Machine Learning Tools for COVID-19 Patient Screening and Improved Laboratory Test Management to be Discussed at AACC Annual Scientific Meeting in 2021 |

0


ATLANTA, September 27, 2021 / PRNewswire / – Scientists have created a new machine learning tool that could help healthcare workers quickly detect and direct the flow of COVID-19 patients arriving at hospitals. The results of an evaluation of this algorithm, along with an artificial intelligence method that improves test uptake and reimbursement, were presented today at the AACC 2021 Annual Scientific Meeting and the clinical laboratory exhibit.

Streamline hospital admission for COVID-19 patients

It is important for clinicians to promptly diagnose COVID-19 patients upon arrival at the hospital, both to sort them out and to separate them from other vulnerable patients who may be immunocompromised or have pre-existing medical conditions. This can be difficult, however, as COVID-19 shares many symptoms with other viral infections, and the most accurate PCR tests for COVID-19 can take several days to show results.

A team of researchers led by Rana Zeeshan Haider, doctorate and Tahir Sultan Shamsi, FRCP, from the National Institute of Blood Diseases Karachi, Pakistan, therefore created a machine learning algorithm to help healthcare workers effectively screen for incoming COVID-19 patients. Scientists extracted routine diagnostic and demographic data from the charts of 21,672 patients presenting to hospitals and applied several statistical techniques to develop this algorithm, which is a predictive model that differentiates COVID-19 patients from non-COVID- 19. During validation experiments, the model performed with an accuracy of up to 92.5% when tested with an independent dataset and showed a negative predictive value of up to 96.9%. The latter means that the model is particularly reliable in identifying patients who do not have COVID-19.

“The true effectiveness of negative labeling in our research argues for its utility as a screening test for the rapid expulsion of SARS-CoV-2 from emergency departments, facilitating rapid care decisions, directing patient flow -cases and fulfilling the role of a ‘pre-test’ regarding RT-PCR tests ordered where this is not practical, “Haider said.” We offer this test to meet the challenge of critical diagnostic needs in resource-limited environments where molecular testing is not under the banner of routine testing panels. ”

Optimize the selection and reimbursement of laboratory tests

Of the 5 billion lab orders submitted each year, at least 20% are considered inappropriate. These inappropriate tests can lead to slower or incorrect diagnoses for patients. Such tests may also not be covered by Medicare if they were not intended to be used for specific medical conditions or if they were ordered with the wrong ICD-10 diagnostic codes, increasing the costs of health.

Rojeet Shrestha, PhD, of Patients Choice Laboratories at Indianapolis, set out with colleagues to determine whether an automated test management system known as the Laboratory Decision System (LDS) could help improve test ordering. The LDS scores potential tests based on medical necessity and test indications, helping providers minimize test misuse and select the best tests for a given medical condition.

Using LDS, the researchers reassessed a total of 374,423 test orders from a referral lab, of which 48,049 had not met criteria for Medicare coverage. For 96.4% of the first 10,000 test requests, the LDS ranking system recommended alternative tests that better matched the medical need or had a more appropriate ICD-10 code. Of those recommendations, 80.5% would also meet Medicare policies. All of this indicates that the LDS could help correct erroneous or inappropriate lab commands.

“Our study implies that the use of the LDS automated test ordering system would be extremely useful for providers, laboratories and payers,” said Shrestha. “Using this algorithm-based test selection and ordering database, which evaluates and scores potential tests for a given disease based on clinical relevance, medical necessity and indication for testing , would ultimately help providers select and order the right test and reduce over- and under-use of tests. “

Abstract information

Registration for the AACC Annual Scientific Meeting is free for members of the media. Journalists can register online here: https://www.xpressreg.net/register/aacc0921/media/landing.asp

Abstract A-226: Machine learning based decryption of cell population data; a promising hospital screening tool for COVID-19 will be presented at:

Presentation of the student poster

Monday September 27

9h005:00 p.m.

Scientific poster session

Tuesday, September 28

9:30 a.m. – 5:00 p.m. (present author of 1:30 p.m. – 2:30 p.m.)

Summary B-011: Using Artificial Intelligence for Efficient Use of Tests and to Increase Reimbursement will be presented at:

Scientific poster session

Wednesday September 29

9:30 a.m. – 5:00 p.m. (present author of 1:30 p.m. – 2:30 p.m.)

All sessions will take place in the Poster Room, located in Exhibit Hall C of the Georgia World Congress Center in Atlanta.

About the 2021 AACC Annual Scientific Meeting and Clinical Laboratory Exhibition

The AACC Annual Scientific Meeting offers 5 days filled with opportunities to learn about the exciting science of September 26-30. Plenary sessions explore COVID-19 vaccines and the evolution of the virus, research lessons from the pandemic, artificial intelligence in the clinic, miniaturization of diagnostic platforms and improvements in cystic fibrosis treatments.

At the AACC Clinical Lab Expo, more than 400 exhibitors will fill the Georgia World Congress Center show in Atlanta with displays of the latest diagnostic technologies including, but not limited to, COVID-19 testing, artificial intelligence, mobile health, molecular diagnostics, mass spectrometry, point of care, and automating.

About AACC

Dedicated to improving health through laboratory medicine, AACC brings together more than 50,000 clinical laboratory professionals, physicians, researchers and business leaders from around the world focused on clinical chemistry, molecular diagnostics, mass spectrometry, translational medicine, laboratory management and others. areas of progress in laboratory science. Since 1948, the AACC has strived to advance common interests in the field, delivering programs that advance scientific collaboration, knowledge, expertise and innovation. For more information visit www.aacc.org.

Christine DeLong

AACC

Senior Director, Communications and Public Relations

(p) 202.835.8722

[email protected]

Molly polen

AACC

Senior Director, Communications and Public Relations

(p) 202.420.7612

(c) 703.598.0472

[email protected]

View original content to download multimedia: https://www.prnewswire.com/news-releases/machine-learning-tools-for-covid-19-patient-screening-and-improved-lab-test-management-to -be-discussed-at-the-annual-scientific-meeting-aacc-2021-301385691.html

SOURCE AACC


Leave A Reply

Your email address will not be published.