China
Africa
Explore chapters and articles related to this topic
Innovative Nanobiosensors for Infectious Disease Diagnosis
Published in Suresh Kaushik, Vijay Soni, Efstathia Skotti, Nanosensors for Futuristic Smart and Intelligent Healthcare Systems, 2022
Amitesh Anand, Deependra Kumar Ban
Every diagnostic method is being put to test during the ongoing pandemic caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Among many, one challenge the entire scientific community is facing is in scaling up the testing without compromising the detection sensitivity. The rapid antigen test has serious limitations of relatively high false negatives and therefore requires further confirmation by the PCR based molecular test. This has taken its toll on the mechanisms of curbing the spread of the virus. This bottleneck has motivated the scientific community to develop simpler and reliable detection methods.
Developing epidemic forecasting models to assist disease surveillance for influenza with electronic health records
Published in International Journal of Computers and Applications, 2020
Episodes occurring between January 1, 2010, and December 31, 2015 with at least one influenza diagnosis (ICD-9 code: 487 and ICD-10 code: J09-J11) were defined as influenza cases [4]. According to EMRs, some of the patients received influenza tests, such as the influenza A/B virus rapid antigen test, influenza A/B IgG antibody test, influenza A/B RNA detection, and virus isolation and identification. To validate cases defined using EMRs, we evaluated the correlation between the EMR from CGMH and the data from the national disease surveillance system, including RODS and National Health Insurance (NHI) data, by using Pearson’s correlation, which assigns a value between −1 and + 1. A value greater than 0.7 or −0.7 shows a high correlation. In RODS, participating hospitals upload targeted diagnosis codes from emergency room visits on the system every day, and then, TCDC uses the data to detect possible infection outbreak at the earliest [4]. The NHI collected influenza-like illness codes from outpatient visits [7]. Both datasets are available in a weekly aggregated format at the following link: https://nidss.cdc.gov.tw/en/. Influenza cases from CGMH emergency room visits were compared with those from RODS, whereas influenza cases from CGMH outpatient visits were compared with those from NHI data. All analyses were performed using R software (v. 3.4.0, R Foundation for Statistical Computing, www.r-project.org/).
Automated Identification of COVID-19 from Chest X-Ray Images Using Machine Learning
Published in IETE Journal of Research, 2023
Debanshu Biswas, Abhaya Kumar Sahoo
Currently, most of the medical personnel take these steps to diagnose COVID-19: Various symptoms like body temperature, coughing, breathing problems etc. are diagnosed.Rapid Antigen Test (RAT) [2] is done.Real-time Reverse Transcription – Polymerase Chain Reaction (RT–PCR) [3] test is done.Finally, whether the patient has COVID-19 or not is determined.
COVID-19: a pandemic challenging healthcare systems
Published in IISE Transactions on Healthcare Systems Engineering, 2021
Lidong Wang, Cheryl Ann Alexander
Motivated by the severity of the pandemic and the use of AI in other areas of infectious disease control, researchers have developed a convolutional neural network that will help providers identify COVID-19 infections even quicker despite or in absence of a negative PCR test. This Chest XR should be used as an adjunct to rapid testing and the rtPCR testing (Mishra et al., 2020). Some of the benefits of using the convolutional AI neural network, COVID-NET, is that it is tailored for the identification of COVID-19 cases and contains cases that can help identify COVID-19, even when used as an adjunct with positive or negative rtPCRs or rapid antigen test to broaden the scope of testing for the disease. Within this database of AI convolutional neural networks will be comparable cases of COVID-19 for the provider to compare to the patient. COVID-NET is the first neural network to contain images and a projection-expansion-projection-extension (PEPX) design for providers (Wang et al., 2020; Vandenberg et al., 2020). This can help providers identify cases of COVID-19 by examining the database for similarities or other abnormalities and comparing them to the current CXR. This is a convenient and easy method of identifying and diagnosing CXR abnormalities within a patient with COVID-19. The CXR and Chest CT has become an excellent alternative to diagnose COVID-19 because the majority of patients present with a specific abnormal pattern to the radiograph or CT; ground-glass opacity, bilateral abnormalities, and interstitial abnormalities can be looked up in COVID-NET. COVID-NET, the neural network database serves as a strong representation of how COVID-19 affects the lungs and how providers can use the database to examine current COVID-19 CXRs to determine if a similar abnormality exists in the CXR. COVID-NET uses an explainability approach to patients with COVID-19 lung abnormalities and can be used as an adjunct to rtPCR testing and rapid testing due to the quick turnaround time for imaging and radiographical reads, especially since it is a test done anyway (Wang et al., 2020).