LUNG ULTRASOUND DURING COVID-19 PANDEMICS: WHY, HOW AND WHEN?

The aim: To optimize diagnostic of pathological processes in lungs affected by COVID-19, dynamic monitoring and clinical decision making using lung ultrasound in limited resources settings. Materials and methods: Between the onset of pandemics and January 2021, approximately 9000 patients have been treated for confirmed COVID-19 in the Olexandrivska Clinical Hospital. Assessment of all hospitalized patients included hematology, chemistries and proinflammatory cytokines – IL-6, CRP, procalcitonin, ferritin. Diagnosis was confirmed by PCR for SARS-CoV-2 RNA. Chest X-ray was performed in all hospitalized cases, while CT was available approximately in 30% of cases during hospital stay. Lung ultrasound was proactively utilized to assess the type and extent of lung damage and to monitor the progress of disease in patients hospitalized into the ICU and Infection Unit (n=135). Ultrasound findings were recorded numerically based on scales. Results: In the setting of СOVID-19, bedside lung ultrasound has been promptly recognized as a tool to diagnose and monitor the nature and extent of lung injury. Lung ultrasound is a real time assessment, which helps determine the nature of a pathologic process affecting lungs. In this paper the accuracy of bedside LUS, chest X-ray and computer tomography are compared based on clinical cases, typical for COVID-19 lung ultrasound appearance is evaluated. Described in article data is collected in one of the biggest facility that deals with COVID-19. Chest X-ray was performed in all hospitalized cases, while CT was available approximately in 30% of cases during hospital stay. The cases presented in the paper indicate potential advantages to the use of ultrasound in limited resource healthcare settings, especially when the risk of transportation to CT outweighs the value of information obtained. Conclusions: Grading of ultrasonographic findings in the lungs was sufficient for both initial assessment with identification of high risk patients, and routine daily monitoring. Hence, lung ultrsound may be used to predict deterioration, stratify risks and make clinical decisions.

Download Full-text

Slumped posture on chest X-ray—association with mortality and length of hospital stay in older hospitalised patients

Age and Ageing ◽

10.1093/ageing/afz037 ◽

2019 ◽

Vol 48 (4) ◽

pp. 588-591

Author(s):

Aled Lloyd ◽

Elin Thomas ◽

Hasan Haboubi

Keyword(s):

Length Of Stay ◽

Hospital Stay ◽

Clinical Decision Making ◽

Length Of Hospital Stay ◽

Clinical Decision ◽

Health Board ◽

X Ray ◽

Shortest Distance ◽

Hospitalised Patients ◽

Chest X Ray

Abstract Introduction frail, older patients are occasionally incapable of keeping their head out of the field of view of a chest radiograph (CXR) resulting in a ‘slumpogram’. This study aims to explore a possible link between a slumped appearance on a CXR; mortality and length of hospital stay. Methods the CXRs of patients aged over 65 admitted to a Health Board with a catchment area of approximately 300,000 were investigated in a retrospective analysis of all CXRs taken during the first week of January 2015. Slumped patients were compared to age matched controls. The degree of slumping was measured by the number of ribs covered and the MA/C factor (the shortest distance between the angle of the mandible and a line drawn between the heads of both acromion divided by the length of the patient’s clavicle). Outcomes investigated included length of hospital stay and 18-month mortality. Results 806 CXRs were viewed with 53 slumped patients and 53 matched controls identified. In all patients aged over 65 there was a statistically significant correlation between the length of stay and the number of ribs covered by the patients’ head (P = 0.038). The MA/C factor was also associated with length of stay (P = 0.025). In patients over 80 there was a significant association between the number of ribs covered and death (P = 0.015). Conclusion a slumped CXR may be associated with longer hospitalisation or death. The results of this small study require further revalidation but if true could help inform clinical decision making.

Download Full-text

Lung Ultrasound in COVID-19 pandemic: Why? How? And When?

Likarska sprava ◽

10.31640/jvd.5-6.2020(1) ◽

2020 ◽

pp. 3-12

Author(s):

Khrystyna Pronyuk ◽

Andriy Vysotskyi

Keyword(s):

Critically Ill ◽

Computer Tomography ◽

Critically Ill Patients ◽

Clinical Decision Making ◽

Lung Ultrasound ◽

Clinical Decision ◽

X Rays ◽

Lung Involvement ◽

X Ray ◽

Chest X Ray

During COVID-19 pandemic Lung ultrasound has rapidly become a tool for diagnosis and monitoring of lung involvement and it’s severity. Accurate evaluation of lung pathologic entities at the bedside, especially in critically ill patients, and those on mechanical ventilation, remains problematic. CT should not be frequently repeated and is not available everywhere, especially for critically ill patients. Limitations of bedside chest X-ray have been well described and lead to poor-quality X-ray films with low sensitivity.The lung ultrasound has been shown to be a useful tool in intensive care patients with adult respiratory distress syndrome (ARDS) and can be used forassessing severity of lung involvement in COVID-19. In this paper the accuracy of bedside LUS, chest X-ray and computer tomography are compared based on clinical cases, typical for COVID-19 lung ultrasound appearance is evaluated. There have been shown that lung ultrasound can predict the deterioration of the patient's conditionand can be used for risk stratification and clinical decision making, reducethe use of both chest x‐rays and computer tomography, what is very important especially in limited resources settings.

Download Full-text

Cost-effective clinical decision making

PEDIATRICS ◽

10.1542/peds.60.5.756a ◽

1977 ◽

Vol 60 (5) ◽

pp. 756-759

Author(s):

Duncan Neuhauser

Keyword(s):

Decision Making ◽

Hospital Stay ◽

Clinical Decision Making ◽

Cost Effective ◽

Clinical Decision ◽

Inappropriate Therapy ◽

X Ray ◽

Scarce Resources ◽

Chest X Ray ◽

The Cost

Are pediatric preoperative chest x-ray examinations worth doing? Sane et al. (p. 669) conclude that they are "medically and economically justified and essential." To answer this question requires at least the following information. What is the cost of the examination (dollars, radiation exposure, cost of further testing and perhaps inappropriate therapy resulting therefrom, and possible prolongation of hospital stay)? What is the benefit? What percent of patients have unsuspected findings; of these, the percent with modified treatment; and of these, what percent benefited therefrom? What was the cost per unit of benefit received? Is there some other use of these scarce resources that would have yielded greater benefits?

Download Full-text

Deep convolutional approaches for the analysis of Covid-19 using chest X-Ray images from portable devices

10.1101/2020.06.18.20134593 ◽

2020 ◽

Author(s):

Joaquim de Moura ◽

Lucía Ramos ◽

Plácido L. Vidal ◽

Milena Cruz ◽

Laura Abelairas ◽

...

Keyword(s):

Network Architecture ◽

Clinical Decision Making ◽

Clinical Decision ◽

World Health ◽

Portable Devices ◽

Learning Approaches ◽

Portable Equipment ◽

Convolutional Network ◽

X Ray ◽

Chest X Ray

The recent human coronavirus disease (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been declared as a global pandemic on 11 March 2020 by the World Health Organization. Given the effects of COVID-19 in pulmonary tissues, chest radiography imaging plays an important role for the screening, early detection and monitoring of the suspected individuals. Hence, as the pandemic of COVID-19 progresses, there will be a greater reliance on the use of portable equipment for the acquisition of chest X-Ray images due to its accessibility, widespread availability and benefits regarding to infection control issues, minimizing the risk of cross contamination. This work presents novel fully automatic approaches specifically tailored for the classification of chest X-Ray images acquired by portable equipment into 3 different clinical categories: normal, pathological and COVID-19. For this purpose, two complementary deep learning approaches based on a densely convolutional network architecture are herein presented. The joint response of both approaches allows to enhance the differentiation between patients infected with COVID-19, patients with other diseases that manifest characteristics similar to COVID-19 and normal cases. The proposed approaches were validated over a dataset provided by the Radiology Service of the Complexo Hospitalario Universitario A Coruña (CHUAC) specifically retrieved for this research. Despite the poor quality of chest X-Ray images that is inherent to the nature of the portable equipment, the proposed approaches provided satisfactory results, allowing a reliable analysis of portable radiographs, to support the clinical decision-making process.

Download Full-text

The role of chest X-ray in the diagnosis of bacteriologically confirmed pulmonary tuberculosis in hospitalised Xpert MTB/RIF-negative patients

ERJ Open Research ◽

10.1183/23120541.00708-2020 ◽

2020 ◽

pp. 00708-2020

Author(s):

Wakjira Kebede ◽

Gemeda Abebe ◽

Esayas Kebede Gudina ◽

Elias Kedir ◽

Thuy Ngan Tran ◽

...

Keyword(s):

Clinical Decision Making ◽

Clinical Symptoms ◽

Medical Center ◽

Strong Association ◽

Clinical Decision ◽

Prediction Tool ◽

X Ray ◽

Hospitalised Patients ◽

Chest X Ray

IntroductionThe role of a chest X-ray (CXR) to diagnose active tuberculosis (TB) in symptomatic patients who have a negative Xpert MTB/RIF (Xpert) test result is unclear. This study aimed to assess the performance of CXR and the value of CXR findings for a prediction tool to identify cases of active pulmonary TB among symptomatic, Xpert-negative hospitalised patients.MethodsXpert-negative patients hospitalised between January and July 2019 at Jimma University Medical Center in Ethiopia were assessed by mycobacterial culture and CXR. CXR was interpreted by a clinician for clinical decision making and by a radiologist for research purposes. Using bacteriological confirmation as the reference standard, the performance of CXR to diagnose active TB was assessed by the area under the receiver operating characteristic (AUC) curve, predictors of active TB were identified using bivariate and multivariate logistic regression analyses.ResultsOf 247 Xpert-negative patients, 38% and 40% were classified as suggestive of TB by clinician and radiologist, respectively. Of the 39 (15.8%) bacteriologically confirmed cases, 69% and 79% were classified as having CXR findings suggestive of TB by clinician or radiologist, respectively. While there was a strong association between bacteriologically confirmed TB and CXR classified by clinician as suggestive of TB (aOR 2.7, 95% CI: 1.2–6.6), CXR with signs typical of TB (aOR 5.3, 95% CI: 2.1–14.4) or compatible with TB (aOR 5.1, 95% CI: 1.3–20.0), the positive predictive value of the CXR was low (27% and 34% for classification by clinician and radiologist, respectively). The addition of CXR findings by clinician or radiologist to clinical characteristics did not improve the performance of the prediction tool, with similar risk classification distribution, AUCs and negative and positive prediction values.ConclusionDespite the strong association between CXR findings and active TB among hospitalised Xpert negative individuals, CXR findings did not improve the performance of a risk prediction tool based solely on clinical symptoms. Countries with a high TB/HIV burden should urgently replace Xpert by the more sensitive Xpert ultra assay to improve the diagnosis of active TB.

Download Full-text

A Prospective Observational Study to Investigate Performance of a Chest X-ray Artificial Intelligence Diagnostic Support Tool Across 12 U.S. Hospitals

10.1101/2021.06.04.21258316 ◽

2021 ◽

Author(s):

Ju Sun ◽

Le Peng ◽

Taihui Li ◽

Dyah Adila ◽

Zach Zaiman ◽

...

Keyword(s):

Real Time ◽

Clinical Decision Making ◽

External Validation ◽

Model Performance ◽

Signs And Symptoms ◽

Clinical Decision ◽

Indiana University ◽

X Ray ◽

Emory University ◽

Chest X Ray

Importance: An artificial intelligence (AI)-based model to predict COVID-19 likelihood from chest x-ray (CXR) findings can serve as an important adjunct to accelerate immediate clinical decision making and improve clinical decision making. Despite significant efforts, many limitations and biases exist in previously developed AI diagnostic models for COVID-19. Utilizing a large set of local and international CXR images, we developed an AI model with high performance on temporal and external validation. Objective: Investigate real-time performance of an AI-enabled COVID-19 diagnostic support system across a 12-hospital system. Design: Prospective observational study. Setting: Labeled frontal CXR images (samples of COVID-19 and non-COVID-19) from the M Health Fairview (Minnesota, USA), Valencian Region Medical ImageBank (Spain), MIMIC-CXR, Open-I 2013 Chest X-ray Collection, GitHub COVID-19 Image Data Collection (International), Indiana University (Indiana, USA), and Emory University (Georgia, USA) Participants: Internal (training, temporal, and real-time validation): 51,592 CXRs; Public: 27,424 CXRs; External (Indiana University): 10,002 CXRs; External (Emory University): 2002 CXRs Main Outcome and Measure: Model performance assessed via receiver operating characteristic (ROC), Precision-Recall curves, and F1 score. Results: Patients that were COVID-19 positive had significantly higher COVID-19 Diagnostic Scores (median .1 [IQR: 0.0-0.8] vs median 0.0 [IQR: 0.0-0.1], p < 0.001) than patients that were COVID-19 negative. Pre-implementation the AI-model performed well on temporal validation (AUROC 0.8) and external validation (AUROC 0.76 at Indiana U, AUROC 0.72 at Emory U). The model was noted to have unrealistic performance (AUROC > 0.95) using publicly available databases. Real-time model performance was unchanged over 19 weeks of implementation (AUROC 0.70). On subgroup analysis, the model had improved discrimination for patients with severe as compared to mild or moderate disease, p < 0.001. Model performance was highest in Asians and lowest in whites and similar between males and females. Conclusions and Relevance: AI-based diagnostic tools may serve as an adjunct, but not replacement, for clinical decision support of COVID-19 diagnosis, which largely hinges on exposure history, signs, and symptoms. While AI-based tools have not yet reached full diagnostic potential in COVID-19, they may still offer valuable information to clinicians taken into consideration along with clinical signs and symptoms.

Download Full-text

Does imbalance in chest X-ray datasets produce biased deep learning approaches for COVID-19 screening?

10.21203/rs.3.rs-960883/v1 ◽

2021 ◽

Author(s):

Lorena Alvarez-Rodríguez ◽

Joaquim de Moura ◽

Jorge Novo ◽

Marcos Ortega

Keyword(s):

Decision Making ◽

Deep Learning ◽

Clinical Decision Making ◽

Patient Characteristics ◽

Clinical Decision ◽

Decision Making Process ◽

Health Crisis ◽

X Ray ◽

Reliable Analysis ◽

Chest X Ray

Abstract Background: The health crisis resulting from the global COVID-19 pandemic highlighted more than ever the need for rapid, reliable and safe methods of diagnosis and monitoring of respiratory diseases. To study pulmonary involvement in detail, one of the most common resources is the use different lung imaging modalities (like chest radiography) to explore the possible affected areas. Methods: In this work, we performed a comprehensive analysis of sex and age factors in chest X-ray images. The study of these recurrent patient characteristics in pathologies of this type is crucial, since there is a clear scarcity of data that may lead to biases when trying to develop systems that are as representative as possible, as well as to gain knowledge of the disease itself. To identify possible biases, we analyzed 3 different computational approaches for automatic COVID-19 screening: Normal vs COVID-19, Pneumonia vs COVID-19 and Non-COVID-19 vs COVID-19. The presented study was validated using two public chest X-ray datasets, allowing a reliable analysis to support the clinical decision-making process in the context of this dramatic global pandemic. Results: The obtained results for the sex-related imbalance analysis indicate that this factor slightly affects the system performance in the Normal VS COVID-19 and Pneumonia VS COVID-19 approaches, although the identified differences are not relevant enough to worsen considerably the system’s response. Regarding the age-related imbalance analysis, this factor was observed to be again influencing the system in a more consistent way than the sex factor, as it was present in all the approaches. Once again, this worsening is not a major problem for our data and system, as it is not of great magnitude. Conclusions: Multiple studies have been conducted in other fields in order to determine if certain patient characteristics such as sex or age influenced these deep learning systems. However, to the best of our knowledge, this study has not been done for COVID-19 despite the urgency and lack of COVID-19 chest x-ray images. The presented results evidenced that the proposed methodology and tested approaches allow a robust and reliable analysis to support the clinical decision-making process in this pandemic scenario.

Download Full-text

Features of glomerular filtration rate evaluation for kidney function assessment in patients with rheumatoid arthritis

Medical alphabet ◽

10.33667/2078-5631-2020-15-44-48 ◽

2020 ◽

pp. 44-48

Author(s):

V. A. Aleksandrov ◽

L. N. Shilova ◽

A. V. Aleksandrov

Keyword(s):

Rheumatoid Arthritis ◽

Glomerular Filtration Rate ◽

Glomerular Filtration ◽

Cystatin C ◽

Filtration Rate ◽

Clinical Decision Making ◽

Clinical Decision ◽

Initial Assessment ◽

Serum Cystatin C ◽

Creatinine Concentration

The development of renal dysfunction in patients with rheumatoid arthritis (RA) is due to the presence and severity of autoimmune disorders, chronic systemic inflammation, a multiplicity of comorbid conditions, and pharmacotherapy features. The most important parameter that describes the general condition of the kidneys is glomerular filtration rate (GFR). This review presents the data on the possibilities of modern methods for determining estimated GFR (e-GFR) and the specificity of their use in various clinical situations that accompany the course of RA. For the initial assessment of GFR in patients with RA it is advisable to use the measurement of e-GFR based on serum creatinine concentration using the CKD-EPI equation (2009) (with or without indexing by body surface area). In cases where the e-GFR equations are not reliable enough or the results of this test are insufficient for clinical decision making, the serum cystatin C level should be measured and the combined GFR calculation based on creatinine and cystatin C should be used.

Download Full-text

Laboratory predictors of death from coronavirus disease 2019 (COVID-19) in the area of Valcamonica, Italy

Clinical Chemistry and Laboratory Medicine (CCLM) ◽

10.1515/cclm-2020-0459 ◽

2020 ◽

Vol 58 (7) ◽

pp. 1100-1105 ◽

Cited By ~ 16

Author(s):

Graziella Bonetti ◽

Filippo Manelli ◽

Andrea Patroni ◽

Alessandra Bettinardi ◽

Gianluca Borrelli ◽

...

Keyword(s):

Hospital Stay ◽

Clinical Decision Making ◽

Troponin I ◽

Laboratory Data ◽

High Sensitivity ◽

Clinical Decision ◽

International Normalized Ratio ◽

Serum Glucose ◽

Hospital Death ◽

Laboratory Findings

AbstractBackgroundComprehensive information has been published on laboratory tests which may predict worse outcome in Asian populations with coronavirus disease 2019 (COVID-19). The aim of this study is to describe laboratory findings in a group of Italian COVID-19 patients in the area of Valcamonica, and correlate abnormalities with disease severity.MethodsThe final study population consisted of 144 patients diagnosed with COVID-19 (70 who died during hospital stay and 74 who survived and could be discharged) between March 1 and 30, 2020, in Valcamonica Hospital. Demographical, clinical and laboratory data were collected upon hospital admission and were then correlated with outcome (i.e. in-hospital death vs. discharge).ResultsCompared to patients who could be finally discharged, those who died during hospital stay displayed significantly higher values of serum glucose, aspartate aminotransferase (AST), creatine kinase (CK), lactate dehydrogenase (LDH), urea, creatinine, high-sensitivity cardiac troponin I (hscTnI), prothrombin time/international normalized ratio (PT/INR), activated partial thromboplastin time (APTT), D-dimer, C reactive protein (CRP), ferritin and leukocytes (especially neutrophils), whilst values of albumin, hemoglobin and lymphocytes were significantly decreased. In multiple regression analysis, LDH, CRP, neutrophils, lymphocytes, albumin, APTT and age remained significant predictors of in-hospital death. A regression model incorporating these variables explained 80% of overall variance of in-hospital death.ConclusionsThe most important laboratory abnormalities described here in a subset of European COVID-19 patients residing in Valcamonica are highly predictive of in-hospital death and may be useful for guiding risk assessment and clinical decision-making.

Download Full-text