Impact of multimodal information on the estimation of fetal growth indicators using machine learning regression models
Clinical Snapshot
PICO Framework
| P — Population | Pregnant women with fetometric, clinical, and sociodemographic data (n=154) |
| I — Intervention | Multimodal machine learning models incorporating echographic, clinical, and sociodemographic features |
| C — Comparator | Traditional models using only fetometric data or clinical-sociodemographic data alone |
| O — Outcomes | Prediction accuracy for birth weight, birth length, and gestational age at birth (measured by R², MAE, MAPE) |
Bottom Line
This Mexican study suggests that combining ultrasound measurements with clinical and sociodemographic data using machine learning can improve prediction of fetal growth indicators at birth. The multimodal random forest model achieved strong performance (R² >0.86) for predicting birth weight, length, and gestational age. However, the small sample size (n=154), lack of external validation, and absence of confidence intervals limit confidence in these findings. Key predictive factors included maternal height and weight, placenta location, and alcohol consumption alongside traditional fetometric measurements. While promising, these models require validation in larger, diverse populations before clinical implementation. Australian clinicians should await external validation studies and consider local population differences before adopting such predictive tools in routine antenatal care.
Key Findings
P Value: Not reported
Effect Size: R² = 0.8991 for birth weight prediction
Primary Outcome: Birth weight prediction accuracy using multimodal random forest model
Nnt Or Sensitivity: MAE: 255.08g for birth weight, 7.21cm for birth length, 1.34 days for gestational age
Confidence Interval: Not reported
Clinical Application
Requires integration of multiple data sources and machine learning infrastructure in clinical settings Would need validation in Australian population; potential integration with existing antenatal care pathways and electronic health records Pregnant women undergoing routine antenatal care with available ultrasound and clinical data
Abstract
Accurate estimation of fetal growth indicators such as birth weight, birth length, and gestational age at birth is essential for monitoring pregnancy outcomes and guiding clinical decisions. Traditional predictive models typically rely on ultrasound-based fetometric data to estimate fetal weight or length. While valuable, these models provide estimates only at the time of measurement, rather than predicting values at birth, and may overlook important clinical and sociodemographic factors that also influence fetal growth. This study aimed to evaluate whether incorporating echographic, clinical, and sociodemographic features could improve the accuracy of predicting fetal growth indicators at birth and to quantify the contribution of each variable. Data from 154 cases were collected and processed for model development (61.5% for training and 38.5% for testing), divided into three feature sets: fetometric, clinical-sociodemographic, and combined clinical, echographic, and sociodemographic data. Six regression models were developed to predict three fetal growth indicators: birth weight, birth length, and gestational age at birth. Model performances were assessed usingR2, mean absolute error (MAE), and mean absolute percentage error (MAPE). The multimodal models significantly outperformed those relying only on fetometric or clinical-sociodemographic data, with the random forest achieving the best performance for birth weightR2: 0.8991; MAE: 255.08 g; MAPE: 8.46%, birth lengthR2: 0.8679; MAE: 7.21 cm; MAPE: 2.73%, and gestational age at birthR2: 0.8886; MAE: 1.34 d; MAPE: 2.76%. Feature relevance analysis revealed that variables such as maternal height, maternal weight, placenta location, and alcohol consumption played substantial roles in prediction accuracy, alongside classic fetometric measurements such as head circumference. These findings highlight the multifactorial nature of fetal growth and demonstrate that integrating clinical and sociodemographic information enhances the performance of fetal growth prediction models, ultimately supporting improved perinatal care.
References
- 1.Castellanos-Diaz, O., Perez-Gonzalez, J., Arambula-Cosio, F., Gonzalez-Meza, L., Camargo-Marin, L., Guzman-Huerta, M., Vazquez-Salazar, F., Aguilera-Perez, J., Ortega-Castillo, V., Medina-Banuelos, V., & Valdes-Cristerna, R. (2026). Impact of multimodal information on the estimation of fetal growth indicators using machine learning regression models. Biomedical Physics & Engineering Express. https://doi.org/10.1088/2057-1976/ae5caa
Related Research
Acta obstetricia et gynecologica Scandinavica
ChatGPT in urogynecology: Comparing large language model responses to human experts
3 Aug 2026
Ultrasound in medicine & biology
A Systematic Review: The Application of Attention Mechanisms in Medical Ultrasound Image Processing
2 Aug 2026
Preventing chronic disease
Reducing Rates of Cesarean Delivery in Rural US Communities: A Systematic Review of Interventions and Approaches to Care
31 July 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service