Machine learning-based tool can help screen COVID patients

By LabPulse.com staff writers

September 27, 2021 -- Researchers have developed a machine-learning algorithm that could help healthcare workers quickly screen and direct the flow of COVID-19 patients arriving at hospitals, according to a September 27 poster session at the 2021 American Association for Clinical Chemistry (AACC) annual meeting.

The team developed the algorithm using diagnostic and demographic data from 21,672 patient hospital records. The model can differentiate between COVID-19 and non-COVID-19 patients with an accuracy rate of up to 92.5%.

The model is particularly reliable when identifying patients who don't have COVID-19, showing a negative predictive value of up to 96.9%, according to the group, led by Rana Zeeshan Haider, PhD, and Dr. Tahir Sultan Shamsi of the National Institute of Blood Disease and Bone Marrow Transplantation in Karachi, Pakistan.

"The true negative labeling efficiency of our research advocates its utility as a screening test ... aiding prompt care decisions, directing patient-case flow, and fulfilling the role of a 'pretest' concerning orderly RT-PCR [reverse transcription polymerase chain reaction] testing where it is not handy," Haider said.

COVID-19 nasal swab causes leak in brain fluid
Clinicians treated a patient for a cerebrospinal fluid leak after a COVID-19 test with a nasal swab led to an injury at the base of his skull. Details...
COVIDome Explorer lets public decipher COVID pathology
A new multidimensional dataset for COVID-19 multiomics research has been released to the public, along with a free online research portal for analyzing...
Scientists develop spectroscopy-based COVID-19 triage tool
Attenuated total reflection Fourier-transform infrared spectroscopy is a rapid, low-cost tool that can be used to triage the severity of illness in patients...
AACC study details streamlined COVID testing protocol
A team of researchers has developed a new streamlined protocol for COVID-19 testing called SwabExpress. The protocol can increase the testing capacity...
AACC advises against Ct values for COVID patient care
The American Association for Clinical Chemistry (AACC) recently issued a public statement advising against using coronavirus test cycle threshold (Ct)...

Copyright © 2021 LabPulse.com

Last Updated bc 9/27/2021 6:44:14 AM