Dataset Information

Accurate prediction of birth implementing a statistical model through the determination of steroid hormones in saliva.

ABSTRACT: Steroidal hormone interaction in pregnancy is crucial for adequate fetal evolution and preparation for childbirth and extrauterine life. Estrone sulphate, estriol, progesterone and cortisol play important roles in the initiation of labour mechanism at the start of contractions and cervical effacement. However, their interaction remains uncertain. Although several studies regarding the hormonal mechanism of labour have been reported, the prediction of date of birth remains a challenge. In this study, we present for the first time machine learning algorithms for the prediction of whether spontaneous labour will occur from week 37 onwards. Estrone sulphate, estriol, progesterone and cortisol were analysed in saliva samples collected from 106 pregnant women since week 34 by enzyme-immunoassay (EIA) techniques. We compared a random forest model with a traditional logistic regression over a dataset constructed with the values observed of these measures. We observed that the results, evaluated in terms of accuracy and area under the curve (AUC) metrics, are sensibly better in the random forest model. For this reason, we consider that machine learning methods contribute in an important way to the obstetric practice.

SUBMITTER: Alonso S

PROVIDER: S-EPMC7970941 | biostudies-literature | 2021 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Accurate prediction of birth implementing a statistical model through the determination of steroid hormones in saliva.

Alonso Silvia S Cáceres Sara S Vélez Daniel D Sanz Luis L Silvan Gema G Illera Maria Jose MJ Illera Juan Carlos JC

Scientific reports 20210310 1

Steroidal hormone interaction in pregnancy is crucial for adequate fetal evolution and preparation for childbirth and extrauterine life. Estrone sulphate, estriol, progesterone and cortisol play important roles in the initiation of labour mechanism at the start of contractions and cervical effacement. However, their interaction remains uncertain. Although several studies regarding the hormonal mechanism of labour have been reported, the prediction of date of birth remains a challenge. In this st ...[more]

PMID: 33692437

Similar Datasets

Project description:This paper describes a methodology for simultaneous determination of 19 steroid hormones, viz. estrone, estradiol, estriol, testosterone, 5α-dihydrotestosterone, androstenedione, androstenediol, dehydroepiandrosterone, progesterone, pregnenolone, 17α-OH-progesterone, 17α-OH-pregnenolone, cortisone, cortisol, 11-deoxycortisol, 11-deoxycorticosterone, 11-dehydrocorticosterone, aldosterone, and corticosterone, in 500-µL of urine or serum/plasma. The method was optimized using isotopically labeled internal standards and liquid-liquid extraction followed by detection using liquid chromatography-electrospray ionization-tandem mass spectrometry (LC-MS/MS). Dansylation of estrogens significantly improved their sensitivities (~11- to 23-fold) and chromatographic separation. The respective limit of detection (LOD) and limit of quantification (LOQ) of all analytes were 0.04−0.28 and 0.14−0.92 ng/mL in human urine, and 0.11−0.35 and 0.38−1.18 ng/mL in human serum/plasma. Recoveries of all analytes (except for progesterone) fortified at 10, 20, and 200 ng/mL in urine and serum were 80−120%, with standard deviations ranging from 0 to 17.3%. Repeated analysis of similarly fortified urine and serum samples yielded intra-day and inter-day variations of 0−21.7% and 0.16−11.5%, respectively. All analytes except cortisone exhibited weak matrix effects in urine and serum (−13.9−18.2%). The method was further validated through the analysis of the National Institute of Standards and Technology (NIST) plasma Standard Reference Material (SRM1950) with certified concentrations for cortisol, progesterone, and testosterone (coefficient of variation: 3−11%). The developed method was applied in the analysis of urine samples from 20 volunteers, which revealed the occurrence of 16 analytes with detection frequencies (DFs) > 80%. Furthermore, 15 analytes were found in plasma SRM1950, indicating the feasibility of our method in the analysis of steroid hormones in urine and serum/plasma. This method will facilitate analysis of steroid hormones in population-based biomonitoring studies.

Dataset Information

Accurate prediction of birth implementing a statistical model through the determination of steroid hormones in saliva.

Publications

Accurate prediction of birth implementing a statistical model through the determination of steroid hormones in saliva.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets