Study on Risk Factors and Receiver Operator Characteristic Curve of Iatrogenic Withdrawal Syndrome in Pediatric Intensive Care Units: A Retrospective Study.

INTRODUCTION: The aims of this study were to investigate the independent risk factors associated with iatrogenic withdrawal syndrome in pediatric intensive care units (PICUs) and to establish receiver operator characteristic (ROC) curve to facilitate the diagnosis of iatrogenic withdrawal syndrome in clinical settings. METHODS: Pediatric patients who received analgesic and sedative medication at a tertiary hospital in the southern Zhejiang region of China between January 2016 and December 2022 were selected for the study. Clinical case data were retrospectively analyzed to gather information including age, gender, weight, total dose of analgesic and sedative medication, total treatment duration, average maintenance dose, and other relevant parameters. Medically induced withdrawal symptom scores were assessed using the Sophia Observation Scale for Withdrawal Symptoms (SOS). Univariate and multivariate logistic regression analyses were conducted on the above indicators to identify the risk factors for iatrogenic withdrawal, and an ROC curve was constructed. RESULTS: The study encompassed a total of 104 pediatric patients, comprising 47 patients in the SOS score ≥4 group and 57 patients in the SOS score ≤3 group. The incidence of iatrogenic withdrawal was 45.19%. Univariate analysis identified cumulative total dose of fentanyl, average daily dose of fentanyl, average daily dose of midazolam, and patient weight (p < 0.05) as factors associated with iatrogenic withdrawal syndrome. The logistic multiple regression analysis revealed that the average daily dose of fentanyl was an independent risk factor for the occurrence of iatrogenic withdrawal syndrome in critically ill children (p < 0.05). ROC curve analysis indicated an area under the curve of 0.711 (95% CI: 0.610-0.811) with sensitivity and specificity of 73.7% and 61.7%, respectively. CONCLUSION: The average daily maintenance dose of fentanyl holds significant clinical value in diagnosing and evaluating the prognosis of iatrogenic withdrawal syndrome and can provide a scientific foundation for enhancing sedative and analgesic management in clinical practice.

Meibomian glands segmentation in infrared images with limited annotation.

AIM: To investigate a pioneering framework for the segmentation of meibomian glands (MGs), using limited annotations to reduce the workload on ophthalmologists and enhance the efficiency of clinical diagnosis. METHODS: Totally 203 infrared meibomian images from 138 patients with dry eye disease, accompanied by corresponding annotations, were gathered for the study. A rectified scribble-supervised gland segmentation (RSSGS) model, incorporating temporal ensemble prediction, uncertainty estimation, and a transformation equivariance constraint, was introduced to address constraints imposed by limited supervision information inherent in scribble annotations. The viability and efficacy of the proposed model were assessed based on accuracy, intersection over union (IoU), and dice coefficient. RESULTS: Using manual labels as the gold standard, RSSGS demonstrated outcomes with an accuracy of 93.54%, a dice coefficient of 78.02%, and an IoU of 64.18%. Notably, these performance metrics exceed the current weakly supervised state-of-the-art methods by 0.76%, 2.06%, and 2.69%, respectively. Furthermore, despite achieving a substantial 80% reduction in annotation costs, it only lags behind fully annotated methods by 0.72%, 1.51%, and 2.04%. CONCLUSION: An innovative automatic segmentation model is developed for MGs in infrared eyelid images, using scribble annotation for training. This model maintains an exceptionally high level of segmentation accuracy while substantially reducing training costs. It holds substantial utility for calculating clinical parameters, thereby greatly enhancing the diagnostic efficiency of ophthalmologists in evaluating meibomian gland dysfunction.