No abstract

BACKGROUND For critically ill children who cannot communicate and express themselves sufficiently, facial expressions are important indicators of their pain levels. Dataset training and testing quality is a crucial factor affecting the performance of facial expression analysis algorithms. Establishing a high-quality standardized dataset requires in-depth research. OBJECTIVE This study aims to propose a standard for constructing a facial expression-based pain assessment dataset for critically ill children by establishing a large-scale, high-quality sample dataset and validating the dataset using deep learning models. METHODS Based on the principles of standardization, diversity, and authority of high-quality datasets, we establish standards for constructing a facial expression-based pain assessment dataset for critically ill children. The children's facial expression data were collected in two typical scenarios, the Pediatric Intensive Care Unit (PICU) and the Cardiac Intensive Care Unit (CICU) at Children's Hospital of Fudan University. Then, each sample was annotated by three clinical experts to classify their facial expressions into five pain levels. Finally, deep learning algorithms were used to verify the feasibility and applicability of the dataset. RESULTS The Pain Expression of Critically Ill Children (PECIC) dataset established in this study is the most extensive facial expression-based pain assessment dataset for critically ill children to date, including 53 children, 119 pain expression videos, and 6,951 pain expression images collected from the Pediatric Intensive Care Unit (PICU) and Cardiac Intensive Care Unit (CICU) at Children's Hospital of Fudan University from December 2022 to January 2023. Data collection was balanced for age, weight, sex, and mechanical ventilation status of the children. Each image was annotated by three clinical experts. The Swin Transformer model was trained and tested using the established PECIC dataset, achieving an accuracy of 88.3%, precision of 88.3%, recall rate of 88.7%, F1-Score of 88.5%, and false-positive rate of 3.0%. Prediction errors were evenly distributed among adjacent pain levels. The comparison results with the Classification of Pain Expressions (COPE) dataset demonstrated the usefulness, accuracy, validity, and comprehensiveness of the PECIC dataset. CONCLUSIONS Compared to the COPE dataset, the PECIC dataset in this study leads to higher accuracy with the trained model, demonstrating better usability and comprehensiveness in training algorithm models. Therefore, using the PECIC dataset for deep learning-based analysis and evaluating pain expressions in critically ill children is more feasible and applicable.

Background Acinetobacter baumannii complex (ABC) is a group of increasingly prevalent opportunistic pathogens that cause a variety of life-threatening nosocomial infections, especially in the intensive care unit (ICU). It is unclear whether ABC bacteremia differs with infection site. This study assessed the differences between pneumonia- and non-pneumonia-related ABC bacteremia and possible independent risk factors for 30-day mortality. Methods The clinical data of 188 patients diagnosed with ABC bacteremia in our 29-bed ICU between January 2009 and December 2020 were collected. Of these, 44 cases (23.4%) were defined as pneumonia-related ABC bacteremia and 144 (76.6%) as non-pneumonia-related ABC bacteremia. Results Significant changes in the incidence of ABC bacteremia and antibiotic resistance were observed over the 12-year study, with an overall 30-day mortality rate of 61.7%. Compared with non-pneumonia-related ABC bacteremia, pneumonia-related ABC bacteremia was associated with a higher rate of hypertension, less prior tigecycline use, more carbapenem-resistant (CR) strains, and had a higher 30-day mortality rate. Univariate analysis showed that hematological malignancy, previous corticosteroid use, prior exposure to quinolone and anti-fungal agents, CR strains, monomicrobial bacteremia, respiratory tract bacteremia origin, lower albumin and higher lactate levels at the time of bacteremia, immunosuppression, septic shock, and severity of illness based on the Pitt bacteremia score, Acute Physiology and Chronic Health Evaluation II (APACHE II), and Sequential Organ Failure Assessment (SOFA) scores at the time of bacteremia were associated with poor outcomes. In multivariate analysis, immunosuppression, and higher APACHE II and SOFA scores, were risk factors for 30-day mortality. Moreover, the risk of death was 1.919 times higher in the pneumonia-related group. Conclusions Our study described the clinical characteristics and independent predictors of 30-day mortality in patients with pneumonia- and non-pneumonia-related ABC bacteremia. Although pneumonia-related ABC bacteremia had worse outcomes, it was not an independent risk factor for death statistically. Detection of immune status and maintenance of organ function may be effective therapeutic strategies to improve patient outcomes.