Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Multicenter Study
. 2022 Sep 7;24(9):e38727.
doi: 10.2196/38727.

Newborn Skin Maturity Medical Device Validation for Gestational Age Prediction: Clinical Trial

Zilma Silveira Nogueira Reis #  1   2   3 , Roberta Maia de Castro Romanelli  4 , Rodney Nascimento Guimarães #  2 , Juliano de Souza Gaspar  2 , Gabriela Silveira Neves #  5 , Marynea Silva do Vale #  6 , Paulo de Jesus Nader #  7 , Martha David Rocha de Moura #  8 , Gabriela Luíza Nogueira Vitral #  4 , Marconi Augusto Aguiar Dos Reis #  4 , Marcia Margarida Mendonça Pereira #  6 , Patrícia Franco Marques #  6 , Silvana Salgado Nader #  7 , Augusta Luize Harff #  7 , Ludmylla de Oliveira Beleza #  8 , Maria Eduarda Canellas de Castro #  8 , Rayner Guilherme Souza #  2 , Gisele Lobo Pappa #  3   9 , Regina Amélia Pessoa Lopes de Aguiar #  10
Affiliations
Multicenter Study

Newborn Skin Maturity Medical Device Validation for Gestational Age Prediction: Clinical Trial

Zilma Silveira Nogueira Reis et al. J Med Internet Res. .

Abstract

Background: Early access to antenatal care and high-cost technologies for pregnancy dating challenge early neonatal risk assessment at birth in resource-constrained settings. To overcome the absence or inaccuracy of postnatal gestational age (GA), we developed a new medical device to assess GA based on the photobiological properties of newborns' skin and predictive models.

Objective: This study aims to validate a device that uses the photobiological model of skin maturity adjusted to the clinical data to detect GA and establish its accuracy in discriminating preterm newborns.

Methods: A multicenter, single-blinded, and single-arm intention-to-diagnosis clinical trial evaluated the accuracy of a novel device for the detection of GA and preterm newborns. The first-trimester ultrasound, a second comparator ultrasound, and data regarding the last menstrual period (LMP) from antenatal reports were used as references for GA at birth. The new test for validation was performed using a portable multiband reflectance photometer device that assessed the skin maturity of newborns and used machine learning models to predict GA, adjusted for birth weight and antenatal corticosteroid therapy exposure.

Results: The study group comprised 702 pregnant women who gave birth to 781 newborns, of which 366 (46.9%) were preterm newborns. As the primary outcome, the GA as predicted by the new test was in line with the reference GA that was calculated by using the intraclass correlation coefficient (0.969, 95% CI 0.964-0.973). The paired difference between predicted and reference GAs was -1.34 days, with Bland-Altman limits of -21.2 to 18.4 days. As a secondary outcome, the new test achieved 66.6% (95% CI 62.9%-70.1%) agreement with the reference GA within an error of 1 week. This agreement was similar to that of comparator-LMP-GAs (64.1%, 95% CI 60.7%-67.5%). The discrimination between preterm and term newborns via the device had a similar area under the receiver operating characteristic curve (0.970, 95% CI 0.959-0.981) compared with that for comparator-LMP-GAs (0.957, 95% CI 0.941-0.974). In newborns with absent or unreliable LMPs (n=451), the intent-to-discriminate analysis showed correct preterm versus term classifications with the new test, which achieved an accuracy of 89.6% (95% CI 86.4%-92.2%), while the accuracy for comparator-LMP-GA was 69.6% (95% CI 65.3%-73.7%).

Conclusions: The assessment of newborn's skin maturity (adjusted by learning models) promises accurate pregnancy dating at birth, even without the antenatal ultrasound reference. Thus, the novel device could add value to the set of clinical parameters that direct the delivery of neonatal care in birth scenarios where GA is unknown or unreliable.

International registered report identifier (irrid): RR2-10.1136/bmjopen-2018-027442.

Keywords: age; baby; childbirth; device; equipment and supplies; gestational age; learning model; machine learning; medical; newborn; pregnancy; pregnant; prematurity; reproductive health; skin; skin physiological phenomena; therapy; trimester; ultrasound.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: The authors declare a patent deposit on behalf of the Universidade Federal de Minas Gerais and Fundação de Amparo a Pesquisa de Minas Gerais, Brazil. The inventors were ZSNR, RNG, and BR1020170235688 (CTIT-PN862). BirthTech, a spin-off company, received a license to produce and commercialize this technology, and RNG is its founder. No sponsor had any role in the study design, data collection, data analysis, data interpretation, writing, or decision to submit the manuscript.

Figures

Figure 1
Figure 1
The new device and its simulated application on a newborn doll.
Figure 2
Figure 2
Correlation plot between the skin reflectance of the newborn and the reference gestational age at birth.
Figure 3
Figure 3
Flow diagram of participants throughout the study with results for the predictive model. GA: gestational age; US: ultrasound.
Figure 4
Figure 4
The distribution of estimated gestational age at birth by the established methods evaluated in this study. GA: gestational age; LMP: last menstrual period; US: ultrasound.
Figure 5
Figure 5
Correlation between GAs as measured using medical devices, established methods of pregnancy dating, and Bland-Altman plots. GA: gestational age; LMP: last menstrual period; US: ultrasound.
Figure 6
Figure 6
Box plot of day differences between methods and reference GA, with the proportion of agreement within 7 days. GA: gestational age; LMP: last menstrual period; US: ultrasound.
Figure 7
Figure 7
Receiver operating characteristic curves for the models to distinguish between term and preterm newborns. AUROC: area under the receiver operating characteristic curve; GA: gestational age; LMP: last menstrual period; US: ultrasound.
See this image and copyright information in PMC

References

    1. Walani SR. Global burden of preterm birth. Int J Gynaecol Obstet. 2020 Jul;150(1):31–3. doi: 10.1002/ijgo.13195. - DOI - PubMed
    1. Oza S, Cousens SN, Lawn JE. Estimation of daily risk of neonatal death, including the day of birth, in 186 countries in 2013: a vital-registration and modelling-based study. Lancet Glob Health. 2014 Nov;2(11):e635–44. doi: 10.1016/S2214-109X(14)70309-2. https://linkinghub.elsevier.com/retrieve/pii/S2214-109X(14)70309-2 S2214-109X(14)70309-2 - DOI - PubMed
    1. Torres M, Valstar MF, Henry C, Ward C, Sharkey D. Small sample deep learning for newborn gestational age estimation. Proceedings of the 12th IEEE International Conference on Automatic Face & Gesture Recognition; FG '17; May 30-June 3, 2017; Washington, DC, USA. 2017. pp. 79–86. - DOI
    1. Guo X, Li X, Qi T, Pan Z, Zhu X, Wang H, Dong Y, Yue H, Sun B. A birth population-based survey of preterm morbidity and mortality by gestational age. BMC Pregnancy Childbirth. 2021 Apr 10;21(1):291. doi: 10.1186/s12884-021-03726-4. https://bmcpregnancychildbirth.biomedcentral.com/articles/10.1186/s12884... 10.1186/s12884-021-03726-4 - DOI - DOI - PMC - PubMed
    1. Kim ET, Singh K, Moran A, Armbruster D, Kozuki N. Obstetric ultrasound use in low and middle income countries: a narrative review. Reprod Health. 2018 Jul 20;15(1):129. doi: 10.1186/s12978-018-0571-y. https://reproductive-health-journal.biomedcentral.com/articles/10.1186/s... 10.1186/s12978-018-0571-y - DOI - DOI - PMC - PubMed

Publication types