OBJECTIVE Implementation of winter surge management in intensive care is hampered by the annual variability in the start and duration of the winter surge. We aimed to develop a real-time monitoring system that could identify the start promptly and accurately predict the end of the winter surge in a pediatric intensive care (PIC) setting. DESIGN We adapted a method from the stock market called "Bollinger bands" to compare current levels of demand for PIC services to thresholds based on medium term average demand. Algorithms to identify the start and end of the surge were developed using Bollinger bands and pragmatic considerations. The method was applied to a specific PIC service: the North Thames Children's Acute Transport Service (CATS) using eight winters of data (2005-2012) to tune the algorithms and one winter to test the final method (2013/14). SETTING A regional specialised paediatric retrieval service based in London, UK. RESULTS The optimal Bollinger band thresholds were 1.2 and 1 standard deviations above and below a 41-day moving average of demand respectively. A simple linear model was found to predict the end of the surge and overall surge demand volume as soon as the start had been identified. Applying the method to the validation winter of 2013/14 showed excellent performance, with the surge identified from 18th November 2013 to 4th January 2014. CONCLUSIONS We have developed and tested a novel method to identify the start and predict the end of the winter surge in emergency demand for pediatric intensive care.