AI Estimation of Gestational Age from Blind Ultrasound Sweeps in Low-Resource Settings
Open accessPublished version of a preprint
Abstract
BACKGROUND: Ultrasound is indispensable to gestational age estimation and thus to quality obstetrical care, yet high equipment cost and the need for trained sonographers limit its use in low-resource settings. METHODS: From September 2018 through June 2021, we recruited 4695 pregnant volunteers in North Carolina and Zambia and obtained blind ultrasound sweeps (cineloop videos) of the gravid abdomen alongside standard fetal biometry. We trained a neural network to estimate gestational age from the sweeps and, in three test data sets, assessed the performance of the artificial intelligence (AI) model and biometry against previously established gestational age. RESULTS: In our main test set, the mean absolute error (MAE) (±SE) was 3.9±0.12 days for the model versus 4.7±0.15 days for biometry (difference, -0.8 days; 95% confidence interval [CI], -1.1 to -0.5; P<0.001). The results were similar in North Carolina (difference, -0.6 days; 95% CI, -0.9 to -0.2) and Zambia (-1.0 days; 95% CI, -1.5 to -0.5). Findings were supported in the test set of women who conceived by in vitro fertilization (MAE of 2.8±0.28 vs. 3.6±0.53 days for the model vs. biometry; difference, -0.8 days; 95% CI, -1.7 to 0.2) and in the set of women from whom sweeps were collected by untrained users with low-cost, battery-powered devices (MAE of 4.9±0.29 vs. 5.4±0.28 days for the model vs. biometry; difference, -0.6; 95% CI, -1.3 to 0.1). CONCLUSIONS: When provided blindly obtained ultrasound sweeps of the gravid abdomen, our AI model estimated gestational age with accuracy similar to that of trained sonographers conducting standard fetal biometry. Model performance appears to extend to blind sweeps collected by untrained providers in Zambia using low-cost devices. (Funded by the Bill and Melinda Gates Foundation.).
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
An important limitation of GA AI models was application in very late stages of pregnancy due to the thickened texture of the fetal skull.
“or very late stages of pregnancy [146,147,152], the latter of which was due to the thickened texture of the fetal skull.”
From Evolving the Era of 5D Ultrasound? A Systematic Literature Review on the Applications for Artificial Intelligence Ultrasound Imaging in Obstetrics and Gynecology (2023) · cites this paper as [152]
The Discussion (page not provided) identifies a late-pregnancy limitation: scans were sparse beyond 37 weeks, and the model appeared to underestimate gestational age beyond that point in the novice test set. It does not attribute this limitation to thickening of the fetal skull; the Discussion says the image features used by the model are not known. (LLM, conf=0.88)
Experimental — accuracy not yet measuredA benefit of GA AI models was the possibility for application in low-resource countries.
“The benefits of the GA AI models were the possibility for application in low-resource countries [144,145,148,149,152]”
The purpose of the FAMLI studies was the successful establishment of an AI algorithm for GA estimation from simplified blind US sweeps of US novices in low-resource countries.
“The purpose of these studies, which were based on US data from the US and Zambia, was the successful establishment of an AI algorithm for GA estimation from simplified blind US sweeps of US novices in low-resource countries [144,145,152,153].”
GA AI models promised high accuracy with an error of 3.9 to 5 days in GA estimation.
“promising high accuracy with an error of 3.9 to 5 days in GA estimation [149,152].”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 23 · Cited by 80
Research works printed but not linked: 16
- [1]World Health Organization. WHO Recommendations on Antenatal Care for a Positive Pregnancy Experience. 2016 (https://www.who.int/reproductivehealth/publications/maternal_perinatal_health/anc-positive-pregnancy-experience/en/). 28079998
- [2]Kramer MS, McLean FH, Boyd ME, Usher RH. The validity of gestational age estimation by menstrual dating in term, preterm, and postterm gestations. JAMA 1988; 260: 3306– 3308. 3054193
- [3]Matsumoto S, Nogami Y, Ohkuri S. Statistical studies on menstruation: a criticism on the definition of normal menstruation. Gunma J Med Sci 1962; 11: 294– 318.
- [5]Yadav H, Shah D, Sayed S, Horton S, Schroeder LF. Availability of essential diagnostics in ten low-income and middle-income countries:results from national health facility surveys. Lancet Glob Health 2021; 9: e1553– e1560. DOI: 10.1016/S2214-109X(21)00442-3. 34626546 PMC8526361 · DOI
- [6]Marsh-Feiley G, Eadie L, Wilson P. Telesonography in emergency medicine: A systematic review. PLoS One 2018; 13: e0194840. DOI: 10.1371/journal.pone.0194840. 29723198 PMC5933714 · DOI
- [7]Becker DM, Tafoya CA, Becker SL, Kruger GH, Tafoya MJ, Becker TK. The use of portable ultrasound devices in low- and middle-income countries: a systematic review of the literature. Trop Med Int Health 2016; 21: 294– 311. DOI: 10.1111/tmi.12657. 26683523 · DOI
- [8]Carin L, Pencina MJ. On deep learning for medical image analysis. In: Livingston EH, Lewis RJ, eds. JAMA guide to statistics and methods. New York: McGraw-Hill Education, 2019; 1192– 1193. 30422287
- [10]Chi BH, Vwalika B, Killam WP, Implementation of the Zambia electronic perinatal record system for comprehensive prenatal and delivery care. Int J Gynaecol Obstet 2011; 113: 131– 136. DOI: 10.1016/j.ijgo.2010.11.013. 21315347 PMC3071887 · DOI
- [11]Price JT, Winston J, Vwalika B, Quantifying bias between reported last menstrual period and ultrasonography estimates of gestational age in Lusaka, Zambia. Int J Gynaecol Obstet 2019; 144: 9– 15. DOI: 10.1002/ijgo.12686. 30267538 PMC6283668 · DOI
- [12]Castillo MC, Fuseini NM, Rittenhouse K, The Zambian Preterm Birth Prevention Study (ZAPPS): cohort characteristics at enrollment. Gates Open Res 2019; 2: 25. DOI: 10.12688/gatesopenres.12820.3. 30706053 PMC6350406 · DOI
- [13]Price JT, Vwalika B, Rittenhouse KJ, Adverse birth outcomes and their clinical phenotypes in an urban Zambian cohort. Gates Open Res 2020; 3: 1533. DOI: 10.12688/gatesopenres.13046.2. 32161903 PMC7047437 · DOI
- [15]Vwalika B, Price JT, Rosenbaum A, Stringer JSA. Reducing the global burden of preterm births. Lancet Glob Health 2019; 7: e415. DOI: 10.1016/S2214-109X(19)30060-9. 30879504 · DOI
- [16]Gulshan V, Peng L, Coram M, Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 2016; 316: 2402– 2410. DOI: 10.1001/jama.2016.17216. 27898976 · DOI · Paper page
- [17]Milea D, Najjar RP, Zhubo J, Artificial intelligence to detect papilledema from ocular fundus photographs. N Engl J Med 2020; 382: 1687– 1695. DOI: 10.1056/NEJMoa1917130. 32286748 · DOI
- [18]McKinney SM, Sieniek M, Godbole V, International evaluation of an AI system for breast cancer screening. Nature 2020; 577: 89– 94. DOI: 10.1038/s41586-019-1799-6. 31894144 · DOI · Paper page
- [19]Esteva A, Kuprel B, Novoa RA, Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017; 542: 115– 118. DOI: 10.1038/nature21056. 28117445 PMC8382232 · DOI · Paper page
- Authors
- Pokaprakarn, T., Prieto, J. C., Price, J. T., Kasaro, M. P., Sindano, N., Shah, H. R., Peterson, M., Akapelwa, M. M., Kapilya, F. M., Sebastião, Y. V., Goodnight, W., Stringer, E. M., Freeman, B. L., Montoya, L. M., Chi, B. H., Rouse, D. J., Cole, S. R., Vwalika, B., Kosorok, M. R., & Stringer, J. S. A.
- Affiliations
- University of North Carolina at Chapel Hill (US)
- University of Zambia (ZM)
- UNC Global Projects–Zambia, LLC, Lusaka, Zambia
- Brown University (US)
- ORCID
- Venue
- NEJM Evidence
- Publisher
- Massachusetts Medical Society
- Published
- 2022-04-26
- Volume
- 1
- Issue
- 5
- ISSN
- 2766-5526 (ISSN-L)
- PMC
- PMC9980216
- OpenAlex
- W4220897813
- Cited by
- 80
- References
- 23
- Citations by year
- 2026: 26 · 2025: 14 · 2024: 20 · 2023: 12 · 2022: 8
- FWCI
- 4.07
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Locations
- NEJM Evidence (publishedVersion)
- medRxiv (acceptedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Funders
- Bill and Melinda Gates Foundation (INV-003266, OPP1191684)
- National Institutes of Health (UL1TR002489, AI50410)
- National Institute of Allergy and Infectious Diseases (R01AI157758, K24AI120796, P30AI050410)
- Fogarty International Center (K01TW010857)
- National Center for Advancing Translational Sciences
- Eunice Kennedy Shriver National Institute of Child Health and Human Development (T32HD075731)
- School of Medicine, University of North Carolina at Chapel Hill
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Health Sciences › Medicine › Pediatrics, Perinatology and Child Health › Prenatal Screening and Diagnostics
- Keywords
- gestational age estimation, artificial intelligence, artificial neural networks, fetal biometry, resource-limited settings, in vitro fertilization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
