Commentary: Automated detection of preterm condition using uterine electromyography based topological features

A recently published study [1] proposed a machine learning classifier to detect preterm birth at an early stage of the pregnancy by making use of an envelope created from Fourier coefficients. The evaluation of this system within this study is, however, fundamentally flawed which resulted in overly optimistic near-perfect predictive performance measures being reported. (C) 2021 Nalecz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences. Published by Elsevier B.V. All rights reserved.

Automated summary

A recent study proposed a machine learning classifier to detect preterm birth early in pregnancy using a Fourier coefficient envelope. However, the evaluation of the system in the study was flawed, resulting in overly optimistic performance measures being reported.