Risk of apnoea-related cardiorespiratory instability in preterm infants is modulated by clinical, demographic and dynamic indicators.

BACKGROUND: Apnoea of prematurity is common and may cause desaturation and/or bradycardia. There is marked variability in infants' cardiorespiratory responses to apnoea, despite standardised clinical thresholds. Factors influencing apnoea-related cardiorespiratory instability and whether instability can be predicted warrant investigation. METHODS: 181,511 apnoeas >5 s were identified from 146 preterm infants <37 weeks' postmenstrual age. Cardiorespiratory instability was defined as bradycardia (>30% heart rate reduction) and/or oxygen desaturation (<85%). Mixed-effects models assessed clinical, demographic and dynamic modulators of the relationship between apnoea duration and cardiorespiratory instability. Machine learning (XGBoost) was used to train models to predict apnoea-related cardiorespiratory instability. RESULTS: Longer duration apnoeas were associated with increased instability, although variability was substantial and 3.6% of apnoeas <10 s were associated with cardiorespiratory instability, while 61.2% of apnoeas ≥20 s were not. Multiple clinical/demographic (postmenstrual and gestational age, sex, weight z-score, ventilation mode) and dynamic (baseline heart rate, oxygen saturation, recent apnoea clustering) factors were associated with increased instability risk. Apnoea-related cardiorespiratory instability could be predicted with a balanced test accuracy of 75.8% when incorporating all features, and 66.0% using only clinical/demographic features. CONCLUSIONS: Multiple factors influence cardiorespiratory responses to apnoea. Predictive modelling may enable personalised apnoea definitions, improving individualised care. IMPACT: We investigated variability in cardiorespiratory instability following apnoea in preterm infants. We demonstrate multiple factors which influence the cardiorespiratory changes following apnoea and develop a machine learning model which can accurately predict apnoea-related cardiorespiratory instability. Prediction of cardiorespiratory instability could enable personalised apnoea alarms and inform discharge and treatment decision making.