Prediction of low birth weight from fetal ultrasound and clinical characteristics: a comparative study between a low- and middle-income and a high-income country
Open accessAbstract
Introduction: Adverse perinatal outcomes (APO) pose a significant global challenge, particularly in low- and middle-income countries (LMICs). This study aims to analyse two cohorts of high-risk pregnant women for APO to comprehend risk factors and improve prediction accuracy. Methods: We considered an LMIC and a high-income country (HIC) population to derive XGBoost classifiers to predict low birth weight (LBW) from a comprehensive set of maternal and fetal characteristics including socio-demographic, past and current pregnancy information, fetal biometry and fetoplacental Doppler measurements. Data were sourced from the FeDoC (Fetal Doppler Collaborative) study (Pakistan, LMIC) and theIMPACT (Improving Mothers for a Better PrenAtal Care Trial) study (Spain, HIC), and included 520 and 746 pregnancies assessed from 28 weeks gestation, respectively. The models were trained on varying subsets of the mentioned characteristics to evaluate their contribution in predicting LBW cases. For external validation, and to highlight potential differential risk factors for LBW, we investigated the generalisation of these models across cohorts. Models’ performance was evaluated through the area under the curve (AUC), and their interpretability was assessed using SHapley Additive exPlanations. Results: In FeDoC, Doppler variables demonstrated the highest value at predicting LBW compared with biometry and maternal clinical data (AUC Doppler, 0.67; AUC Clinical, 0.65; AUC Biometry, 0.63), and its combination with maternal clinical data yielded the best prediction (AUC Clinical+Doppler, 0.71). In IMPACT, fetal biometry emerged as the most predictive set (AUC Biometry, 0.75; AUC Doppler, 0.70; AUC Clinical, 0.69) and its combination with Doppler and maternal clinical data achieved the highest accuracy (AUC Clinical+Biometry+Doppler, 0.81). External validation consistently indicated that biometry combined with Doppler data yielded the best prediction. Conclusions: Our findings provide new insights into the predictive role of different clinical and ultrasound descriptors in two populations at high risk for APO, highlighting that different approaches are required for different populations. However, Doppler data improves prediction capabilities in both settings, underscoring the value of standardising ultrasound data acquisition, as practiced in HIC, to enhance LBW prediction in LMIC. This alignment contributes to bridging the health equity gap.
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?
Doppler ultrasound features - such as umbilical artery S/D ratios - provided strong discriminatory signals, consistent with clinical understanding of uteroplacental insufficiency.
“Similarly, Doppler ultrasound features – such as umbilical artery S/D ratios – provided strong discriminatory signals, consistent with clinical understanding of uteroplacental insufficiency.15”
From Early detection of severe fetal growth restriction using multimodal deep learning based on ultrasound and prenatal biomarkers (2026) · cites this paper as [15]
The Results report that Doppler features helped predict low birth weight, and the Introduction links fetoplacental blood-flow changes to uteroplacental insufficiency. But Methods specifies umbilical artery pulsatility index, not an umbilical artery systolic/diastolic (S/D) ratio; the paper therefore does not support the claim about that particular feature. Page numbers are unavailable in our copy. (LLM, conf=0.88)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569 · see citing works
Liu, L., Oza, S., Hogan, D., Chu, Y., Perin, J., Zhu, J., Lawn, J. E., Cousens, S., Mathers, C., & Black, R. E. (2016) · The Lancet · doi:10.1016/s0140-6736(16)31593-8 · Cited by 3,453 · see citing works
Collins, G. S., Reitsma, J. B., Altman, D. G., & Moons, K. (2015) · BMC Medicine · doi:10.1186/s12916-014-0241-z · Cited by 1,927 · see citing works
Bhutta, Z. A., Das, J. K., Bahl, R., Lawn, J. E., Salam, R. A., Paul, V. K., Sankar, M. J., Blencowe, H., Rizvi, A., Chou, V. B., et al. (2014) · The Lancet · doi:10.1016/s0140-6736(14)60792-3 · Cited by 1,367 · see citing works
Blencowe, H., Krasevec, J., de Onis, M., Black, R. E., An, X., Stevens, G. A., Borghi, E., Hayashi, C., Estevez, D., Cegolon, L., et al. (2019) · The Lancet Global Health · doi:10.1016/s2214-109x(18)30565-5 · Cited by 1,242 · see citing works
Intrauterine Growth Restriction: Antenatal and Postnatal Aspects
Sharma, D. K., Shastri, S., & Sharma, P. K. (2016) · Clinical Medicine Insights Pediatrics · doi:10.4137/cmped.s40070 · Cited by 887 · see citing works
Lees, C. C., Stampalija, T., Baschat, A. A., da Silva Costa, F., Ferrazzi, E., Figueras, F., Hecher, K., Kingdom, J., Poon, L. C., Salomon, L. J., et al. (2020) · Ultrasound in Obstetrics & Gynecology · doi:10.1002/uog.22134 · Cited by 886 · see citing works
Wahl, B., Cossy-Gantner, A., Germann, S., & Schwalbe, N. R. (2018) · BMJ Global Health · doi:10.1136/bmjgh-2018-000798 · Cited by 796 · see citing works
Estimating fetal age: computer-assisted analysis of multiple fetal growth parameters.
Hadlock, F. P., Deter, R. L., Harrist, R. B., & Park, S. K. (1984) · Radiology · doi:10.1148/radiology.152.2.6739822 · Cited by 561 · see citing works
(2013) · Obstetrics and Gynecology · doi:10.1097/01.aog.0000437385.88715.4a · Cited by 495 · see citing works
Lawn, J. E., Ohuma, E. O., Bradley, E., Idueta, L. S., Hazel, E., Okwaraji, Y. B., Erchick, D. J., Yargawa, J., Katz, J., Lee, A. C., et al. (2023) · The Lancet · doi:10.1016/s0140-6736(23)00522-6 · Cited by 391 · see citing works
Customized birthweight standards for a Spanish population
Figueras, F., Meler, E., Iraola, A., Eixarch, E., Coll, O., Figueras, J., Francis, A., Gratacós, E., & Gardosi, J. O. (2007) · European Journal of Obstetrics & Gynecology and Reproductive Biology · doi:10.1016/j.ejogrb.2006.12.015 · Cited by 387 · see citing works
Self-citationPapageorghiou, A. T., Kennedy, S., Salomon, L. J., Altman, D. G., Ohuma, E. O., Stones, W. R., Gravett, M. G., Barros, F. C., Victora, C. G., Purwar, M., et al. (2018) · American Journal of Obstetrics and Gynecology · doi:10.1016/j.ajog.2018.01.011 · Cited by 301 · see citing works
Čikeš, M., Sanchez‐Martinez, S., Claggett, B. L., Duchateau, N., Piella, G., Butakoff, C., Pouleur, A., Knappe, D., Biering‐Sørensen, T., Kutyifa, V., et al. (2018) · European Journal of Heart Failure · doi:10.1002/ejhf.1333 · Cited by 266 · see citing works
Self-citationSmall vulnerable newborns—big potential for impact
Ashorn, P., Ashorn, U., Muthiani, Y., Aboubaker, S., Askari, S., Bahl, R., Black, R. E., Dalmiya, N., Duggan, C., Hofmeyr, G. J., et al. (2023) · The Lancet · doi:10.1016/s0140-6736(23)00354-9 · Cited by 239 · see citing works
Lundgren, E. M., Cnattingius, S., Jönsson, B., & Tuvemo, T. (2001) · Pediatric Research · doi:10.1203/00006450-200107000-00017 · Cited by 238 · see citing works
Finken, M. J. J., van der Steen, M., Smeets, C. C. J., Walenkamp, M. J. E., de Bruin, C., Hokken-Koelega, A., & Wit, J. M. (2018) · Endocrine Reviews · doi:10.1210/er.2018-00083 · Cited by 220 · see citing works
Kuhle, S., Maguire, B. R., Zhang, H., Hamilton, D. C., Allen, A. C., Joseph, K. S., & Allen, V. M. (2018) · BMC Pregnancy and Childbirth · doi:10.1186/s12884-018-1971-2 · Cited by 166 · see citing works
Morris, R. K., Johnstone, E., Lees, C., Morton, V. H., & Smith, G. C. S. (2024) · BJOG An International Journal of Obstetrics & Gynaecology · doi:10.1111/1471-0528.17814 · Cited by 160 · see citing works
Pusdekar, Y. V., Patel, A., Kurhe, K., Bhargav, S., Thorsten, V., Garcés, A., Goldenberg, R. L., Goudar, S. S., Saleem, S., Esamai, F., et al. (2020) · Reproductive Health · doi:10.1186/s12978-020-01029-z · Cited by 158 · see citing works
Dunn, L., Sherrell, H. C., & Kumar, S. (2017) · Placenta · doi:10.1016/j.placenta.2017.02.006 · Cited by 124 · see citing works
Machine Learning in Fetal Cardiology: What to Expect
Garcia-Canadilla, P., Sanchez-Martinez, S., Crispi, F., & Bijnens, B. (2020) · Fetal Diagnosis and Therapy · doi:10.1159/000505021 · Cited by 123 · see citing works
Crovetto, F., Crispi, F., Casas, R. M., Martín-Asuero, A., Borràs, R., Vieta, E., Estruch, R., Gratacós, E., IMPACT BCN Trial Investigators, Paulés, C., et al. (2021) · JAMA · doi:10.1001/jama.2021.20178 · Cited by 118 · see citing works
Self-citationPredicting risks of low birth weight in Bangladesh with machine learning
Pollob, S. M. A. I., Abedin, M. M., Islam, M. T., Islam, M. M., & Maniruzzaman, M. (2022) · PLoS ONE · doi:10.1371/journal.pone.0267190 · Cited by 68 · see citing works
Khan, W., Zaki, N., Masud, M. M., Ahmad, A., Ali, L., Ali, N., & Ahmed, L. A. (2022) · Scientific Reports · doi:10.1038/s41598-022-14393-6 · Cited by 68 · see citing works
Main Patterns of Fetal Cardiac Remodeling
Crispi, F., Sepúlveda-Martínez, Á., Crovetto, F., Gómez, O., Bijnens, B. H., & Gratacós, E. (2020) · Fetal Diagnosis and Therapy · doi:10.1159/000506047 · Cited by 64 · see citing works
Self-citationMachine learning-based approach for predicting low birth weight
Ranjbar, A., Montazeri, F., Farashah, M. V., Mehrnoush, V., Darsareh, F., & Roozbeh, N. (2023) · BMC Pregnancy and Childbirth · doi:10.1186/s12884-023-06128-w · Cited by 62 · see citing works
Machine learning algorithms for predicting low birth weight in Ethiopia
Bekele, W. T. (2022) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-022-01981-9 · Cited by 61 · see citing works
Miranda, J., Rodríguez‐López, M., Triunfo, S., Sairanen, M., Kouru, H., Parra-Saavedra, M. A., Crovetto, F., Figueras, F., Crispi, F., & Gratacós, E. (2016) · Ultrasound in Obstetrics and Gynecology · doi:10.1002/uog.17393 · Cited by 60 · see citing works
Self-citationFetal growth restriction and stillbirth: Biomarkers for identifying at risk fetuses
King, V. J., Bennet, L., Stone, P. R., Clark, A., Gunn, A. J., & Dhillon, S. K. (2022) · Frontiers in Physiology · doi:10.3389/fphys.2022.959750 · Cited by 52 · see citing works
Kumar, S. N., Saxena, P., Patel, R., et al. (2020) · Reproductive Toxicology · doi:10.1016/j.reprotox.2020.03.009 · Cited by 43 · see citing works
The health workforce crisis in Pakistan: a critical review and the way forward.
Abdullah, M. A., Mukhtar, F., Wazir, S., Gilani, I., Gorar, Z. A., & Shaikh, B. T. (2014) · PubMed · Cited by 40 · see citing works
A Machine Learning Approach to Monitor the Emergence of Late Intrauterine Growth Restriction
Pini, N., Lucchini, M., Esposito, G., et al. (2021) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2021.622616 · Cited by 30 · see citing works
Interpreting the role of nuchal fold for fetal growth restriction prediction using machine learning
Teng, L. Y., Mattar, C. N. Z., Biswas, A., Hoo, W. L., & Saw, S. N. (2022) · Scientific Reports · doi:10.1038/s41598-022-07883-0 · Cited by 29 · see citing works
García‐Canadilla, P., Crispi, F., Cruz-Lemini, M., Triunfo, S., Nadal, A., Valenzuela‐Alcaráz, B., Rudenick, P. A., Gratacós, E., & Bijnens, B. H. (2015) · Placenta · doi:10.1016/j.placenta.2015.07.130 · Cited by 17 · see citing works
Self-citationPatterson, J. K., Thorsten, V., Eggleston, B. S., et al. (2023) · BMC Pregnancy and Childbirth · doi:10.1186/s12884-023-05866-1 · Cited by 16 · see citing works
Machine learning from fetal flow waveforms to predict adverse perinatal outcomes: a study protocol
Hoodbhoy, Z. A., Hasan, B. S., Jehan, F., Bijnens, B. H., & Chowdhury, D. (2018) · Gates Open Research · doi:10.12688/gatesopenres.12796.1 · Cited by 13 · see citing works
Self-citationRisk scores for predicting small for gestational age infants in Japan: The TMM birthree cohort study
Iwama, N., Obara, T., Ishikuro, M., Murakami, K., Ueno, F., Noda, A., Onuma, T., Matsuzaki, F., Hoshiai, T., Saito, M., et al. (2022) · Scientific Reports · doi:10.1038/s41598-022-12892-0 · Cited by 13 · see citing works
Punyapet, P., Suwanrath, C., Chainarong, N., Sawaddisan, R., & Vichitkunakorn, P. (2023) · International Journal of Gynecology & Obstetrics · doi:10.1002/ijgo.14721 · Cited by 9 · see citing works
Lian, C., Wang, Y., Bao, X., Yang, L., Liu, G., Hao, D., Zhang, S., Yang, Y., Li, X., Yu, M., et al. (2022) · Frontiers in Surgery · doi:10.3389/fsurg.2022.951908 · Cited by 7 · see citing works
Hasan, B. S., Hoodbhoy, Z. A., Khan, A., Nogueira, M. A., Bijnens, B. H., & Chowdhury, D. (2023) · BMJ Paediatrics Open · doi:10.1136/bmjpo-2023-002134 · Cited by 5 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 1
- [33]Lundberg S Lee SI A unified approach to interpreting model predictions arXiv 2017
Cited by
Sorted by citations
Wang, J., Wang, J., Peng, Y., Hou, F., Zhang, X., & Jin, H. (2026) · Annals of Medicine · doi:10.1080/07853890.2026.2688297
“8,15,16 A model based on first-trimester clinical, Doppler, and biochemical parameters reported an AUC of 0.82, suggesting early detection is feasible.”
Influential
- Authors
- Sanchez-Martinez, S., Marti-Castellote, P. M., Hoodbhoy, Z., Bernardino, G., Prats-Valero, J., Aguado, A. M., Testa, L., Piella, G., Crovetto, F., Snyder, C., Mohsin, S., Nizar, A., Ahmed, R., Jehan, F., Jenkins, K., Gratacós, E., Crispi, F., Chowdhury, D., Hasan, B. S., & Bijnens, B.
- Affiliations
- Department of Engineering, Universitat Pompeu Fabra, Barcelona, Spain
- Aga Khan University (PK)
- Universitat Pompeu Fabra (ES)
- Hospital Sant Joan de Déu Barcelona (ES)
- Cardiology Care for Children, Lancaster, Pennsylvania, USA
- Sindh Institute of Urology and Transplantation (PK)
- Boston Children's Hospital (US)
- Institució Catalana de Recerca i Estudis Avançats (ES)
- ORCID
- Venue
- BMJ Global Health
- Publisher
- BMJ
- Published
- 2024-12
- Volume
- 9
- Issue
- 12
- Pages
- e016088
- ISSN
- 2059-7908 (ISSN-L)
- PMC
- PMC11624760
- OpenAlex
- W4405037977
- Cited by
- 9
- References
- 41
- Citations by year
- 2026: 5 · 2025: 4
- FWCI
- 4.95
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- BMJ Global Health (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Repositori digital de la UPF (Universitat Pompeu Fabra) (publishedVersion, cc-by)
- Lirias (submittedVersion, cc-by)
- eCommons - AKU (Aga Khan University) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- Grand Challenges in Global Health (INV-021528)
- Topics
- Health Sciences › Medicine › Obstetrics and Gynecology › Pregnancy and preeclampsia studies
- Health Sciences › Health Professions › General Health Professions › Maternal and Neonatal Healthcare
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- prenatal ultrasound, fetal biometry, perinatal complications, high-risk pregnancy, XGBoost, SHAP, external validation, low- and middle-income countries, high-income countries, risk factors, impact studies
- MeSH terms
- Adult, Developing Countries, Female, Humans, Infant, Low Birth Weight, Infant, Newborn, Pakistan, Pregnancy, Risk Factors, Spain, Ultrasonography, Prenatal, Developed Countries
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
