RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación
Artículo científico (JournalArticle)
New electrohysterogram-based estimators of intrauterine pressure signal, tonus and contraction peak for non-invasive labor monitoring
[EN] Background: Uterine activity monitoring is an essential part of managing the progress of pregnancy
and labor. Although intrauterine pressure (IUP) is the only reliable method of estimating uterine
mechanical activity, it is highly invasive. Since there is a direct relationship between the electrical and
mechanical activity of uterine cells, surface electrohysterography (EHG) has become a noninvasive
monitoring alternative. The Teager energy (TE) operator of the EHG signal has been used for IUP
continuous pressure estimation, although its accuracy could be improved. We aimed to develop new
optimized IUP estimation models for clinical application. Approach: We first considered enhancing
the optimal estimation of IUP clinical features (maximum pressure and tonus) rather than
optimizing the signal only (continuous pressure). An adaptive algorithm was also developed to deal
with inter-patient variability. For each optimizing signal feature (continuous pressure, maximum
pressure and tonus), individual (single patient), global (full database) and adaptive models were
built to estimate the recorded IUP signal. The results were evaluated by computing the root mean
square errors (RMSe): continuous pressure error (CPe), maximum pressure error (MPe) and
tonus error (TOe). Main results: The continuous pressure global model yielded IUP estimates with
Cpe = 14.61mm Hg, MPe = 29.17mm Hg and Toe = 7.8mm Hg. The adaptive models significantly
reduced errors to CPe = 11.88, MPe = 16.02 and Toe = 5.61mm Hg. The EHG-based IUP estimates
outperformed those from traditional tocographic recordings, which had significantly higher errors
(CPe = 21.93, MPe = 26.97, and TOe = 13.96). Significance: Our results show that adaptive models
yield better IUP estimates than the traditional approaches and provide the best balance of the
different errors computed for a better assessment of the labor progress and maternal and fetal wellbeing., This research project was supported by the Spanish Ministry of Economy and Competitiveness, the European Regional Development Fund (DPI2015-68397-R), and by the projects UPV_ FE-2018-C03 and GV/2018/104.