Use of artificial intelligence for gestational age estimation: a systematic review and meta-analysis
IntroductionEstimating a reliable gestational age (GA) is essential in providing appropriate care during pregnancy. With advancements in data science, there are several publications on the use of artificial intelligence (AI) models to estimate GA using ultrasound (US) images. The aim of this meta-an...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Global Women's Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fgwh.2025.1447579/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582043325693952 |
|---|---|
| author | Sabahat Naz Sahir Noorani Syed Ali Jaffar Zaidi Abdu R. Rahman Saima Sattar Jai K. Das Jai K. Das Zahra Hoodbhoy |
| author_facet | Sabahat Naz Sahir Noorani Syed Ali Jaffar Zaidi Abdu R. Rahman Saima Sattar Jai K. Das Jai K. Das Zahra Hoodbhoy |
| author_sort | Sabahat Naz |
| collection | DOAJ |
| description | IntroductionEstimating a reliable gestational age (GA) is essential in providing appropriate care during pregnancy. With advancements in data science, there are several publications on the use of artificial intelligence (AI) models to estimate GA using ultrasound (US) images. The aim of this meta-analysis is to assess the accuracy of AI models in assessing GA against US as the gold standard.MethodsA literature search was performed in PubMed, CINAHL, Wiley Cochrane Library, Scopus, and Web of Science databases. Studies that reported use of AI models for GA estimation with US as the reference standard were included. Risk of bias assessment was performed using Quality Assessment for Diagnostic Accuracy Studies-2 (QUADAS-2) tool. Mean error in GA was estimated using STATA version-17 and subgroup analysis on trimester of GA assessment, AI models, study design, and external validation was performed.ResultsOut of the 1,039 studies screened, 17 were included in the review, and of these 10 studies were included in the meta-analysis. Five (29%) studies were from high-income countries (HICs), four (24%) from upper-middle-income countries (UMICs), one (6%) from low-and middle-income countries (LMIC), and the remaining seven studies (41%) used data across different income regions. The pooled mean error in GA estimation based on 2D images (n = 6) and blind sweep videos (n = 4) was 4.32 days (95% CI: 2.82, 5.83; l2: 97.95%) and 2.55 days (95% CI: −0.13, 5.23; l2: 100%), respectively. On subgroup analysis based on 2D images, the mean error in GA estimation in the first trimester was 7.00 days (95% CI: 6.08, 7.92), 2.35 days (95% CI: 1.03, 3.67) in the second, and 4.30 days (95% CI: 4.10, 4.50) in the third trimester. In studies using deep learning for 2D images, those employing CNN reported a mean error of 5.11 days (95% CI: 1.85, 8.37) in gestational age estimation, while one using DNN indicated a mean error of 5.39 days (95% CI: 5.10, 5.68). Most studies exhibited an unclear or low risk of bias in various domains, including patient selection, index test, reference standard, flow and timings and applicability domain.ConclusionPreliminary experience with AI models shows good accuracy in estimating GA. This holds tremendous potential for pregnancy dating, especially in resource-poor settings where trained interpreters may be limited.Systematic Review RegistrationPROSPERO, identifier (CRD42022319966). |
| format | Article |
| id | doaj-art-a495408b4f5b4ebba0bff5108a46595a |
| institution | Kabale University |
| issn | 2673-5059 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Global Women's Health |
| spelling | doaj-art-a495408b4f5b4ebba0bff5108a46595a2025-01-30T06:22:58ZengFrontiers Media S.A.Frontiers in Global Women's Health2673-50592025-01-01610.3389/fgwh.2025.14475791447579Use of artificial intelligence for gestational age estimation: a systematic review and meta-analysisSabahat Naz0Sahir Noorani1Syed Ali Jaffar Zaidi2Abdu R. Rahman3Saima Sattar4Jai K. Das5Jai K. Das6Zahra Hoodbhoy7Department of Pediatrics and Child Health, The Aga Khan University, Karachi, PakistanDepartment of Pediatrics and Child Health, The Aga Khan University, Karachi, PakistanDepartment of Pediatrics and Child Health, The Aga Khan University, Karachi, PakistanInstitute for Global Health and Development, The Aga Khan University, Karachi, PakistanDepartment of Pediatrics and Child Health, The Aga Khan University, Karachi, PakistanDepartment of Pediatrics and Child Health, The Aga Khan University, Karachi, PakistanInstitute for Global Health and Development, The Aga Khan University, Karachi, PakistanDepartment of Pediatrics and Child Health, The Aga Khan University, Karachi, PakistanIntroductionEstimating a reliable gestational age (GA) is essential in providing appropriate care during pregnancy. With advancements in data science, there are several publications on the use of artificial intelligence (AI) models to estimate GA using ultrasound (US) images. The aim of this meta-analysis is to assess the accuracy of AI models in assessing GA against US as the gold standard.MethodsA literature search was performed in PubMed, CINAHL, Wiley Cochrane Library, Scopus, and Web of Science databases. Studies that reported use of AI models for GA estimation with US as the reference standard were included. Risk of bias assessment was performed using Quality Assessment for Diagnostic Accuracy Studies-2 (QUADAS-2) tool. Mean error in GA was estimated using STATA version-17 and subgroup analysis on trimester of GA assessment, AI models, study design, and external validation was performed.ResultsOut of the 1,039 studies screened, 17 were included in the review, and of these 10 studies were included in the meta-analysis. Five (29%) studies were from high-income countries (HICs), four (24%) from upper-middle-income countries (UMICs), one (6%) from low-and middle-income countries (LMIC), and the remaining seven studies (41%) used data across different income regions. The pooled mean error in GA estimation based on 2D images (n = 6) and blind sweep videos (n = 4) was 4.32 days (95% CI: 2.82, 5.83; l2: 97.95%) and 2.55 days (95% CI: −0.13, 5.23; l2: 100%), respectively. On subgroup analysis based on 2D images, the mean error in GA estimation in the first trimester was 7.00 days (95% CI: 6.08, 7.92), 2.35 days (95% CI: 1.03, 3.67) in the second, and 4.30 days (95% CI: 4.10, 4.50) in the third trimester. In studies using deep learning for 2D images, those employing CNN reported a mean error of 5.11 days (95% CI: 1.85, 8.37) in gestational age estimation, while one using DNN indicated a mean error of 5.39 days (95% CI: 5.10, 5.68). Most studies exhibited an unclear or low risk of bias in various domains, including patient selection, index test, reference standard, flow and timings and applicability domain.ConclusionPreliminary experience with AI models shows good accuracy in estimating GA. This holds tremendous potential for pregnancy dating, especially in resource-poor settings where trained interpreters may be limited.Systematic Review RegistrationPROSPERO, identifier (CRD42022319966).https://www.frontiersin.org/articles/10.3389/fgwh.2025.1447579/fullgestational age estimationfetal ultrasoundartificial intelligenceaccuracypregnancy |
| spellingShingle | Sabahat Naz Sahir Noorani Syed Ali Jaffar Zaidi Abdu R. Rahman Saima Sattar Jai K. Das Jai K. Das Zahra Hoodbhoy Use of artificial intelligence for gestational age estimation: a systematic review and meta-analysis Frontiers in Global Women's Health gestational age estimation fetal ultrasound artificial intelligence accuracy pregnancy |
| title | Use of artificial intelligence for gestational age estimation: a systematic review and meta-analysis |
| title_full | Use of artificial intelligence for gestational age estimation: a systematic review and meta-analysis |
| title_fullStr | Use of artificial intelligence for gestational age estimation: a systematic review and meta-analysis |
| title_full_unstemmed | Use of artificial intelligence for gestational age estimation: a systematic review and meta-analysis |
| title_short | Use of artificial intelligence for gestational age estimation: a systematic review and meta-analysis |
| title_sort | use of artificial intelligence for gestational age estimation a systematic review and meta analysis |
| topic | gestational age estimation fetal ultrasound artificial intelligence accuracy pregnancy |
| url | https://www.frontiersin.org/articles/10.3389/fgwh.2025.1447579/full |
| work_keys_str_mv | AT sabahatnaz useofartificialintelligenceforgestationalageestimationasystematicreviewandmetaanalysis AT sahirnoorani useofartificialintelligenceforgestationalageestimationasystematicreviewandmetaanalysis AT syedalijaffarzaidi useofartificialintelligenceforgestationalageestimationasystematicreviewandmetaanalysis AT abdurrahman useofartificialintelligenceforgestationalageestimationasystematicreviewandmetaanalysis AT saimasattar useofartificialintelligenceforgestationalageestimationasystematicreviewandmetaanalysis AT jaikdas useofartificialintelligenceforgestationalageestimationasystematicreviewandmetaanalysis AT jaikdas useofartificialintelligenceforgestationalageestimationasystematicreviewandmetaanalysis AT zahrahoodbhoy useofartificialintelligenceforgestationalageestimationasystematicreviewandmetaanalysis |