scholarly journals Early Prediction of In-Hospital Death of COVID-19 Patients: A Machine-Learning Model Based on Age, Blood Analyses, and Chest X-Ray Score

2021 ◽  
Author(s):  
Emirena Garrafa ◽  
Marika Vezzoli ◽  
Marco Ravanelli ◽  
Davide Farina ◽  
Andrea Borghesi ◽  
...  
Keyword(s):  
Hospital Mortality ◽  
Characteristic Curve ◽  
Hospital Death ◽  
Web Based ◽  
X Ray ◽  
Neutrophil Lymphocyte Ratio ◽  
Patient Allocation ◽  
Chest X Ray ◽  
Blood Analytes ◽  
Second Wave

Background: To develop and validate an early-warning model to predict in-hospital mortality on admission of COVID-19 patients at an emergency department (ED).<br /> Methods: In total, 2782 patients were enrolled between March 2020 and December 2020, including 2106 patients (first wave) and 676 patients (second wave) in the COVID-19 outbreak in Italy. The first wave patients were divided into two groups with 1474 patients used to train the model, and 632 to validate it. The 676 patients in the second wave were used to test the model. Age, 17 blood analytes and Brescia chest X-ray score were the variables processed using a Random Forests classification algorithm to build and validate the model. ROC analysis was used to assess the model performances. A web-based death-risk calculator was implemented and integrated within the Laboratory Information System of the hospital. Results: The final score was constructed by age (the most powerful predictor), blood analytes (the strongest predictors were lactate dehydrogenase, D-dimer, Neutrophil/Lymphocyte ratio, C-reactive protein, Lymphocyte %, Ferritin std and Monocyte %), and Brescia chest X-ray score. The areas under the receiver operating characteristic curve obtained for the three groups (training, validating and testing) were 0.98, 0.83 and 0.78, respectively.<br />Conclusions: The model predicts in-hospital mortality on the basis of data that can be obtained in a short time, directly at the ED on admission. It functions as a web-based calculator, providing a risk score which is easy to interpret. It can be used in the triage process to support the decision on patient allocation.

scholarly journals Early prediction of in-hospital death of COVID-19 patients: a machine-learning model based on age, blood analyses, and chest x-ray score

eLife ◽  
2021 ◽  
Vol 10 ◽  
Author(s):  
Emirena Garrafa ◽  
Marika Vezzoli ◽  
Marco Ravanelli ◽  
Davide Farina ◽  
Andrea Borghesi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Hospital Mortality ◽  
Learning Model ◽  
Hospital Death ◽  
Web Based ◽  
X Ray ◽  
Machine Learning Model ◽  
Chest X Ray ◽  
Blood Analytes ◽  
Second Wave

An early-warning model to predict in-hospital mortality on admission of COVID-19 patients at an emergency department (ED) was developed and validate using a Machine-Learning model. In total, 2782 patients were enrolled between March 2020 and December 2020, including 2106 patients (first wave) and 676 patients (second wave) in the COVID-19 outbreak in Italy. The first-wave patients were divided into two groups with 1474 patients used to train the model, and 632 to validate it. The 676 patients in the second wave were used to test the model. Age, 17 blood analytes and Brescia chest X-ray score were the variables processed using a Random Forests classification algorithm to build and validate the model. ROC analysis was used to assess the model performances. A web-based death-risk calculator was implemented and integrated within the Laboratory Information System of the hospital. The final score was constructed by age (the most powerful predictor), blood analytes (the strongest predictors were lactate dehydrogenase, D-dimer, Neutrophil/Lymphocyte ratio, C-reactive protein, Lymphocyte %, Ferritin std and Monocyte %), and Brescia chest X-ray score. The areas under the receiver operating characteristic curve obtained for the three groups (training, validating and testing) were 0.98, 0.83 and 0.78, respectively. The model predicts in-hospital mortality on the basis of data that can be obtained in a short time, directly at the ED on admission. It functions as a web-based calculator, providing a risk score which is easy to interpret. It can be used in the triage process to support the decision on patient allocation.

scholarly journals COVID outcome prediction in the emergency department (COPE): using retrospective Dutch hospital data to develop simple and valid models for predicting mortality and need for intensive care unit admission in patients who present at the emergency department with suspected COVID-19

BMJ Open ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. e051468
Author(s):  
David van Klaveren ◽  
Alexandros Rekkas ◽  
Jelmer Alsma ◽  
Rob J C G Verdonschot ◽  
Dick T J J Koning ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Emergency Department ◽  
Intensive Care ◽  
Outcome Prediction ◽  
Characteristic Curve ◽  
Hospital Death ◽  
Hospital Data ◽  
Dutch Hospital ◽  
Icu Admission ◽  
Second Wave

ObjectivesDevelop simple and valid models for predicting mortality and need for intensive care unit (ICU) admission in patients who present at the emergency department (ED) with suspected COVID-19.DesignRetrospective.SettingSecondary care in four large Dutch hospitals.ParticipantsPatients who presented at the ED and were admitted to hospital with suspected COVID-19. We used 5831 first-wave patients who presented between March and August 2020 for model development and 3252 second-wave patients who presented between September and December 2020 for model validation.Outcome measuresWe developed separate logistic regression models for in-hospital death and for need for ICU admission, both within 28 days after hospital admission. Based on prior literature, we considered quickly and objectively obtainable patient characteristics, vital parameters and blood test values as predictors. We assessed model performance by the area under the receiver operating characteristic curve (AUC) and by calibration plots.ResultsOf 5831 first-wave patients, 629 (10.8%) died within 28 days after admission. ICU admission was fully recorded for 2633 first-wave patients in 2 hospitals, with 214 (8.1%) ICU admissions within 28 days. A simple model—COVID outcome prediction in the emergency department (COPE)—with age, respiratory rate, C reactive protein, lactate dehydrogenase, albumin and urea captured most of the ability to predict death. COPE was well calibrated and showed good discrimination for mortality in second-wave patients (AUC in four hospitals: 0.82 (95% CI 0.78 to 0.86); 0.82 (95% CI 0.74 to 0.90); 0.79 (95% CI 0.70 to 0.88); 0.83 (95% CI 0.79 to 0.86)). COPE was also able to identify patients at high risk of needing ICU admission in second-wave patients (AUC in two hospitals: 0.84 (95% CI 0.78 to 0.90); 0.81 (95% CI 0.66 to 0.95)).ConclusionsCOPE is a simple tool that is well able to predict mortality and need for ICU admission in patients who present to the ED with suspected COVID-19 and may help patients and doctors in decision making.

scholarly journals Fibrinogen as a Prognostic Predictor in Pediatric Patients with Sepsis: A Database Study

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Xiaomeng Tang ◽  
Lujing Shao ◽  
Jiaying Dou ◽  
Yiping Zhou ◽  
Min Chen ◽  
...  
Keyword(s):  
Hospital Mortality ◽  
Pediatric Patients ◽  
Cell Injury ◽  
Characteristic Curve ◽  
Vascular Endothelial Cell ◽  
Hospital Death ◽  
Training Set ◽  
Database Study ◽  
Validation Set ◽  
Pediatric Sepsis

Background. Systemic inflammatory response and vascular endothelial cell injury during sepsis lead to coagulopathy. Fibrinogen has been reported as a biomarker of coagulopathy; however, the prognostic value of fibrinogen remains undefined in pediatric patients with sepsis. The aim of this study was to assess fibrinogen level on pediatric intensive care unit (PICU) admission and to elucidate the relationship between fibrinogen levels and in-hospital mortality in children with sepsis. Methods. We conducted a database study. The sepsis database was divided into a training set (between July 2014 and June 2018) and a validation set (from July 2018 to June 2019). The clinical and laboratory parameters on PICU admission and in-hospital mortality in sepsis database were collected and analyzed. Results. A total of 819 pediatric patients were included from database as a training set. The overall hospital mortality was 12.1% (99/819). The fibrinogen levels were significantly lower in nonsurvivors than survivors. Multivariate logistic regression analysis showed significant associations between fibrinogen, lactate level, and hospital mortality (fibrinogen: odds ratio (OR), 0.767 (95% CI: 0.628-0.937), P=0.009; lactate: OR, 1.346 (95% CI: 1.217-1.489), P<0.001, respectively), which was confirmed in a validation set (0.616 [95% CI: 0.457-0.829], P=0.001; 1.397 [95% CI: 1.245-1.569], P<0.001, respectively). The hospital mortality of patients with fibrinogen<1 g/L, 1-2 g/L, 2-3 g/L, or over 3 g/L displayed an obvious difference (62.5% vs. 27.66% vs. 18.1% vs. 4.2%, respectively). Furthermore, the area under the receiver operating characteristic curve (ROC) for fibrinogen in predicting hospital mortality was 0.780 (95% CI: 0.711-0.850) in pediatric patients with sepsis. Conclusions. Fibrinogen is a valuable prognostic biomarker for pediatric sepsis. The level of fibrinogen lower than 2 g/L on PICU admission is closely related to the greater risk of hospital death in pediatric sepsis.

scholarly journals Risk Factors and a Scoring System to Predict ARDS in Patients with COVID-19 Pneumonia in Korea: A Multicenter Cohort Study

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Jun-Won Seo ◽  
Seong Eun Kim ◽  
Eun Young Choi ◽  
Kyung Soo Hong ◽  
Tae Hoon Oh ◽  
...  
Keyword(s):  
Prediction Score ◽  
World Health ◽  
Case Report Form ◽  
C Reactive Protein ◽  
Multicenter Cohort Study ◽  
X Ray ◽  
Neutrophil Lymphocyte Ratio ◽  
Reactive Protein ◽  
Chest X Ray ◽  
Epidemiological Characteristics

Predictive studies of acute respiratory distress syndrome (ARDS) in patients with coronavirus disease 2019 (COVID-19) are limited. In this study, the predictors of ARDS were investigated and a score that can predict progression to ARDS in patients with COVID-19 pneumonia was developed. All patients who were diagnosed with COVID-19 pneumonia between February 1, 2020, and May 15, 2020, at five university hospitals in Korea were enrolled. Their demographic, clinical, and epidemiological characteristics and the outcomes were collected using the World Health Organization COVID-19 Case Report Form. A logistic regression analysis was performed to determine the predictors for ARDS. The receiver operating characteristic (ROC) curves were constructed for the scoring model. Of the 166 patients with COVID-19 pneumonia, 37 (22.3%) patients developed ARDS. The areas under the curves for the infiltration on a chest X-ray, C-reactive protein, neutrophil/lymphocyte ratio, and age, for prediction of ARDS were 0.91, 0.90, 0.87, and 0.80, respectively (all P < 0.001 ). The COVID-19 ARDS Prediction Score (CAPS) was constructed using age (≥60 years old), C-reactive protein (≥5 mg/dL), and the infiltration on a chest X-ray (≥22%), with each predictor allocated 1 point. The area under the curve of COVID-19 ARDS prediction score (CAPS) for prediction of ARDS was 0.90 (95% CI 0.86–0.95; P < 0.001 ). It provided 100% sensitivity and 75% specificity when the CAPS score cutoff value was 2 points. CAPS, which consists of age, C-reactive protein, and the area of infiltration on a chest X-ray, was predictive of the development of ARDS in patients with COVID-19 pneumonia.

scholarly journals An Explainable Artificial Intelligence based Prospective Framework for COVID-19 Risk Prediction

2021 ◽  
Author(s):  
Vishal Sharma ◽  
Piyush   ◽  
Samarth Chhatwal ◽  
Bipin Singh
Keyword(s):  
Artificial Intelligence ◽  
Risk Prediction ◽  
Infection Risk ◽  
Alternative Methods ◽  
Confirmatory Test ◽  
Rt Pcr ◽  
Web Based ◽  
X Ray ◽  
Explainable Artificial Intelligence ◽  
Chest X Ray

Given the spread of COVID-19 to vast geographical regions and populations, it is not feasible to undergo or recommend the RT-PCR based tests to all individuals with flu-like symptoms. The reach of RT-PCR based testing is still limited due to the high cost of the test and huge population in few countries. Thus, alternative methods for COVID-19 infection risk prediction can be useful. We built an explainable artificial intelligence (AI) based integrated web-based prospective framework for COVID-19 risk prediction. We employed a two-step procedure for the non-clinical prediction of COVID19 infection risk. In the first step we assess the initial risk of COVID19 infection based on carefully selected parameters associated with COVID-19 positive symptoms from recent research. Generally, X-ray scans are cheaper and easily available in most government and private health centres. Therefore, based on the outcome of the computed initial risk in first step, we further provide an optional prediction using the chest X-ray scans in the second step of our proposed AI based prospective framework. Since there is a bottleneck to undergo an expensive RT-PCR based confirmatory test in economically backward nations, this is a crucial part of our explainable AI based prospective framework. The initial risk assessment outcome is analysed in combination with the advanced deep learning-based analysis of chest X-ray scans to provide an accurate prediction of COVID-19 infection risk. This prospective web-based AI framework can be employed in limited resource settings after clinical validation in future. The cost and time associated with the adoption of this prospective AI based prospective framework will be minimal and hence it will be beneficial to majority of the population living in low-income settings such as small towns and rural areas that have limited access to advanced healthcare facilities.

scholarly journals Detection of Lung Cancer Disease using Machine Learning

2020 ◽  
Vol 9 (5) ◽  
pp. 810-812
Keyword(s):  
Lung Cancer ◽  
Lung Tumor ◽  
The Body ◽  
Cancer Disease ◽  
Web Based ◽  
X Ray ◽  
Chest X Ray ◽  
Clear Idea ◽  
Web Based System ◽  
Disease Present

Cancer causes cell to split uncontrollably. Lung Cancer results in rapid cell growth and division of such infected cell, such growth of cells called tumor. Lung is the first organ where lung tumor begins and can spread to lymph nodes and so on. Early identification of lung cancer would facilitate in sparing a large no. of lives. If we compare death rates in any cancer then lung cancer has highest mortally rate. This article presents an automated web-based system for disease detection in lung using X-Ray images. To identify disease in lung in X-ray images, as it provides detailed picture and gives clear idea of lung in the body. For this project dataset of chest x-ray was taken from Kaggle. Using Mobile Net model we predicted the lung disease. Using this approach, we can early detect the disease present in lung which causes lung cancer

Abstract 13157: Deep Learning for Detection of Elevated Pulmonary Artery Wedge Pressure Using Standard Chest X-ray

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Yukina Hirata ◽  
Kenya Kusunose ◽  
Hirotsugu Yamada ◽  
Takumasa Tsuji ◽  
Kohei Fujimori ◽  
...  
Keyword(s):  
Heart Failure ◽  
Deep Learning ◽  
Characteristic Curve ◽  
Objective Evaluation ◽  
Left Ventricular ◽  
Training Dataset ◽  
Heart Catheterization ◽  
X Ray ◽  
Chest X Ray ◽  
Wedge Pressure

Introduction: Chest X-ray (CXR) is a useful and economical modality for the detection of congestive heart failure. However, the accuracy is limited by the subjective nature of its interpretation. Deep learning (DL) can be used to recognize diseases or findings objectively in various imaging modalities, and may outperform previous diagnostic techniques. Hypothesis: We hypothesized that DL-based analysis of CXR detect the presence of elevated pulmonary arterial wedge pressure (PAWP) in patients with suspected heart failure. Methods: We enrolled 1,013 patients with paired right heart catheterization and CXR performed from October 2009 to February 2020 in our hospital. DL algorithm for the detection of elevated PAWP was developed using the training dataset, based on a single CXR image. Independent evaluation cohort of 115 patients was performed using CXR-based DL model and echocardiographic data to detect the presence of high PAWP. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of the DL-based models compared with echocardiographic data. Results: The study included 1,013 patients (mean age, 67±13 years; 569 males [56%]). The mean PAWP was 12.5±6.4 mmHg and 218 patients (22%) had more than 18mmHg. To detect high PAWP, the AUC produced by DL algorithms was effective, and the DL algorithm with the largest AUC was ResNet50. In an evaluation cohort, to detect high PAWP, the AUC using the DL model with CXR was similar to the AUC produced by the echocardiographic left ventricular diastolic dysfunction algorithm (0.77 vs. 0.70; respectively; p=0.27), and significantly higher than the AUC by measurements of echocardiographic parameters (ResNet50 vs. other parameters; all compared p <0.05) (Figure) . Conclusions: The present results demonstrated that DL based on analysis of CXR can detect the presence of high PAWP. This finding suggests that the DL based approach may support an objective evaluation of CXR in the clinical setting.

Potential of deep learning in assessing pneumoconiosis depicted on digital chest radiography

2020 ◽  
Vol 77 (9) ◽  
pp. 597-602
Author(s):  
Xiaohua Wang ◽  
Juezhao Yu ◽  
Qiao Zhu ◽  
Shuqiang Li ◽  
Zanmei Zhao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Classification Performance ◽  
X Ray ◽  
Testing Dataset ◽  
Learning Techniques ◽  
History Of ◽  
Digital Chest ◽  
Chest X Ray

ObjectivesTo investigate the potential of deep learning in assessing pneumoconiosis depicted on digital chest radiographs and to compare its performance with certified radiologists.MethodsWe retrospectively collected a dataset consisting of 1881 chest X-ray images in the form of digital radiography. These images were acquired in a screening setting on subjects who had a history of working in an environment that exposed them to harmful dust. Among these subjects, 923 were diagnosed with pneumoconiosis, and 958 were normal. To identify the subjects with pneumoconiosis, we applied a classical deep convolutional neural network (CNN) called Inception-V3 to these image sets and validated the classification performance of the trained models using the area under the receiver operating characteristic curve (AUC). In addition, we asked two certified radiologists to independently interpret the images in the testing dataset and compared their performance with the computerised scheme.ResultsThe Inception-V3 CNN architecture, which was trained on the combination of the three image sets, achieved an AUC of 0.878 (95% CI 0.811 to 0.946). The performance of the two radiologists in terms of AUC was 0.668 (95% CI 0.555 to 0.782) and 0.772 (95% CI 0.677 to 0.866), respectively. The agreement between the two readers was moderate (kappa: 0.423, p<0.001).ConclusionOur experimental results demonstrated that the deep leaning solution could achieve a relatively better performance in classification as compared with other models and the certified radiologists, suggesting the feasibility of deep learning techniques in screening pneumoconiosis.

Sign in / Sign up

Export Citation Format

Share Document