An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department

AbstractDuring the coronavirus disease 2019 (COVID-19) pandemic, rapid and accurate triage of patients at the emergency department is critical to inform decision-making. We propose a data-driven approach for automatic prediction of deterioration risk using a deep neural network that learns from chest X-ray images and a gradient boosting model that learns from routine clinical variables. Our AI prognosis system, trained using data from 3661 patients, achieves an area under the receiver operating characteristic curve (AUC) of 0.786 (95% CI: 0.745–0.830) when predicting deterioration within 96 hours. The deep neural network extracts informative areas of chest X-ray images to assist clinicians in interpreting the predictions and performs comparably to two radiologists in a reader study. In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at New York University Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time. In summary, our findings demonstrate the potential of the proposed system for assisting front-line physicians in the triage of COVID-19 patients.

Download Full-text

An Automated Lightweight Deep Neural Network for Diagnosis of COVID-19 from Chest X-ray Images

Arabian Journal for Science and Engineering ◽

10.1007/s13369-021-05956-2 ◽

2021 ◽

Author(s):

Soumya Ranjan Nayak ◽

Janmenjoy Nayak ◽

Utkarsh Sinha ◽

Vaibhav Arora ◽

Uttam Ghosh ◽

...

Keyword(s):

Neural Network ◽

Deep Neural Network ◽

X Ray ◽

Chest X Ray

Download Full-text

Detection of Tuberculosis from Chest X-Ray Images Based on Modified Inception Deep Neural Network Model

2020 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE) ◽

10.1109/wiecon-ece52138.2020.9397994 ◽

2020 ◽

Author(s):

Omar Tawhid Imam ◽

Moinul Haque ◽

Celia Shahnaz ◽

Sheikh Asif Imran ◽

Md. Tariqul Islam ◽

...

Keyword(s):

Neural Network ◽

Network Model ◽

Neural Network Model ◽

Deep Neural Network ◽

X Ray ◽

Chest X Ray

Download Full-text

MFDNN: Multi-channel feature deep neural network algorithm to identify Covid19 chest X-ray images

10.1101/2021.08.04.21261235 ◽

2021 ◽

Author(s):

Liangrui Pan ◽

boya ji ◽

Xiaoqi wang ◽

shaoliang peng

Keyword(s):

Neural Network ◽

Deep Learning ◽

Deep Neural Network ◽

Test Accuracy ◽

Learning Networks ◽

X Ray ◽

Network Algorithm ◽

Life Saving ◽

Chest X Ray ◽

Neural Network Algorithm

The use of chest X-ray images (CXI) to detect Severe Acute Respiratory Syndrome Coronavirus 2 (SARS CoV-2) caused by Coronavirus Disease 2019 (COVID-19) is life-saving important for both patients and doctors. This research proposed a multi-channel feature deep neural network algorithm to screen people infected with COVID-19. The algorithm integrates data oversampling technology and a multi-channel feature deep neural network model to carry out the training process in an end-to-end manner. In the experiment, we used a publicly available CXI database with 10,192 Normal, 6012 Lung Opacity (Non-COVID lung infection), and 1345 Viral Pneumonia images. Compared with traditional deep learning models (Densenet201, ResNet50, VGG19, GoogLeNet), the MFDNN model obtains an average test accuracy of 93.19% in all data. Furthermore, in each type of screening, the precision, recall, and F1 Score of the MFDNN model are also better than traditional deep learning networks. Secondly, compared with the latest CoroDet model, the MFDNN algorithm is 1.91% higher than the CoroDet model in the experiment of detecting the four categories of COVID19 infected persons. Finally, our experimental code will be placed at https://github.com/panliangrui/covid19.

Download Full-text

Appropriateness of emergency care use: a retrospective observational study based on professional versus patients’ perspectives in Taiwan

BMJ Open ◽

10.1136/bmjopen-2019-033833 ◽

2020 ◽

Vol 10 (5) ◽

pp. e033833

Author(s):

Chih-Yuan Lin ◽

Yue-Chune Lee

Keyword(s):

Emergency Department ◽

New York ◽

Health Insurance ◽

Characteristic Curve ◽

Estimating Equation ◽

Equation Model ◽

Sensitivity Analyses ◽

New York University ◽

Single Payer ◽

Explicit Process

ObjectiveThe objectives of this study are to refine the measurement of appropriate emergency department (ED) use and to provide a natural observation of appropriate ED use rates based on professional versus patient perspectives.SettingTaiwan has a population of 23 million, with one single-payer universal health insurance scheme. Taiwan has no limitations on ED use, and a low barrier to ED use may be a surrogate for natural observation of users’ perspectives in ED use.ParticipantsIn 7 years, there were 1 835 860 ED visits from one million random samples of the National Health Insurance Database.MeasuresAppropriate ED use was determined according to professional standards, measured by the modified Billings New York University Emergency Department (NYU-ED) algorithm, and further analysed after the addition of prudent patient standards, measured by explicit process-based and outcome-based criteria.Statistical analysesThe area under the receiver operating characteristic curve (AUC) was used to reflect the performance of appropriate ED use measures, and sensitivity analyses were conducted using different thresholds to determine the appropriateness of ED use. The generalised estimating equation model was used to measure the associations between appropriate ED use based on process and outcome criteria and covariates including sex, age, occupation, health status, place of residence, medical resources area, date and income level.ResultsAppropriate ED use based on professional criteria was 33.5%, which increased to 63.1% when patient criteria were added. The AUC, which combines both professional and patient criteria, was high (0.85).ConclusionsThe appropriate ED use rate nearly doubled when patient criteria were added to professional criteria. Explicit process-based and outcome-based criteria may be used as a supplementary measure to the implicit modified Billings NYU-ED algorithm when determining appropriate ED use.

Download Full-text