How big data shape paediatric anaesthesia

A Narrative Review of Multiinstitutional Data Registries of Pediatric Congenital Heart Disease in Pediatric Cardiac Anesthesia and Critical Care Medicine

Congenital heart disease (CHD) is one of the most common birth anomalies. While the care of children with CHD has improved over recent decades, children with CHD who undergo general anesthesia remain at increased risk for morbidity and mortality. Electronic health record systems have enabled institutions to combine data on the management and outcomes of children with CHD in multicenter registries. The application of descriptive analytics methods to these data can improve clinicians' understanding and care of children with CHD. This narrative review covers efforts to leverage multicenter data registries relevant to pediatric cardiac anesthesia and critical care to improve the care of children with CHD.

PEACHY, another fruitful study

The results of the PErioperAtive CHildhood ObesitY (PEACHY) study showed an alarmingly high incidence of obesity amongst children presenting for surgical procedures under general anaesthesia in the UK. The study was performed by the Paediatric Anaesthesia Trainee Research Network (PATRN), a network of trainee anaesthetists seeking to quantify important clinical problems. Networks and consortia that facilitate collaboration amongst clinicians and academics working in a wide range of types of hospitals are particularly important in the current era, as they have the potential to gather data rapidly on important clinical problems, and by their size improve the power to identify factors associated with rare complications. Collaboration amongst clinicians within networks instead of competition between clinicians can have wide-ranging benefits that extend beyond research, and can include improvements in training, rapid dissemination of protocols, and knowledge concerning new problems, ultimately improving general standards of care.

Pediatric Anesthesia Specialty Societies and Multi-Institutional Collaborations

Pediatric anesthesiology is a subspecialty of anesthesiology that deals with the high-risk pediatric population. The specialty has made significant advancement in large collaborative efforts to study and increase patient safety, including the creation of international societies, a dedicated journal, special committees and interest groups, and multi-institution databases for research and quality improvement. Readily available resources were created to help with the education of future pediatric anesthesiologists as well as continuing medical education. Conclusions: Specialty societies and collaborations in pediatric anesthesia are crucial for continuous improvement in the care of children. They promote research, education, quality improvement, and advocacy at the local, national, and international level.

Artifacts annotations in anesthesia blood pressure data by man and machine

Physiologic data from anesthesia monitors are automatically captured. Yet erroneous data are stored in the process as well. While this is not interfering with clinical care, research can be affected. Researchers should find ways to remove artifacts. The aim of the present study was to compare different artifact annotation strategies, and to assess if a machine learning algorithm is able to accept or reject individual data points. Non-cardiac procedures requiring invasive blood pressure monitoring were eligible. Two trained research assistants observed procedures live for artifacts. The same procedures were also retrospectively annotated for artifacts by a different person. We compared the different ways of artifact identifications and modelled artifacts with three different learning algorithms (lasso restrictive logistic regression, neural network and support vector machine). In 88 surgical procedures including 5711 blood pressure data points, the live observed incidence of artifacts was 2.1% and the retrospective incidence was 2.2%. Comparing retrospective with live annotation revealed a sensitivity of 0.32 and specificity of 0.98. The performance of the learning algorithms which we applied ranged from poor (kappa 0.053) to moderate (kappa 0.651). Manual identification of artifacts yielded different incidences in different situations, which were not comparable. Artifact detection in physiologic data collected during anesthesia could be automated, but the performance of the learning algorithms in the present study remained moderate. Future research should focus on optimization and finding ways to apply them with minimal manual work. The present study underlines the importance of an explicit definition for artifacts in database research.