Aim: To evaluate machine learning algorithms (MLAs) for predicting factors (oxidative stress biomarkers [OSBs] and single-nucleotide polymorphism of the antioxidant enzymes) for respiratory distress syndrome (RDS) and significant alterations in the liver functions (SALVs). Materials & methods: MLAs were applied for predicting the RDS and SALV (with OSB and single-nucleotide polymorphisms in the antioxidant enzymes) with area under the curve (AUC) as the accuracy measure. Results: The C5.0 algorithm best predicted SALV (AUC: 0.63) with catalase as the most important predictor. Bayesian network best predicted RDS (AUC: 0.6) and ENOS1 was the most important predictor. Conclusion: MLAs carry great potential in identifying the potential genetic and OSBs in neonatal RDS and SALV. Validation in prospective studies is needed urgently.
Keywords: MLA; RDS; liver function; neonates; oxidative stress.
Childbirth usually occurs around 37 weeks of pregnancy. A newborn that is born before this gestational period is referred to as preterm neonate that in many aspects may not have optimum organ functions, in particular, the ability of respiration by lung. This is referred to as respiratory distress syndrome. Respiratory distress syndrome is most often characterized with an imbalance in the molecules that prevent oxidative damage to the cellular molecules (called antioxidants) and those that cause damage (called pro-oxidants). When the balance shifts more to pro-oxidants, it is referred to as oxidative stress. Antioxidant enzymes are key elements for providing appropriate antioxidants in the body. The present study evaluated the role of artificial intelligence (machine learning algorithms in particular) in delineating the role of genetic and oxidative stress biomarkers with oxidative stress in preterm neonates with respiratory distress syndrome. We observed that mutations in certain antioxidant enzymes are associated with respiratory distress syndrome and abnormal liver functions.