Extract
Pulmonary embolism (PE) is a major cause of morbidity and mortality [1]. Computed tomography pulmonary angiography (CTPA) is the gold standard for diagnosing PE [2] and a common investigation which contributes to potentially avoidable radiation exposure. CTPA use has quadrupled in the past two decades [3], and this has been associated with lower rates of PE detection [4] and possible overdiagnosis [5].
Abstract
Combining novel machine learning algorithms with extended D-dimer cut-offs may improve pulmonary embolism prediction and reduce patient radiation exposure resulting from avoidable scans https://bit.ly/3oUKd7X
Footnotes
Author contributions: A.N. Franciosi conceptualised the study and design, performed data analysis, wrote the manuscript and is the co-lead author. N. McCarthy co-designed the study, performed data analysis, performed machine learning analyses and is the co-lead author. B. Gaffney, J. Duignan, E. Sweeney and N. O'Connell performed data collection, preliminary data coding and participated in study design. K. Murphy, F. Ní Áinle, M.W. Butler, J.D. Dodd, M.P. Keane and D.J. Murphy consulted on study design, performed internal review and edited the manuscript. K.M. Curran and C. McCarthy participated in study design, performed internal review and edited the final manuscript. C. McCarthy is the senior author and had full access to all the data in the study, and takes responsibility for the integrity of the data and the accuracy of the data analysis.
Conflict of interest: The authors report no conflict of interests.
- Received November 22, 2021.
- Accepted February 7, 2022.
- Copyright ©The authors 2022. For reproduction rights and permissions contact permissions{at}ersnet.org