• Politics
  • Diversity, equity and inclusion
  • Financial Decision Making
  • Telehealth
  • Patient Experience
  • Leadership
  • Point of Care Tools
  • Product Solutions
  • Management
  • Technology
  • Healthcare Transformation
  • Data + Technology
  • Safer Hospitals
  • Business
  • Providers in Practice
  • Mergers and Acquisitions
  • AI & Data Analytics
  • Cybersecurity
  • Interoperability & EHRs
  • Medical Devices
  • Pop Health Tech
  • Precision Medicine
  • Virtual Care
  • Health equity

Pregnancy-Adapted Algorithm Effectively Ruled Out Pulmonary Embolism in Suspected Patients

Article

The algorithm prevented the need for CT scans in nearly 40 percent of patients.

artificial intelligence

Researchers found that the pregnancy-adapted YEARS algorithm was able to safely rule out pulmonary embolism in pregnant women with suspected pulmonary embolism, according to a new study published in the New England Journal of Medicine.

Menno Huisman, M.D., Ph.D., professor of internal medicine and Leiden University in the Netherlands, told Inside Digital Health™ that there are two major problems with pulmonary embolisms. He said that there is a psychologically high suspicion of pulmonary embolisms because doctors and patients do not want to miss the disease and that there are no guidelines present that tell the optimal diagnostic pathway.

So, Huisman and the research team applied the YEARS algorithm and combined it with the D-dimer blood test. This method revealed the suspicion level of having a pulmonary embolism and allowed physicians to prevent the need for CT scans in 39 percent of patients.

The team found that the algorithm was very safe and efficient and were able to spare CT scans for 65 percent of patients in the first trimester — which is when radiation is potentially the most harmful to the fetus — 46 percent of patients during the second trimester and 32 percent of patients in the third trimester.

The algorithm was most efficient in the first trimester of pregnancy and lowest during the third.

The research team assessed three criteria from the YEARS algorithm — clinical signs of deep-vein thrombosis, hemoptysis and pulmonary embolism as the most likely diagnosis — and measured the D-dimer level.

Pulmonary embolism was ruled out if none of the three criteria were met and the D-dimer level was less than 1,000 nanograms per milliliter. The disease was also ruled out if one or more of the three criteria were met and the D-dimer level was less than 500 nanograms per milliliter.

The study included 498 participants and 494 of them had their suspected pulmonary embolism managed according to the YEARS algorithm. Of the 494 participants, 252 met none of the YEARS criteria, while 242 met one to three of the criteria.

Huisman said that the findings of this study are important for emergency department workers, physicians and patients alike, as the algorithm is an evidence-based diagnostic that many nursing units should be able to adopt. The algorithm can spare women a CT scan, reducing the potential harm to them or their fetus through radiation.

Although suspicion for pulmonary embolisms is high, it is psychosomatic, with only 4 percent of the participants being diagnosed at baseline.

Due to the psychological suspicion of the disease, the researcher’s method give patients answers more quickly than the traditional CT scan, which has the potential to take more than a day.

“Our algorithm provides solid evidence for the safe management of suspected pulmonary embolism in pregnant women, with selective use of CT pulmonary angiography,” the study authors wrote.

Get the best insights in healthcare analytics directly to your inbox.

Read More About AI

Google Finds that AI Can Improve Ophthalmologist's Accuracy

How Machine Learning Predicted Post-Cardiothoracic Surgery Complications

Mobile Machine-Learning Program Predicts Autism with High Accuracy

Related Videos
Image: Ron Southwick, Chief Healthcare Executive
George Van Antwerp, MBA
Edmondo Robinson, MD
Craig Newman
© 2024 MJH Life Sciences

All rights reserved.