Predicting Miscarriage Risk Based on Periodontal and Hematological Parameters Using Artificial Neural Network and XGBoost Models.

Researchers compared periodontal and blood inflammatory markers in pregnant women who had miscarriages versus healthy pregnancies, using machine learning models to predict miscarriage risk. Clinical attachment loss emerged as a key predictor, with the XGBoost model showing strong performance in identifying risk.

A plain-English summary of the study's own findings — we don't add our own claims or interpretation. Read the full paper for the complete methods and results, and apply your own clinical judgement.