Sign in Subscribe
Artificial intelligence

Artificial Intelligence Model Predicts Birthweight with High Accuracy

Strategic Insights

— 1 min read

Artificial intelligence (AI) has become a valuable tool in the medical field, and researchers from the Manipal Academy of Higher Education have developed a new AI model that can predict birthweight with high accuracy. The study, published in the journal Scientific Reports, aimed to create a more practical machine learning (ML) model that incorporates explainable artificial intelligence (XAI) to provide meaningful explanations for clinical predictive models. The research used data from 237 singleton pregnancies and developed a stacked ensemble model that integrated various algorithms, including a custom-stacked ensemble approach and three XAI methodologies.

Key Takeaways:

  • The AI model achieved a maximum accuracy of 77%, a precision of 73%, a recall of 77%, and an F1 score of 72% among the ML classifiers evaluated.
  • The stacked model demonstrated an accuracy of 75%, indicating its possibility in clinical application.
  • The model identified several key attributes that influence birthweight, such as maternal height, nuchal translucency thickness, parity, crown-rump length, glycated hemoglobin, hypertensive disorders of pregnancy, and pregnancy-associated plasma protein A.
  • The AI model can assist medical professionals in making more precise birthweight predictions using routinely collected antenatal parameters, enabling timely medical decisions and treatments.
  • The study concluded that the developed model can be used in clinical practice to improve birthweight prediction and related medical decisions.

Statistics:

  • Maximum accuracy: 77%
  • Precision: 73%
  • Recall: 77%
  • F1 score: 72%
  • Number of pregnant women in the dataset: 237
  • Number of singleton pregnancies in the dataset: 237
  • Number of key attributes influencing birthweight: 7
  • Accuracy of the stacked model: 75%

Sources:

  • Prediction of birthweight with early and mid-pregnancy antenatal markers utilising machine learning and explainable artificial intelligence. Scientific Reports, 2025;15(1):26223.
  • Manipal Academy of Higher Education Reports Findings in Artificial Intelligence (Prediction of birthweight with early and mid-pregnancy antenatal markers utilising machine learning and explainable artificial intelligence). Journal of Engineering. August 4, 2025; p 1847.

Read more