Follow us
๐Ÿง‘๐Ÿผโ€๐Ÿ’ป Research - January 17, 2025

Enhancing Small-for-Gestational-Age Prediction: Multi-Country Validation of Nuchal Thickness, Estimated Fetal Weight, and Machine Learning Models.

๐ŸŒŸ Stay Updated!
Join Dr. Ailexa’s channels to receive the latest insights in health and AI.

โšก Quick Summary

A recent study focused on enhancing the prediction of small-for-gestational-age (SGA) infants by developing a nuchal thickness reference chart and comparing traditional algorithms with machine learning models. The findings revealed that employing a disjunctive rule significantly improved prediction accuracy, with the best-performing model achieving an AUC of 0.81 in Singapore cohorts.

๐Ÿ” Key Details

  • ๐Ÿ“Š Dataset: 5,519 singleton pregnancies from University Malaya Medical Centre
  • ๐Ÿงฉ Features used: Nuchal thickness, estimated fetal weight, abdominal circumference, femur length, maternal age, ultrasound-confirmed gestational age
  • โš™๏ธ Technology: Logistic regression and support vector machines
  • ๐Ÿ† Performance: Logistic regression AUC 0.75 (Malaysia), Support vector machine AUC 0.81 (Singapore)

๐Ÿ”‘ Key Takeaways

  • ๐Ÿ“‰ SGA infants show significantly lower nuchal thickness compared to appropriate-for-gestational-age infants.
  • ๐Ÿ’ก Disjunctive rule (nuchal thickness < 10th centile or estimated fetal weight < 10th centile) improved prediction accuracy by 5.83% in Malaysia and 7.75% in Singapore.
  • ๐Ÿค– Machine learning models outperformed traditional rule-based algorithms in predicting SGA.
  • ๐Ÿฅ Clinical relevance of nuchal thickness as a predictive marker for SGA infants is reinforced.
  • ๐ŸŒ Multi-country validation enhances the robustness of the findings across different populations.
  • ๐Ÿ” Further research is needed to assess the clinical utility of these predictive models.

๐Ÿ“š Background

The prediction of small-for-gestational-age (SGA) infants is crucial for improving maternal and neonatal outcomes. SGA is associated with increased risks of morbidity and mortality. Traditional methods of prediction often rely on subjective assessments and can be inconsistent. This study aims to enhance prediction accuracy through the development of a nuchal thickness reference chart and the application of advanced machine learning techniques.

๐Ÿ—’๏ธ Study

Conducted at the University Malaya Medical Centre, this retrospective study involved analyzing data from 5,519 singleton pregnancies. The researchers developed a nuchal thickness reference chart and evaluated its predictive value for SGA using cohorts from Malaysia and Singapore. They compared the performance of traditional rule-based algorithms with seven machine learning models trained on Malaysian data.

๐Ÿ“ˆ Results

The study found that SGA infants had a significantly lower nuchal thickness (4.57 mm) compared to appropriate-for-gestational-age infants (4.86 mm, p < 0.001). The implementation of the disjunctive rule significantly improved prediction accuracy, with logistic regression achieving an AUC of 0.75 for Malaysia and support vector machines achieving an AUC of 0.81 for Singapore cohorts.

๐ŸŒ Impact and Implications

The findings from this study have significant implications for clinical practice. By enhancing the prediction of SGA infants, healthcare providers can implement timely interventions, potentially reducing the associated risks. The use of machine learning models represents a promising advancement in prenatal care, paving the way for more accurate and reliable assessments in diverse populations.

๐Ÿ”ฎ Conclusion

This study highlights the importance of integrating machine learning into prenatal assessments for predicting SGA infants. The development of a nuchal thickness reference chart and the validation of predictive models across multiple countries underscore the potential for improved clinical outcomes. Continued research in this area is essential to fully realize the benefits of these technologies in obstetric care.

๐Ÿ’ฌ Your comments

What are your thoughts on the use of machine learning in predicting small-for-gestational-age infants? We would love to hear your insights! ๐Ÿ’ฌ Leave your comments below or connect with us on social media:

Enhancing Small-for-Gestational-Age Prediction: Multi-Country Validation of Nuchal Thickness, Estimated Fetal Weight, and Machine Learning Models.

Abstract

OBJECTIVE: The first objective is to develop a nuchal thickness reference chart. The second objective is to compare rule-based algorithms and machine learning models in predicting small-for-gestational-age infants.
METHOD: This retrospective study involved singleton pregnancies at University Malaya Medical Centre, Malaysia, developed a nuchal thickness chart and evaluated its predictive value for small-for-gestational-age using Malaysian and Singapore cohorts. Predictive performance using conjunctive (AND)/disjunctive (OR) rule-based algorithms was assessed. Seven machine learning models were trained on Malaysia data and evaluated on both Malaysia and Singapore cohorts.
RESULTS: 5519 samples were collected from the University Malaya Medical Centre. Small-for-gestational-age infants exhibit significantly lower nuchal thickness (small-for-gestational-age: 4.57 [1.04] mm, appropriate-for-gestational-age: 4.86 [1.06] mm, pย <ย 0.001). Implementing disjunctive rule (nuchal thicknessย <ย 10th centile or estimated fetal weightย <ย 10th centile) significantly improved small-for-gestational-age prediction across all growth charts, with balanced accuracy gains of 5.83% in Malaysia (pย <ย 0.05) and 7.75% in Singapore. The best model for predicting small-for-gestational-age was: logistic regression with five variables (abdominal circumference, femur length, nuchal thickness, maternal age, and ultrasound-confirmed gestational age), which achieved an area under the curve of 0.75 for Malaysia cohorts; support vector machine with all variables, achieved area under the curve of 0.81 for Singapore cohorts. CONCLUSIONS: Small-for-gestational-age infants demonstrate significantly reduced second-trimester nuchal thickness. Employing the disjunctive rule enhanced small-for-gestational-age prediction. Logistic regression and support vector machines show superior performance among all models, highlighting the advantages of machine learning. Larger prospective studies are needed to assess clinical utility.

Author: [‘Deng J’, ‘Naresh Sethi NSA’, ‘Ahmad Kamar A’, ‘Saaid R’, ‘Loo CK’, ‘Mattar CNZ’, ‘Jalil NS’, ‘Saw SN’]

Journal: Prenat Diagn

Citation: Deng J, et al. Enhancing Small-for-Gestational-Age Prediction: Multi-Country Validation of Nuchal Thickness, Estimated Fetal Weight, and Machine Learning Models. Enhancing Small-for-Gestational-Age Prediction: Multi-Country Validation of Nuchal Thickness, Estimated Fetal Weight, and Machine Learning Models. 2025; (unknown volume):(unknown pages). doi: 10.1002/pd.6748

Share on facebook
Facebook
Share on twitter
Twitter
Share on linkedin
LinkedIn
Share on whatsapp
WhatsApp

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.