Predictive modeling with machine learning for low birth weight in the state of São Paulo: a retrospective population-based study
Keywords:
Infant, low birth weight, Machine learning, Predictive learning model, Logistic models, Random forest, Infant, newborn, Pregnancy, Prenatal care, Health policyAbstract
BACKGROUND: Low birth weight (LBW) is a major public health concern associated with increased neonatal morbidity and mortality.
OBJECTIVE: This study was aimed to develop a predictive learning model using machine learning techniques to identify LBW from live birth data.
METHODS: A retrospective population-based study was conducted using data from the Brazilian Live Birth Information System (SINASC), which includes all live births registered in the state of São Paulo between 2019 and 2023. After data curation and exclusion of records with missing or unknown information, a total of 2,548,570 live births were analyzed. Predictors included maternal sociodemographic characteristics, obstetric history, prenatal care indicators, and newborn characteristics. Logistic regression and random forest models were trained using an 80/20 train–test split, with class imbalance addressed through class weighting. Model performance was evaluated using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC).
RESULTS: The analysis showed that the balanced logistic regression model performed best in terms of sensitivity (0.688), F1-score (0.567), and AUC-ROC (0.850). A proportional analysis of the variables between the LBW and normal-weight groups revealed a higher prevalence of LBW among mothers with low education levels, without a partner, of Black or Brown ethnicity, aged ≤ 19 years or ≥ 35 years, with multiple pregnancies, with a reduced number of prenatal consultations, and with late initiation of prenatal care.
CONCLUSIONS: The findings highlight the importance of large-scale data analysis supported by machine learning techniques to inform public policies aimed at preventing LBW and promoting maternal and child health.
Downloads
References
1. World Health Organization (WHO). WHO [Internet]. Geneva; 2025 [cited 2026 May 11]. ICD-11 for Mortality and Morbidity Statistics. Available from: https://icd.who.int/browse/2025-01/mms/en.
2. Okwaraji YB, Krasevec J, Bradley E, et al. National, regional, and global estimates of low birthweight in 2020, with trends from 2000: a systematic analysis. The Lancet. 2024 Mar;403(10431):1071–80. https://doi.org/10.1016/S0140-6736(23)01198-4.
3. Brasil. Ministério da Saúde. Informações de Saúde (TABNET) – DATASUS [Internet]. 2023 [cited 2026 May 15]. Available from: https://datasus.saude.gov.br/informacoes-de-saude-tabnet/.
4. Gaíva MAM, Lopes FSP, Mufato LF, Ferreira SMB. Fatores associados à mortalidade neonatal em recém-nascidos de baixo peso ao nascer. Revista Eletrônica Acervo Saúde. 2020 Aug 13;12(11):e4831. https://doi.org/10.25248/reas.e4831.2020.
5. Vale CCR, Almeida NKDO, Almeida RMVRD. Association between Prenatal Care Adequacy Indexes and Low Birth Weight Outcome. Rev Bras Ginecol Obstet. 2021 Apr;43(04):256–63. https://doi.org/10.1055/s-0041-1728779.
6. Morais FL, Silva Rocha E, Masson G, et al. Utilization of tree-based machine learning models for predicting low birth weight cases. BMC Pregnancy Childbirth. 2025 Feb 26;25(1):207. https://doi.org/10.1186/s12884-025-07303-x.
7. Ranjbar A, Montazeri F, Farashah MV, Mehrnoush V, Darsareh F, Roozbeh N. Machine learning-based approach for predicting low birth weight. BMC Pregnancy Childbirth. 2023 Nov 20;23(1):803. https://doi.org/10.1186/s12884-023-06128-w.
8. Abdi F, Roozbeh N, Darsareh F, Mehrnoush V, Vahidi Farashah MS, Montazeri F. Developing a prognostic model for predicting preterm birth using a machine learning algorithm. BMC Pregnancy Childbirth. 2025 Sep 30;25(1):974. https://doi.org/10.1186/s12884-025-08136-4.
9. Rezaei N, Amani M, Asgharpoor H, Mehrnoush V, Darsareh F, Nikmanesh A. Machine Learning Approach to Predict Emergency Cesarean Sections Among Nulliparous Women. Cureus. 2025 Aug 19. https://doi.org/10.7759/cureus.90501.
10. Nascimento RC, Barbosa MCR, Corrêa MM. Baixo-peso ao nascer: estudo de fatores associados em um hospital terciário da Grande Vitória. DEMETRA: Alimentação, Nutrição & Saúde. 2019 Oct 28;14:e43508–e43508. https://doi.org/10.12957/demetra.2019.43508.
11. Suarez TOF, Santana ABC. Fatores de risco para baixo peso ao nascer em recém-nascidos vivos no Amazonas 2016-2020. Revista Eletrônica Acervo Saúde. 2024 Jul 3;24(7):e16472. https://doi.org/10.25248/reas.e16472.2024.
12. Ludermir TB. Inteligência Artificial e Aprendizado de Máquina: estado atual e tendências. Estudos Avançados. 2021 Apr 30;35(101):85–94. https://doi.org/10.1590/s0103-4014.2021.35101.007.
13. Paixão GMM, Santos BC, Araujo RM, et al. Machine Learning na Medicina: Revisão e Aplicabilidade. Arq Bras Cardiol [Internet]. 2022 Jan 10;118(1):95–102. Available from: https://abccardiol.org/article/machine-learning-na-medicina-revisao-e-aplicabilidade/.
14. Askin L, Tanrıverdi O, Cetin M. Algoritmos Artificiais Superam os Modelos Tradicionais na Predição de Doença Arterial Coronariana. Arquivos Brasileiros de Cardiologia. 2021 Nov 22;117(6):1071–2. https://doi.org/10.36660/abc.20210823.
15. Carvalho ACPDLFD. Inteligência Artificial: riscos, benefícios e uso responsável. Estud Av. 2021 Apr;35(101):21–36. https://doi.org/10.1590/s0103-4014.2021.35101.003.
16. Kingsford C, Salzberg SL. What are decision trees? Nat Biotechnol. 2008 Sep;26(9):1011–3. https://doi.org/10.1038/nbt0908-1011.
17. Fernandes AAT, Filho DBF, Rocha EC, Nascimento WS. Read this paper if you want to learn logistic regression. Revista de Sociologia e Política. 2020 Dec 15;28(74):1–19. https://doi.org/10.5380/rsocp.v28i74.78515.
18. Vellido A. The importance of interpretability and visualization in machine learning for applications in medicine and health care. Neural Comput & Applic. 2020 Dec 1;32(24):18069–83. https://doi.org/10.1007/s00521-019-04051-w.
19. Islam Pollob SMA, Abedin MM, Islam MT, Islam MM, Maniruzzaman M. Predicting risks of low birth weight in Bangladesh with machine learning. PLoS One. 2022 May 26;17(5):e0267190. PMID: 35617201; https://doi.org/10.1371/journal.pone.0267190.
20. Victor A, Almeida F, Xavier SP, Rondó PHC. Predicting low birth weight risks in pregnant women in Brazil using machine learning algorithms: data from the Araraquara cohort study. BMC Pregnancy Childbirth. 2025 Mar 19;25(1):320. https://doi.org/10.1186/s12884-025-07351-3.
21. Instituto Brasileiro de Geografia e Estatística (IBGE). IBGE [Internet]. Brasília (DF); 2025 [cited 2026 May 11]. Estimativas da população residente para os municípios e para as unidades da federação. Available from: https://www.ibge.gov.br/estatisticas/sociais/populacao/9103-estimativas-de-populacao.html.
22. Morais FL, Neri ABT, Silva Rocha E, et al. Predicting Low Birth Weight Using Machine Learning Models. In: 2023 18th Iberian Conference on Information Systems and Technologies (CISTI) [Internet]. Aveiro, Portugal: IEEE; 2023 [cited 2026 May 11]. p. 1–7. Available from: https://ieeexplore.ieee.org/document/10211576/. https://doi.org/10.23919/CISTI58278.2023.10211576.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Allbert Velleniche de Aquino Almeida, Adriana de Oliveira Ribeiro dos Santos, Luiz Fernando Costa Nascimento
This work is licensed under a Creative Commons Attribution 4.0 International License.
