Related Experiment Videos
Comparative Performance of Artificial Intelligence Models in Predicting Low Birth Weight: Systematic Review and
Fatemeh Shabani1, Somayeh Abdolalipour1, Sakineh Mohammad-Alizadeh-Charandabi1
1Midwifery Department, Faculty of Nursing and Midwifery, Tabriz University of Medical Sciences, Tabriz, Iran.
Insights
Artificial Intelligence (AI) and Machine Learning (ML) show promise for predicting Low Birth Weight (LBW), but performance varies significantly by region and data type. Methodological biases and lack of calibration currently hinder clinical application of these AI/ML models.
Area of Science:
- Medical Informatics
- Public Health
- Computational Biology
Background:
- Low Birth Weight (LBW) is a significant global health concern requiring early prediction for effective intervention.
- Artificial Intelligence (AI) and Machine Learning (ML) are increasingly explored for predicting LBW.
- This systematic review evaluates the performance of AI/ML algorithms in LBW prediction.
Purpose of the Study:
- To systematically review and assess the performance of AI/ML algorithms for predicting Low Birth Weight (LBW).
- To identify factors influencing the efficacy of AI/ML models in diverse clinical settings.
- To highlight methodological limitations and guide future research for clinical translation.
Main Methods:
- Systematic literature search across Scopus, Web of Science, and PubMed following PRISMA guidelines.
- Assessment of methodological quality using the PROBAST tool.
- Narrative synthesis due to extreme statistical heterogeneity and inconsistent reporting of metrics.
Main Results:
- Forty studies were included, with 82.5% showing high or unclear risk of bias, mainly due to poor reporting of calibration and data handling.
- Ensemble AI/ML models (Random Forest, XGBoost) generally outperformed linear models.
- Model performance varied significantly: higher discrimination in high-income settings (AUC: 0.85-0.95) versus resource-limited settings (AUC: 0.65-0.75).
- Models using dynamic data (e.g., longitudinal ultrasound) showed better sensitivity than those using static clinical history.
Conclusions:
- AI/ML models hold potential for LBW prediction but are highly context-dependent.
- Current methodological biases and lack of calibration impede clinical readiness.
- Future clinical translation necessitates population-specific, interpretable models validated by external cohorts.
Background:
Low Birth Weight (LBW), defined as < 2500 g, is a global public health priority. Early prediction is essential for intervention. This systematic review investigates the performance of Artificial Intelligence (AI)/Machine Learning (ML) algorithms for LBW prediction.
Methods:
Following PRISMA guidelines, Scopus, Web of Science, and PubMed were searched for studies utilizing AI/ML for LBW. Methodological quality was assessed via the PROBAST tool. Due to extreme statistical heterogeneity and inconsistent reporting of metrics, a narrative synthesis approach was employed.
Results:
Forty studies met inclusion criteria. Quality assessment revealed that 82.5% were at high or unclear risk of bias, primarily due to poor reporting of calibration and data handling. Formal metaanalysis was precluded by extreme statistical heterogeneity (I2>98%) and the role of LBW as a surrogate marker for diverse phenotypes. Narrative synthesis indicated that ensemble architectures (Random Forest, XGBoost) consistently outperformed traditional linear models. Discrimination was significantly higher in high-income settings (AUC: 0.85-0.95) than in resource-limited settings (AUC: 0.65-0.75). Models integrating dynamic data, such as longitudinal ultrasound, demonstrated superior sensitivity over those relying on static clinical history. Performance trends across settings were highly variable, and given the heterogeneity, these findings must be considered strictly exploratory.
Conclusion:
AI/ML models show promise for LBW prediction, but their efficacy is strictly contextdependent. Widespread methodological bias and lack of calibration metrics currently limit "bedside readiness." Clinical translation requires a transition toward population-specific, interpretable tools validated through rigorous external cohorts.
