Artificial neural network promising for predicting neonatal metabolic bone disease

Artificial neural network (ANN) may be an efficient tool for predicting neonatal metabolic bone disease (MBD) during prenatal and postnatal periods, according to a recent study.

MBD is often seen in infants born preterm and lacking fetal mineral accumulation. Hypophosphatemia, hyperphosphatemia, and skeletal demineralization are all characteristics of MBD. Osteopenia, osteoporosis, rickets, and pathologic fractures can also all occur in MBD, increasing bone fragility and potentially impacting short- and long-term bone growth.

While infants at risk of MBD receive screening, there is a wide variety of diagnostic methods, and early recognition can be difficult because of the late onset of clinical symptoms and a lack of specific biochemical markers. This has led to a need for predictive tools for MBD.

A flexible and accurate machine learning algorithm, the ANN, has been able to predict multiple diseases. Investigators developed serial ANN models for the risk of MBD to determine the most efficient and accurate model for prediction.

Pregnant Chinese women gave written consent to participate in a diagnostic study, conducted from January 1, 2012, to December 31, 2021. Recruitment occurred early in pregnancy, and follow-up continued until 1 month after parturition.

To be included, participants needed to have a singleton pregnancy, complete clinical data during the antenatal, delivery, and postpartum periods, and surviving infants with detailed values of alkaline phosphatase. A peak serum alkaline phosphatase level above 500 U/L 72 hours after birth was used to determine MBD.

Data on maternal and neonatal characteristics were gathered from electronic health records. These characteristics included demographic data and prior pregnancy history, nutritional conditions during pregnancy, complications and comorbidities, medication use during pregnancy, birth outcomes, and neonatal disorders.

Five predictive models were built using an ANN, with a receiver operating characteristic curve used to evaluate the model performance.

There were 10,801 Chinese women participating in the study, 65.8% of which were local residents, 98.1% of Han ethnicity, and 9.3% had uterine scanning. Of the infants, 55.1% were male and 44.9% female. MBD presented in 138 infants, only 6 of which were term infants. In comparison, 75.9% of control infants were term infants.

In putative predictive factors, offspring of women with inadequate folic acid during pregnancy were 2.31 times more likely to develop MBD, compared to 3.26 times higher when born to women taking calcium supplementation and 0.38 times lower when born to women taking iron supplements.

MBD risk factors included magnesium sulfate use in pregnancy and infants with low birth weight, anemia, septicemia, or respiratory distress syndrome.

The area under the receiver operating characteristic curve (AUC) was calculated for ANN models. Model 1 showed the highest AUC, followed by model 5, model 4, model 3, and model 2. As model 1 had a net reclassification improvement of 0.205 compared to model 5, it showed an improved discriminative ability.

Results also indicated improved identification of neonates at high risk of MBD with fewer instances of misclassification in model 1. Overall, model 1 showed the best performance for significant prenatal and postnatal factors and model 5 for postnatal factors, making them viable for use in clinical practice.

Reference

Jiang H, Guo J, Li J, Li C, Du W, Canavese F, et al. Artificial neural network modeling to predict neonatal metabolic bone disease in the prenatal and postnatal periods. JAMA Netw Open. 2023;6(1):e2251849. doi:10.1001/jamanetworkopen.2022.51849