When COVID-19 struck in 2020, Singapore responded swiftly with containment and mitigation measures to curb community spread. Underlying the city-state's quick public health response was an all-of-government approach characterised by decisive actions, rigorous surveillance, and prompt adaptation. Additionally, harnessing advanced healthcare technologies, such as artificial intelligence (AI) and data analytics, supported these efforts. Chatbots and automated instant messaging communications, as well as dissemination of information via traditional and social media, helped the public make sense of the uncertainties during the early days of the outbreak. As the pandemic progressed, digital contact tracing and even a robot dog were roped in to complement community surveillance measures as the country fought the war against COVID-19. More importantly, AI-enabled technologies and analytics played a vital role in disease diagnosis and prognosis as well as in supporting the research community in understanding the epidemiology of the novel coronavirus, predicting its evolution, and planning healthcare capacity. In 2023, WHO finally declared the end of COVID-19 as a global health emergency. However, the enduring effects of the pandemic persisted and continued to take a toll on the healthcare sector and on non-COVID-19 patients who had delayed medical care. Part of the burden of endemicity entailed living with the consequences of decisions made to prioritise hospital resources for COVID-19 patients, while non-urgent surgeries were either cancelled or postponed. Addressing the post-pandemic collateral damage became a pressing need. But how? Could AI, data analytics and other advanced technologies contribute to resolving this new healthcare challenge?

In early 2019, Alan Jay, an executive in the Quality, Safety and Risk Management (QSRM) department of Gloria Hospital, a full-service hospital that specialised in children and women healthcare, had been requested to gather insights and seek improvements to the pre-consultation waits at the hospital's Children's Emergency (CE) department. After an initial study, minor schedule adjustments were put into place, with many shifts starting one hour in advance to reduce snowballing of patients awaiting consultation. However, post-implementation data suggested that the patient load to capacity ratios remained uneven across each day of the week. Subsequently, a team of operations professors and students were assembled to join Jay in a second phase of the Children's Emergency Consultation Queue (CECQ) project, started April 2019, to better understand the actual waiting time of patients at the CE.