as normal, mild, moderate, and severe. Chi-square tests and multivariable logistic regression were used to assess the association between the severity category and admission location and clinical characteristics.

Results

Based on the multivariable regression analysis, it has been found that male sex, hypertension, and the RALE severity score were significantly associated with in-hospital mortality. The baseline RALE severity score was associated with the need for critical care (P<0.001), in-hospital mortality (P<0.001), and the admission location (P=0.002).

Discussion

The utilization of RALE severity scores helps to predict clinical outcomes and promote prudent use of resources during the COVID-19 pandemic.

CT-based severity assessment for COVID-19 using weakly supervised non-local CNN

Evaluating patient criticality is the foremost step in administering appropriate COVID-19 treatment protocols. Learning an Artificial Intelligence (AI) model from clinical data for automatic risk-stratification enables accelerated response to patients displaying critical indicators. Chest CT manifestations including ground-glass opacities and consolidations are a reliable indicator for prognostic studies and show variability with patient condition. To this end, we propose a novel attention framework to estimate COVID-19 severity as a regression score from a weakly annotated CT scan dataset. It takes a non-locality approach that correlates features across different parts and spatial scales of the 3D scan. An explicit guidance mechanism from limited infection labeling drives attention refinement and feature modulation. The resulting encoded representation is further enriched through cross-channel attention. The attention model also infuses global contextual awareness into the deep voxel features by querying the base CT scan to mine relevant features. Consequently, it learns to effectively localize its focus region and chisel out the infection precisely. Experimental validation on the MosMed dataset shows that the proposed architecture has significant potential in augmenting existing methods as it achieved a 0.84 R-squared score and 0.133 mean absolute difference.

Microscopic Imaging and Labeling Dataset for the Detection of Pneumocystis jirovecii Using Methenamine Silver Staining Method

Pneumocystis jirovecii pneumonia is one of the diseases that most affects immunocompromised patients today, and under certain circumstances, it can be fatal. On the other hand, more and more automatic tools based on artificial intelligence are required every day to help diagnose diseases and thus optimize the resources of the healthcare system. It is therefore important to develop techniques and mechanisms that enable early diagnosis. One of the most widely used techniques in diagnostic laboratories for the detection of its etiological agent, Pneumocystis jirovecii, is optical microscopy. Therefore, an image dataset of 29 different patients is presented in this work, which can be used to detect whether a patient is positive or negative for this fungi. These images were taken in at least four random positions on the specimen holder. The dataset consists of a total of 137 RGB images. Likewise, it contains realistic, annotated, and high-quality microscope images. In addition, we provide image segmentation and labeling that can also be used in numerous studies based on artificial intelligence implementation. The labeling was also validated by an expert, allowing it to be used as a reference in the training of automatic algorithms with supervised learning methods and thus to develop diagnostic assistance systems. Therefore, the dataset will open new opportunities for researchers working in image segmentation, detection, and classification problems related to Pneumocystis jirovecii pneumonia diagnosis.

The Prognostic Capacity of the Radiographic Assessment for Lung Edema Score in Patients With COVID-19 Acute Respiratory Distress Syndrome-An International Multicenter Observational Study

Background: The radiographic assessment for lung edema (RALE) score has an association with mortality in patients with acute respiratory distress syndrome (ARDS). It is uncertain whether the RALE scores at the start of invasive ventilation or changes thereof in the next days have prognostic capacities in patients with COVID-19 ARDS.

Aims and Objectives: To determine the prognostic capacity of the RALE score for mortality and duration of invasive ventilation in patients with COVID-19 ARDS.

Methods: An international multicenter observational study included consecutive patients from 6 ICUs. Trained observers scored the first available chest X-ray (CXR) obtained within 48 h after the start of invasive ventilation (“baseline CXR”) and each CXRs thereafter up to day 14 (“follow-up CXR”). The primary endpoint was mortality at day 90. The secondary endpoint was the number of days free from the ventilator and alive at day 28 (VFD-28).

Results: A total of 350 CXRs were scored in 139 patients with COVID-19 ARDS. The RALE score of the baseline CXR was high and was not different between survivors and non-survivors (33 [24–38] vs. 30 [25–38], P = 0.602). The RALE score of the baseline CXR had no association with mortality (hazard ratio [HR], 1.24 [95% CI 0.88–1.76]; P = 0.222; area under the receiver operating characteristic curve (AUROC) 0.50 [0.40–0.60]). A change in the RALE score over the first 14 days of invasive ventilation, however, had an independent association with mortality (HR, 1.03 [95% CI 1.01–1.05]; P < 0.001). When the event of death was considered, there was no significant association between the RALE score of the baseline CXR and the probability of being liberated from the ventilator (HR 1.02 [95% CI 0.99–1.04]; P = 0.08).

Conclusion: In this cohort of patients with COVID-19 ARDS, with high RALE scores of the baseline CXR, the RALE score of the baseline CXR had no prognostic capacity, but an increase in the RALE score in the next days had an association with higher mortality.

Comprehensive literature review on the radiographic findings, imaging modalities, and the role of radiology in the COVID-19 pandemic

Since the outbreak of the coronavirus disease 2019 (COVID-19) pandemic, over 103214008 cases have been reported, with more than 2231158 deaths as of January 31, 2021. Although the gold standard for diagnosis of this disease remains the reverse-transcription polymerase chain reaction of nasopharyngeal and oropharyngeal swabs, its false-negative rates have ignited the use of medical imaging as an important adjunct or alternative. Medical imaging assists in identifying the pathogenesis, the degree of pulmonary damage, and the characteristic features in each imaging modality. This literature review collates the characteristic radiographic findings of COVID-19 in various imaging modalities while keeping the preliminary focus on chest radiography, computed tomography (CT), and ultrasound scans. Given the higher sensitivity and greater proficiency in detecting characteristic findings during the early stages, CT scans are more reliable in diagnosis and serve as a practical method in following up the disease time course. As research rapidly expands, we have emphasized the CO-RADS classification system as a tool to aid in communicating the likelihood of COVID-19 suspicion among healthcare workers. Additionally, the utilization of other scoring systems such as MuLBSTA, Radiological Assessment of Lung Edema, and Brixia in this pandemic are reviewed as they integrate the radiographic findings into an objective scoring system to risk stratify the patients and predict the severity of disease. Furthermore, current progress in the utilization of artificial intelligence via radiomics is evaluated. Lastly, the lesson from the first wave and preparation for the second wave from the point of view of radiology are summarized.

Chest Radiograph Scoring Alone or Combined with Other Risk Scores for Predicting Outcomes in COVID-19

Background

Radiographic severity may help predict patient deterioration and outcomes from COVID-19 pneumonia.

Purpose

To assess the reliability and reproducibility of three chest radiograph reporting systems (radiographic assessment of lung edema [RALE], Brixia, and percentage opacification) in patients with proven SARS-CoV-2 infection and examine the ability of these scores to predict adverse outcomes both alone and in conjunction with two clinical scoring systems, National Early Warning Score 2 (NEWS2) and International Severe Acute Respiratory and Emerging Infection Consortium: Coronavirus Clinical Characterization Consortium (ISARIC-4C) mortality.

Materials and Methods

This retrospective cohort study used routinely collected clinical data of patients with polymerase chain reaction–positive SARS-CoV-2 infection admitted to a single center from February 2020 through July 2020. Initial chest radiographs were scored for RALE, Brixia, and percentage opacification by one of three radiologists. Intra- and interreader agreement were assessed with intraclass correlation coefficients. The rate of admission to the intensive care unit (ICU) or death up to 60 days after scored chest radiograph was estimated. NEWS2 and ISARIC-4C mortality at hospital admission were calculated. Daily risk for admission to ICU or death was modeled with Cox proportional hazards models that incorporated the chest radiograph scores adjusted for NEWS2 or ISARIC-4C mortality.

Results

Admission chest radiographs of 50 patients (mean age, 74 years ± 16 [standard deviation]; 28 men) were scored by all three radiologists, with good interreader reliability for all scores, as follows: intraclass correlation coefficients were 0.87 for RALE (95% CI: 0.80, 0.92), 0.86 for Brixia (95% CI: 0.76, 0.92), and 0.72 for percentage opacification (95% CI: 0.48, 0.85). Of 751 patients with a chest radiograph, those with greater than 75% opacification had a median time to ICU admission or death of just 1–2 days. Among 628 patients for whom data were available (median age, 76 years [interquartile range, 61–84 years]; 344 men), opacification of 51%–75% increased risk for ICU admission or death by twofold (hazard ratio, 2.2; 95% CI: 1.6, 2.8), and opacification greater than 75% increased ICU risk by fourfold (hazard ratio, 4.0; 95% CI: 3.4, 4.7) compared with opacification of 0%–25%, when adjusted for NEWS2 score.

Conclusion

Brixia, radiographic assessment of lung edema, and percentage opacification scores all reliably helped predict adverse outcomes in SARS-CoV-2 infection.

© RSNA, 2021

Online supplemental material is available for this article.

See also the editorial by Little in this issue.

The application of artificial intelligence and data integration in COVID-19 studies: a scoping review

OBJECTIVE

To summarize how artificial intelligence (AI) is being applied in COVID-19 research and determine whether these AI applications integrated heterogenous data from different sources for modeling.

MATERIALS AND METHODS

We searched 2 major COVID-19 literature databases, the National Institutes of Health's LitCovid and the World Health Organization's COVID-19 database on March 9, 2021. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guideline, 2 reviewers independently reviewed all the articles in 2 rounds of screening.

RESULTS

In the 794 studies included in the final qualitative analysis, we identified 7 key COVID-19 research areas in which AI was applied, including disease forecasting, medical imaging-based diagnosis and prognosis, early detection and prognosis (non-imaging), drug repurposing and early drug discovery, social media data analysis, genomic, transcriptomic, and proteomic data analysis, and other COVID-19 research topics. We also found that there was a lack of heterogenous data integration in these AI applications.

DISCUSSION

Risk factors relevant to COVID-19 outcomes exist in heterogeneous data sources, including electronic health records, surveillance systems, sociodemographic datasets, and many more. However, most AI applications in COVID-19 research adopted a single-sourced approach that could omit important risk factors and thus lead to biased algorithms. Integrating heterogeneous data for modeling will help realize the full potential of AI algorithms, improve precision, and reduce bias.

CONCLUSION

There is a lack of data integration in the AI applications in COVID-19 research and a need for a multilevel AI framework that supports the analysis of heterogeneous data from different sources.

Applications of Artificial Intelligence, Machine Learning, Big Data and the Internet of Things to the COVID-19 Pandemic: A Scientometric Review Using Text Mining

The COVID-19 pandemic has wreaked havoc in every country in the world, with serious health-related, economic, and social consequences. Since its outbreak in March 2020, many researchers from different fields have joined forces to provide a wide range of solutions, and the support for this work from artificial intelligence (AI) and other emerging concepts linked to intelligent data analysis has been decisive. The enormous amount of research and the high number of publications during this period makes it difficult to obtain an overall view of the different applications of AI to the management of COVID-19 and an understanding of how research in this field has been evolving. Therefore, in this paper, we carry out a scientometric analysis of this area supported by text mining, including a review of 18,955 publications related to AI and COVID-19 from the Scopus database from March 2020 to June 2021 inclusive. For this purpose, we used VOSviewer software, which was developed by researchers at Leiden University in the Netherlands. This allowed us to examine the exponential growth in research on this issue and its distribution by country, and to highlight the clear hegemony of the United States (USA) and China in this respect. We used an automatic process to extract topics of research interest and observed that the most important current lines of research focused on patient-based solutions. We also identified the most relevant journals in terms of the COVID-19 pandemic, demonstrated the growing value of open-access publication, and highlighted the most influential authors by means of an analysis of citations and co-citations. This study provides an overview of the current status of research on the application of AI to the pandemic.

Comparison of deep learning, radiomics and subjective assessment of chest CT findings in SARS-CoV-2 pneumonia

Purpose

Comparison of deep learning algorithm, radiomics and subjective assessment of chest CT for predicting outcome (death or recovery) and intensive care unit (ICU) admission in patients with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection.

Methods

The multicenter, ethical committee-approved, retrospective study included non-contrast-enhanced chest CT of 221 SARS-CoV-2 positive patients from Italy (n = 196 patients; mean age 64 ± 16 years) and Denmark (n = 25; mean age 69 ± 13 years). A thoracic radiologist graded presence, type and extent of pulmonary opacities and severity of motion artifacts in each lung lobe on all chest CTs. Thin-section CT images were processed with CT Pneumonia Analysis Prototype (Siemens Healthineers) which yielded segmentation masks from a deep learning (DL) algorithm to derive features of lung abnormalities such as opacity scores, mean HU, as well as volume and percentage of all-attenuation and high-attenuation (opacities >−200 HU) opacities. Separately, whole lung radiomics were obtained for all CT exams. Analysis of variance and multiple logistic regression were performed for data analysis.

Results

Moderate to severe respiratory motion artifacts affected nearly one-quarter of chest CTs in patients. Subjective severity assessment, DL-based features and radiomics predicted patient outcome (AUC 0.76 vs AUC 0.88 vs AUC 0.83) and need for ICU admission (AUC 0.77 vs AUC 0.0.80 vs 0.82). Excluding chest CT with motion artifacts, the performance of DL-based and radiomics features improve for predicting ICU admission.

Conclusion

DL-based and radiomics features of pulmonary opacities from chest CT were superior to subjective assessment for differentiating patients with favorable and adverse outcomes.

Accuracy of the Radiographic Assessment of Lung Edema Score for the Diagnosis of ARDS

Background: Bilateral opacities on chest radiographs are part of the Berlin Definition for Acute Respiratory Distress Syndrome (ARDS) but have poor interobserver reliability. The “Radiographic Assessment of Lung Edema” (RALE) score was recently proposed for evaluation of the extent and density of alveolar opacities on chest radiographs of ARDS patients. The current study determined the accuracy of the RALE score for the diagnosis and the prognosis of ARDS.

Methods:Post-hoc analysis of a cohort of invasively ventilated intensive care unit (ICU) patients expected to need invasive ventilation for >24 h. The Berlin Definition was used as the gold standard. The RALE score was calculated for the first available chest radiograph after start of ventilation in the ICU. The primary endpoint was the diagnostic accuracy for ARDS of the RALE score. Secondary endpoints included the prognostic value of the RALE score for ICU and hospital mortality, and the association with ARDS severity, and the PaO₂/FiO₂. Receiver operating characteristic (ROC) curves were constructed, and the optimal cutoff was used to determine sensitivity, specificity and the negative and positive predictive value of the RALE score for ARDS.

Results: The study included 131 patients, of whom 30 had ARDS (11 mild, 15 moderate, and 4 severe ARDS). The first available chest radiograph was obtained median 0 [0 to 1] days after start of invasive ventilation in ICU. Compared to patients without ARDS, a higher RALE score was found in patients with ARDS (24 [interquartile range (IQR) 16–30] vs. 6 [IQR 3–11]; P < 0.001), with RALE scores of 20 [IQR 14–24], 26 [IQR 16–32], and 32 [IQR 19–36] for mild, moderate and severe ARDS, respectively, (P = 0.166). The area under the ROC for ARDS was excellent (0.91 [0.86–0.96]). The best cutoff for ARDS diagnosis was 10 with 100% sensitivity, 71% specificity, 51% positive predictive value and 100% negative predictive value. The RALE score was not associated with ICU or hospital mortality, and weakly correlated with the PaO₂/FiO₂.

Conclusion: In this cohort of invasively ventilated ICU patients, the RALE score had excellent diagnostic accuracy for ARDS.

Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal

OBJECTIVE

To review and appraise the validity and usefulness of published and preprint reports of prediction models for diagnosing coronavirus disease 2019 (covid-19) in patients with suspected infection, for prognosis of patients with covid-19, and for detecting people in the general population at increased risk of covid-19 infection or being admitted to hospital with the disease.

DESIGN

Living systematic review and critical appraisal by the COVID-PRECISE (Precise Risk Estimation to optimise covid-19 Care for Infected or Suspected patients in diverse sEttings) group.

DATA SOURCES

PubMed and Embase through Ovid, up to 1 July 2020, supplemented with arXiv, medRxiv, and bioRxiv up to 5 May 2020.

STUDY SELECTION

Studies that developed or validated a multivariable covid-19 related prediction model.

DATA EXTRACTION

At least two authors independently extracted data using the CHARMS (critical appraisal and data extraction for systematic reviews of prediction modelling studies) checklist; risk of bias was assessed using PROBAST (prediction model risk of bias assessment tool).

RESULTS

37 421 titles were screened, and 169 studies describing 232 prediction models were included. The review identified seven models for identifying people at risk in the general population; 118 diagnostic models for detecting covid-19 (75 were based on medical imaging, 10 to diagnose disease severity); and 107 prognostic models for predicting mortality risk, progression to severe disease, intensive care unit admission, ventilation, intubation, or length of hospital stay. The most frequent types of predictors included in the covid-19 prediction models are vital signs, age, comorbidities, and image features. Flu-like symptoms are frequently predictive in diagnostic models, while sex, C reactive protein, and lymphocyte counts are frequent prognostic factors. Reported C index estimates from the strongest form of validation available per model ranged from 0.71 to 0.99 in prediction models for the general population, from 0.65 to more than 0.99 in diagnostic models, and from 0.54 to 0.99 in prognostic models. All models were rated at high or unclear risk of bias, mostly because of non-representative selection of control patients, exclusion of patients who had not experienced the event of interest by the end of the study, high risk of model overfitting, and unclear reporting. Many models did not include a description of the target population (n=27, 12%) or care setting (n=75, 32%), and only 11 (5%) were externally validated by a calibration plot. The Jehi diagnostic model and the 4C mortality score were identified as promising models.

CONCLUSION

Prediction models for covid-19 are quickly entering the academic literature to support medical decision making at a time when they are urgently needed. This review indicates that almost all pubished prediction models are poorly reported, and at high risk of bias such that their reported predictive performance is probably optimistic. However, we have identified two (one diagnostic and one prognostic) promising models that should soon be validated in multiple cohorts, preferably through collaborative efforts and data sharing to also allow an investigation of the stability and heterogeneity in their performance across populations and settings. Details on all reviewed models are publicly available at https://www.covprecise.org/. Methodological guidance as provided in this paper should be followed because unreliable predictions could cause more harm than benefit in guiding clinical decisions. Finally, prediction model authors should adhere to the TRIPOD (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) reporting guideline.

SYSTEMATIC REVIEW REGISTRATION

Protocol https://osf.io/ehc47/, registration https://osf.io/wy245.

READERS' NOTE

This article is a living systematic review that will be updated to reflect emerging evidence. Updates may occur for up to two years from the date of original publication. This version is update 3 of the original article published on 7 April 2020 (BMJ 2020;369:m1328). Previous updates can be found as data supplements (https://www.bmj.com/content/369/bmj.m1328/related#datasupp). When citing this paper please consider adding the update number and date of access for clarity.