Every year there are more than 11000 hospitalizations related to heart failure in children resulting in significant morbidity and mortality. Over the last two decades, our understanding, diagnosis and management of pediatric heart failure is evolving but our ability to prognosticate outcomes in pediatric heart acute heart failure is extremely limited due to lack of data. In adult heart failure patients, the role of cardiac biomarkers has exponentially increased over the last two decades. Current guidelines for management of heart failure emphasize the role of cardiac biomarkers in diagnosis, management and prognostication of heart failure. It is also noteworthy that these biomarkers reflect important biological processes that also open up the possibility of therapeutic targets. There is however, a significant gap present in the pediatric population with regards to biomarkers in pediatric heart failure. Here, we seek to review available data regarding cardiac biomarkers in the pediatric population and also explore some of the emerging biomarkers from adult literature that may be pertinent to pediatric heart failure.
9 April 2018 in IEEE EMBS International Conference on Biomedical & Health Informatics (BHI)
Endomyocardial biopsies are the current gold standard for monitoring heart transplant patients for signs of cardiac allograft rejection. Manually analyzing the acquired tissue samples can be costly, time-consuming, and subjective. Computer-aided diagnosis, using digitized whole-slide images, has been used to classify the presence and grading of diseases such as brain tumors and breast cancer, and we expect it can be used for prediction of cardiac allograft rejection. In this paper, we first create a pipeline to normalize and extract pixel-level and object-level features from histopathological whole-slide images of endomyocardial biopsies. Then, we develop a two-stage classification algorithm, where we first cluster individual tiles and then use the frequency of tiles in each cluster for classification of each whole-slide image. Our results show that the addition of an unsupervised clustering step leads to higher classification accuracy, as well as the importance of object-level features based on the pathophysiology of rejection. Future expansion of this study includes the development of a multi-class classification pipeline for subtypes and grades of cardiac allograft rejection.
IMPORTANCE: Extubation failure (EF) after pediatric cardiac surgery is associated with increased morbidity and mortality. OBJECTIVES: We sought to describe the risk factors associated with early (< 48 hr) and late (48 hr ≤ 168 hr) EF after pediatric cardiac surgery and the clinical implications of these two types of EF. DESIGN, SETTING, AND PARTICIPANTS: Retrospective cohort study using prospectively collected clinical data for the Pediatric Cardiac Critical Care Consortium (PC4) Registry. Pediatric patients undergoing Society of Thoracic Surgeons benchmark operation or heart transplant between 2013 and 2018 available in the PC4 Registry were included. MAIN OUTCOMES AND MEASURES: We analyzed demographics and risk factors associated with EFs (primary outcome) including by type of surgery. We identified potentially modifiable risk factors. Clinical outcomes of mortality and length of stay (LOS) were reported. RESULTS: Overall 18,278 extubations were analyzed. Unplanned extubations were excluded from the analysis. The rate of early EF was 5.2% (948) and late EF was 2.5% (461). Cardiopulmonary bypass time, ventilator duration, airway anomaly, genetic abnormalities, pleural effusion, and diaphragm paralysis contributed to both early and late EF. Extubation during day remote from shift change and nasotracheal route of initial intubation was associated with decreased risk of early EF. Extubation in the operating room was associated with an increased risk of early EF but with decreased risk of late EF. Across all operations except arterial switch, EF portrayed an increased burden of LOS and mortality. CONCLUSION AND RELEVANCE: Both early and late EF are associated with significant increase in LOS and mortality. Study provides potential benchmarking data by type of surgery. Modifiable risk factors such as route of intubation, time of extubation as well as treatment of potential contributors such as diaphragm paralysis or pleural effusion can serve as focus areas for reducing EFs.