Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Delirium is an acute, fluctuating state of consciousness disturbance characterized by cognitive alterations and perceptual disturbances. Pediatric delirium has a notably higher incidence rate than adult delirium, and it is time-consuming and labor-intensive for clinicians to analyze, requiring effective recognition approaches. Deep learning has shown potential for the extraction of robust representations and improvement of patient outcomes. In this study, 129 video samples labeled by professional clinicians were collected from multiple hospitals, including 74 non-delirium and 55 delirium labeled samples. An 18-layer deep spatiotemporal convolutional neural network is employed, in which two-dimensional and one-dimensional convolutional filters are applied to individual video frames to extract frame-level and inter-frame-level features, respectively. The entire architecture is pretrained on a large-scale video analysis dataset, and a three-layer fully connected classification head is integrated for the delirium recognition task. The proposed model was fine-tuned with a training dataset and evaluated on a testing dataset, exploring various models and strategies. The proposed algorithm demonstrated robust classification performance, achieving an accuracy of 0.8718, precision of 0.8711, recall of 0.8730, and F1-score of 0.8715, with approximately 31.54 million model parameters. These metric results validate the clinical applicability and technical reliability of the model under various training and testing strategies. In addition, the developed delirium classification model is deployed a hospital system to enable intelligent video diagnosis. The independent test accuracy for 100 newly collected samples is 0.8800. Therefore, the proposed algorithm enables new methods for pediatric delirium recognition and cures.

Download full-text PDF

Source
http://dx.doi.org/10.1109/JBHI.2025.3604448DOI Listing

Publication Analysis

Top Keywords

pediatric delirium
12
delirium recognition
12
delirium
8
video analysis
8
proposed algorithm
8
video
5
automated pediatric
4
recognition
4
recognition deep
4
deep learning-powered
4

Similar Publications

Background: Emergence delirium (ED) is a common postoperative complication during the recovery period in pediatric anesthesia. Continuous intravenous infusion of remimazolam can effectively prevent the occurrence of ED. However, the optimal dose for preventing ED in pediatric patients remains unclear.

View Article and Find Full Text PDF

Background: Delirium in patients with ulcerative colitis may be seen, especially in the elderly and in patients hospitalized for a long time. In children, Wernicke's encephalopathy may occur due to thiamine deficiency in both ulcerative colitis and Crohn's disease. We present a patient with ulcerative colitis who presented with delirium as the first symptom, did not respond to steroid treatment and improved with anti-tumor necrosis factor-alpha treatment.

View Article and Find Full Text PDF

Background: In pediatric intensive care units, pain, sedation, delirium, and iatrogenic withdrawal syndrome (IWS) must be managed as interrelated conditions. Although clinical practice guidelines (CPGs) exist, new evidence needs to be incorporated, gaps in recommendations addressed, and recommendations adapted to the European context.

Objective: This protocol describes the development of the first patient- and family-informed European guideline for managing pain, sedation, delirium, and IWS by the European Society of Paediatric and Neonatal Intensive Care.

View Article and Find Full Text PDF

Objective: To assess the incidence of delirium and its predictors among adult patients admitted to the intensive care units of comprehensive specialised hospitals in the Amhara region of northwest Ethiopia from 18 October 2024 to 20 February 2025.

Design: A multicentre prospective observational study was conducted.

Setting: Four comprehensive specialised hospitals in the Amhara region of northwest Ethiopia, from 18 October 2024 to 20 February 2025.

View Article and Find Full Text PDF

Background: Preoperative anxiety in children is a known risk factor for Emergence Delirium (ED). The family environment may indirectly influence ED by modulating anxiety levels, but its direct role in ED remains unclear. The purpose of this study is to explore the associations between the occurrence of ED and family environmental factors in children.

View Article and Find Full Text PDF