Machine learning-based prediction of delirium 24 h after pediatric intensive care unit admission in critically ill children: A prospective cohort study.

BACKGROUND: Accurately identifying patients at high risk of delirium is vital for timely preventive intervention measures. Approaches for identifying the risk of developing delirium among critically ill children are not well researched. OBJECTIVE: To develop and validate machine learning-based models for predicting delirium among critically ill children 24 h after pediatric intensive care unit (PICU) admission. DESIGN: A prospective cohort study. SETTING: A large academic medical center with a 57-bed PICU in southwestern China from November 2019 to February 2022. PARTICIPANTS: One thousand five hundred and seventy-six critically ill children requiring PICU stay over 24 h. METHODS: Five machine learning algorithms were employed. Delirium was screened by bedside nurses twice a day using the Cornell Assessment of Pediatric Delirium. Twenty-four clinical features from medical and nursing records during hospitalization were used to inform the models. Model performance was assessed according to numerous learning metrics, including the area under the receiver operating characteristic curve (AUC). RESULTS: Of the 1576 enrolled patients, 929 (58.9 %) were boys, and the age ranged from 28 days to 15 years with a median age of 12 months (IQR 3 to 60 months). Among them, 1126 patients were assigned to the training cohort, and 450 were assigned to the validation cohort. The AUCs ranged from 0.763 to 0.805 for the five models, among which the eXtreme Gradient Boosting (XGB) model performed best, achieving an AUC of 0.805 (95 % CI, 0.759-0.851), with 0.798 (95 % CI, 0.758-0.834) accuracy, 0.902 sensitivity, 0.839 positive predictive value, 0.640 F1-score and a Brier score of 0.144. Almost all models showed lower predictive performance in children younger than 24 months than in older children. The logistic regression model also performed well, with an AUC of 0.789 (95 % CI, 0.739, 0.838), just under that of the XGB model, and was subsequently transformed into a nomogram. CONCLUSIONS: Machine learning-based models can be established and potentially help identify critically ill children who are at high risk of delirium 24 h after PICU admission. The nomogram may be a beneficial management tool for delirium for PICU practitioners at present.

Frequency of child restraint system use and parental knowledge of such systems in western China.

OBJECTIVES: This study investigated the frequency of child restraint system (CRS) use in cars and assessed parental knowledge and attitudes toward such restraint systems in western China. STUDY DESIGN: Cross-sectional survey. METHODS: This cross-sectional survey was conducted between December 2021 and January 2022. Hospitals and kindergartens were convenience sampling selected, and parents with cars were asked whether they owned and used CRS. Parents' knowledge and attitudes toward such systems were also determined. Factors associated with CRS were explored using binary logistic regression. RESULTS: A total of 4764 questionnaires were distributed to parents with children 0-6 years old. Among the 4455 responses received, 50.8% of the respondents owned CRS, and most of which were front-facing child seats (42.0%). Less than half (44.4%) reported using a CRS sometimes, but only 19.6% used it all the time. The possession and use of a CRS varied significantly with the parental education level, age of the child, place of residence, number of children, family income, travel frequency, and travel distance. Logistic regression analysis showed that the frequency of car travel with a child and monthly family income significantly affected CRS use. Most parents (85.2%) perceived that adult seat belt in cars are effective at protecting their children in the event of a crash. The most frequent reason for not using a CRS was the tendency for children to travel in the car less often. CONCLUSIONS: Although approximately half of the respondents owned a CRS, most of them used it rarely, if at all. Educating parents about safe ways for children to ride in a car and use of safety belts may promote CRS use.

A review of neonatal peripherally inserted central venous catheters in extremely or very low birthweight infants based on a 3-year clinical practice: Complication incidences and risk factors.

Background: The application of peripherally inserted central venous catheters (PICCs) in neonates has proven effective in avoiding repetitive insertions and excessive use of transfusion consumables. However, the frequent occurrence of PICC-associated complications deserves special attention, especially in extremely or very low birthweight (E/VLBW) infants, which in turn affects the quality of neonatal PICC practice. Therefore, we conducted a retrospective study of a 3-year clinical practice of neonatal PICCs in E/VLBW infants to understand the incidences of various catheter-related complications and their risk factors to help form an empirical summary and evidence-based guidance for the improvement of practice. Methods: A retrospective study was conducted based on a 3-year practice of neonatal PICCs in E/VLBW infants. Neonatal health records were collected, including demographic characteristics, PICC placement data, and treatment information. Results: A total of 519 E/VLBW infants were included in this study. There were 77 cases of complications involving 72 infants with an overall incidence of 12.13%. The order of incidences of different complications from high to low was phlebitis (7.71%), malposition (3.66%), leakage (1.35%), pleural effusion (1.15%), central line-associated bloodstream infection (0.58%, 0.25/1,000d), and accidental removal (0.38%). Multivariate analysis revealed that the inserted vessel was an independent risk factor for PICC-associated complications (mainly phlebitis; p = 0.002). Neonatal PICCs inserted in the axillary vein were only one-tenth (p = 0.026) as likely to cause phlebitis as in the basilic vein, whereas when applied in the saphenous vein, neonatal PICCs were five times as likely to cause phlebitis (p = 0.000). Conclusion: E/VLBW infants might be more inclined to develop PICC-associated phlebitis. Catheters inserted in the axillary or basilic vein are preferred if possible.

Family functioning and delinquency among Chinese adolescents: Mediating effects of positive behavior recognition according to the humanistic perspective.

Background: Empirical research on the relationship between family functioning and delinquency has been sparse, although many studies have focused on the influence of family functioning on adolescent development. The current research aimed to fill this gap by exploring the influences of family functioning on adolescent delinquency and the mechanisms connecting the processes. Methods: We derived the baseline data from a prospective observational school-based cohort Chengdu Positive Child Development (CPCD) project. Students responded to a questionnaire containing validated measures of family functioning, positive behavior recognition, and delinquent behavior. We utilized structural equation modeling and maximum likelihood estimation to test the relationships. Results: Across 8811 Chinese adolescents, the incidence of delinquency behaviors among Chinese adolescents was relatively low. Family functioning and positive behavior recognition negatively predict delinquency (p < 0.001). Further, positive behavior recognition partially mediated the influence of family functioning on delinquency [p < 0.001, std. error = 0.01, 95% CI = (0.04, 0.07)]. Adolescents with better family functioning had little delinquency behavior, with positive behavior recognition and delinquency behavior negatively reinforcing each other. Conclusions: This study demonstrated that family functioning was a protective factor against adolescent delinquency and revealed that positive behavior recognition was a critical mediating mechanism linking family functioning to delinquency.

A case of transfusion-associated necrotizing enterocolitis in neonates. / æ–°ç”Ÿå„¿è¾“è¡€ç›¸å ³æ€§åæ­»æ€§å°è‚ ç»“è‚ ç‚Ž1例.

A male infant, whose weight was 1 120 g at 28+2 weeks of gestational age, was admitted to Neonatal Intensive Care Unit of West China Second Hospital of Sichuan University at 20 min after preterm birth. Blood transfusion was performed for anemia (hemoglobin 81 g/L) on day 30 of hospitalization, and feeding was continued during the transfusion. Eight hours after blood transfusion, the patient's manifestations included abdominal distension and stiff to palpation, bowel sound weakening, currant jelly stool, poor responsiveness, and apnea. The clinical diagnosis was necrotizing enterocolitis. Abdominal X-ray showed that the abdominal bowel was significantly dilated and inflated. The patient was immediately treated with fasting, gastrointestinal decompression, enema, and anti-infection treatment. After 40 days in hospital, the patient recovered and was discharged.

Arterial embolism caused by a peripherally inserted central catheter in a very premature infant: A case report and literature review.

BACKGROUND: Extremely premature infants have poor vascular conditions. Operators often choose deep veins such as the femoral vein and axillary vein to peripherally insert central catheters, and these vessels are often accompanied by arteries; thus, it is easy to mistakenly enter the artery. CASE SUMMARY: The case of an extremely premature infant (born at gestational age 28+3) in whom the left upper extremity artery was accidentally entered during peripheral puncture of the central venous catheter is reported. On the 19th day of hospitalization, the index finger, middle finger and ring finger of the left hand were rosy, the left radial artery and brachial artery pulse were palpable, the recovery was 95%, and the improvement was obvious. At discharge 42 d after admission, there was no abnormality in fingertip activity during the follow-up period. CONCLUSION: Arterial embolization in preterm infants requires an individualized treatment strategy combined with local anticoagulation and 2% nitroglycerin ointment for local tissue damage caused by arterial embolism in the upper limb. Continuous visualization of disease changes using image visualization increases the likelihood of a good outcome.

[Effect of golden-hour body temperature bundle management on admission temperature and clinical outcome in preterm infants after birth].

OBJECTIVE: To study the effect of golden-hour body temperature bundle management strategy on admission temperature and clinical outcome in preterm infants with a gestational age of <34 weeks after birth. METHODS: The preterm infants who were born in the delivery room of the West China Second University Hospital of Sichuan University and admitted to the department of neonatology of this hospital within 1 hour after birth from December 2015 to June 2016 and from January to May, 2017 were enrolled. The 173 preterm infants who were admitted from January to May, 2017 were enrolled as the intervention group and were given golden-hour body temperature bundle management. The 164 preterm infants who were admitted from December 2015 to June 2016 were enrolled as the control group and were given conventional body temperature management. RESULTS: The intervention group had a significantly higher mean admission temperature than the control group (36.4±0.4°C vs 35.3±0.6°C; P<0.001). The incidence rate of hypothermia on admission in the intervention group was significantly lower than that in the control group (56.6% vs 97.6%; P<0.001). The intervention group had a significantly lower incidence rate of intracranial hemorrhage within one week after admission than the control group (15.0% vs 31.7%; P<0.05). CONCLUSIONS: Golden-hour body temperature bundle management for preterm infants within one hour after birth can reduce the incidence of hypothermia on admission and improve clinical outcome.

A survey on the current status of pediatric nursing human resources in Sichuan province of China.

OBJECTIVE: To investigate the status of pediatric nurses in Sichuan province of China, and to compare the status with the national standards. METHODS: This study used a convenience sample of hospitals with pediatric departments in Sichuan province. A list of hospitals was obtained from the Health and Family Planning Commission of Sichuan province. Fifty hospitals with pediatric departments were selected to receive questionnaires. Thirty-nine hospitals responded and 38 responses were valid. Bed-to-nurse ratios were evaluated. The Wilcoxon signed rank test was used to compare the bed-to-nurse ratios among the studied hospitals and the Chinese national standard. RESULTS: In the 38 surveyed hospitals, the average bed-to-nurse ratio was 1:0.57 and the average physician-to-nurse ratio was 1:1.53. The average bed-to nurse ratio in the pediatric departments was 1:0.51. The average bed-to-nurse ratio in the pediatric inpatient wards was 1:0.40. There were significant differences in the average bed-to-nurse ratios in the pediatric departments (Z = -2.149, P = 0.032) and the pediatric inpatient wards (Z = -2.328, P = 0.020) between general hospitals and specialty hospitals. There were significant differences between the average bed-to-nurse ratios in tertiary-level hospitals (Z = -4.178, P < 0.0001) and the pediatric inpatient wards of the surveyed hospitals (Z = -4.518, P < 0.0001) and the national standard. CONCLUSION: There is a nursing shortage in tertiary-level hospitals and some grade-A specialty hospitals in Sichuan, China. The shortage is worse in pediatric inpatient wards, especially in the general hospitals and some grade-B specialty hospitals. Hospital administrations need to understand the situation and offer strategies to cope for routine nursing management as well as disaster management.