The sudden outbreak of novel coronavirus 2019 (COVID-19) increased the diagnostic burden of radiologists. In the time of an epidemic crisis, we hope artificial intelligence (AI) to reduce physician workload in regions with the outbreak, and improve the diagnosis accuracy for physicians before they could acquire enough experience with the new disease. In this paper, we present our experience in building and deploying an AI system that automatically analyzes CT images and provides the probability of infection to rapidly detect COVID-19 pneumonia. The proposed system which consists of classification and segmentation will save about 30%-40% of the detection time for physicians and promote the performance of COVID-19 detection. Specifically, working in an interdisciplinary team of over 30 people with medical and/or AI background, geographically distributed in Beijing and Wuhan, we are able to overcome a series of challenges ( data discrepancy, testing time-effectiveness of model, data security, etc.) in this particular situation and deploy the system in four weeks. In addition, since the proposed AI system provides the priority of each CT image with probability of infection, the physicians can confirm and segregate the infected patients in time. Using 1,136 training cases (723 positives for COVID-19) from five hospitals, we are able to achieve a sensitivity of 0.974 and specificity of 0.922 on the test dataset, which included a variety of pulmonary diseases.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7654325PMC
http://dx.doi.org/10.1016/j.asoc.2020.106897DOI Listing

Publication Analysis

Top Keywords

building deploying
8
probability infection
8
proposed system
8
covid-19
5
system
5
ai-assisted imaging
4
imaging analysis
4
analysis covid-19
4
covid-19 screening
4
screening building
4

Similar Publications

Achieving net-zero greenhouse gas emissions likely entails not only lowering emissions but also deploying carbon dioxide (CO) removal technologies. We explored the annual potential to store CO in building materials. We found that fully replacing conventional building materials with CO-storing alternatives in new infrastructure could store as much as 16.

View Article and Find Full Text PDF

Large language models (LLMs) offer promising applications in mental health care to address gaps in treatment and research. By leveraging clinical notes and transcripts as data, LLMs could improve diagnostics, monitoring, prevention, and treatment of mental health conditions. However, several challenges persist, including technical costs, literacy gaps, risk of biases, and inequalities in data representation.

View Article and Find Full Text PDF

Background: Current clinical decision support systems (DSS) are trained and validated on observational data from the clinic in which the DSS is going to be applied. This is problematic for treatments that have already been validated in a randomized clinical trial (RCT), but have not yet been introduced in any clinic. In this work, we report on a method for training and validating the DSS core before introduction to a clinic, using the RCT data themselves.

View Article and Find Full Text PDF

Applying the Surge Capacity Components for Capacity-Building Purposes in the Context of the EMT Initiative.

Int J Environ Res Public Health

December 2024

CRIMEDIM (Center for Research and Training in Disaster Medicine, Humanitarian Aid and Global Health), Università del Piemonte Orientale, 13100 Vercelli, Italy.

Background: On 16 January 2021 (EB148/18 Session), the World Health Organization (WHO) and Member States emphasized the importance of expanding the WHO Emergency Medical Teams (EMT) Initiative, investing in a global health workforce and multidisciplinary teams capable of being rapidly deployed, equipped, and fully trained to respond to all-hazard emergencies effectively. This resulted in the need to define a comprehensive framework. To achieve this, the EMT Initiative proposes the application of the four components of Surge Capacity, known as the 4"S" (Staff, Systems, Supplies, and Structure/Space), to build global capacities and capabilities, ensuring rapid mobilization and efficient coordination of national and international medical teams for readiness and response, complying with crisis standards of care defined in an ethical and evidence-based manner.

View Article and Find Full Text PDF

Background: Primary health care (PHC) services face operational challenges due to high patient volumes, leading to complex management needs. Patients access services through booked appointments and walk-in visits, with walk-in visits often facing longer waiting times. No-show appointments are significant contributors to inefficiency in PHC operations, which can lead to an estimated 3%-14% revenue loss, disrupt resource allocation, and negatively impact health care quality.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!