Princess Margaret Hospital for Children (PMH) is a former children's hospital and centre for paediatric research and care located in Perth, Western Australia. It was the state's only specialist children's hospital until it closed in 2018, coinciding with the opening of the new Perth Children's Hospital that was built to replace it. Together with the Child and Adolescent Community Health Division, it made up the Child and Adolescent Health Service. Located on Roberts Road in Subiaco, Western Australia, in April 2008 the hospital had approximately 220 beds and served 300,000 patients per year.
OBJECTIVE:The Fontan operation is the final step in staged palliation for patients with single-ventricle physiology. It has extended their life expectancy and improved their quality of life. However, long-term complications and Fontan failure remain lifelong concerns. We aimed to use machine learning to develop a patient-specific preoperative Fontan failure risk calculator. METHODS:Patient data were obtained from the Australia and New Zealand Fontan Registry (ANZFR). The primary composite end point was Fontan failure, defined as any of death, transplant, Fontan takedown or conversion, protein-losing enteropathy, plastic bronchitis, or New York Heart Association class III/IV. To construct the risk calculator, we first used Cox regression with regularization to predict Fontan failure from 54 preoperative predictors in the ANZFR database. A regularization machine learning tool was used to automate variable selection among many predictors. We then manually added clinically relevant predictors. Six predictors (age, ventricular morphology, primary diagnosis, total anomalous pulmonary venous drainage, Fontan type, and moderate or greater atrioventricular valve regurgitation) were ultimately used in a subsequent multivariable Cox regression (without regularization) to ensure the final risk prediction model was simple and easy to interpret. RESULTS:Data from 1888 patients over 48 years (1975-2023) were available. The ANZFR collects perioperative and follow-up variables about each patient. After excluding patients with Fontan procedures with an atriopulmonary connection (n = 290) and missing predictors or outcome data (n = 125), data from 1473 patients were used to construct the calculator. Median age at Fontan was 4.5 years (interquartile range, 3.7, 5.6 years). Median follow-up was 11.0 years (interquartile range, 5.3, 17.8 years). Freedom from Fontan failure for the overall cohort at 10, 20, and 30 years was 92% (confidence interval [CI], 90%-93%), 83% (CI, 80%-86%), and 72% (CI, 65%-78%), respectively. External validation in an independent cohort demonstrated acceptable model performance. The risk prediction model was then implemented in a Desktop application using the Shiny library in R and used to develop the preoperative Fontan failure calculator on the basis of the 6 predictors. CONCLUSIONS:Machine learning can be applied to "big data" from a binational Fontan Registry to develop a preoperative, patient-specific Fontan failure risk calculator. The model will continue to learn and improve as more data is added. This is a step toward personalized medicine enabling patient-specific pre-operative counselling and realistic expectations.
INTRODUCTION:Parents and caregivers play a critical role in the care of their child peri-operatively. Our team undertook previous research with parents/carers, which identified Australian parents' top 10 research priorities for paediatric anaesthesia and peri-operative medicine. While this was an important exercise, it focused on parent-reported experiences rather than the priorities of the children themselves; however, the experiences and concerns of parents/carers may not always reflect those of their child. It has been shown previously how integral it is to listen to each child's own voice to improve and create a more adaptive and safer peri-operative environment. METHODS:This research prioritisation study was developed for children and used a modified James Lind Alliance method that involved surveys, a youth community conversation and a final consensus-based prioritisation meeting, all of which were conducted online. RESULTS:Participants were children and young people aged 6-18 y living in Australia. In total, we engaged 356 children and young people. We identified the top research priorities for Australian children and young people for paediatric anaesthesia and peri-operative medicine through a rigorous process of consensus. The final top 10 priorities were agreed by consensus after a multi-step process and included how to: reduce anxiety (including needle phobia); make anaesthesia safer; avoid postoperative complications (e.g. pain, sickness, agitation); and improve communication between children and doctors. DISCUSSION:The resulting priorities differed from those conducted in Australia for adult peri-operative medicine and from the parent/carer and clinician priorities identified previously for paediatric anaesthesia care. These research priorities can help guide future paediatric anaesthesia and peri-operative medicine research directions.
