Background: Bronchopulmonary dysplasia (BPD) is a common chronic lung disease in extremely preterm neonates. The outcome and clinical burden vary dramatically according to severity. Although some prediction tools for BPD exist, they seldom pay attention to disease severity and are based on populations in developed countries. This study aimed to develop machine learning prediction models for BPD severity based on selected clinical factors in a Chinese population. Methods: In this retrospective, single-center study, we included patients with a gestational age < 32 weeks who were diagnosed with BPD in our neonatal intensive care unit from 2016 to 2020. We collected their clinical information during the maternal, birth and early postnatal periods. Risk factors were selected through univariable and ordinal logistic regression analyses. Prediction models based on logistic regression (LR), gradient boosting decision tree, XGBoost (XGB) and random forest (RF) models were implemented and assessed by the area under the receiver operating characteristic curve (AUC). Results: We ultimately included 471 patients (279 mild, 147 moderate, and 45 severe cases). On ordinal logistic regression, gestational diabetes mellitus, initial fraction of inspiration O2 value, invasive ventilation, acidosis, hypochloremia, C-reactive protein level, patent ductus arteriosus and Gram-negative respiratory culture were independent risk factors for BPD severity. All the XGB, LR and RF models (AUC = 0.85, 0.86 and 0.84, respectively) all had good performance. Conclusions: We found risk factors for BPD severity in our population and developed machine learning models based on them. The models have good performance and can be used to aid in predicting BPD severity in the Chinese population.
Background: Respiratory infections are one of three leading causes of childhood mortality, and worldwide increase and recent plateau in childhood asthma has been reported. However, data on trends of respiratory diseases over long period of time is limited. This study aimed to determine the trends of respiratory disease outpatient visits (ROVs) and diagnoses (RODs) in one of the largest children’s teaching hospitals in China between 2009 and 2018. Methods: A retrospective study based on routine administrative data was designed and implemented according to the RECORD statement. Demographic details and diagnoses of the outpatients < 18 years visiting the respiratory department of the hospital were extracted from the Hospital Information System. Age- and gender-specific trends were illustrated by calculating average annual growth rate (AAGR) for ROVs and comparing change of proportion for different RODs over time. Results: There were 698,054 ROVs from 285,574 children (40.4% female). AAGR of ROVs was 15.2%. Children aged 4 to < 7 years had a faster increase than other age groups. Bronchitis (27.6%), pneumonia (18.5%), pneumonia affecting other systems (18.4%), asthma and status asthmaticus (10.7%), and vasomotor and allergic rhinitis (9.2%) accounted for 84.4% of all RODs. The proportion of bronchitis decreased across years, with the concomitant increasing trend in the proportion of pneumonia. Age-specific trend in diagnoses showed greater proportion of asthma in all visits for the children aged 7 to < 18 years than younger children. Gender-specific trend in diagnoses showed the proportion of asthma was greater for males but the AAGR was greater for females. Conclusion: The persistent upward trend in ROVs was observed among children at different ages and a gender difference was also seen. In contrast to what has been reported, burden of asthma and allergies diseases continues to increase locally.
Background: To evaluate the effectiveness of training on knowledge and practice of infection prevention and control (IPC) among pediatric health care workers (HCW) in Shanghai, China, in the context of COVID-19 pandemic. Methods: An online training program was designed by the Shanghai Pediatric Clinical Quality Control Center (SPQCC) during the early phase of COVID-19 pandemic on disease knowledge and practice of IPC. Training took place in the 81 partner hospitals affiliated with SPQCC. A multicenter, cross-sectional questionnaire survey was designed with a 25-item self-administered questionnaire to evaluate the knowledge gained from the training. Stratified-random sampling was used to select HCW according to three professionals (i.e., pediatricians, nurses and administrators) within each partner hospital. Awareness and knowledge of COVID-19 and its related infection control and practice were assessed by comparing survey results between different types of hospitals, professionals and professional ranks. A higher survey score meant that the respondent was more prepared and knowledgeable about COVID-19 and its infection control measures. Results: Completed questionnaires were returned from 1,062 subjects (385 pediatricians, 410 nurses, and 267 administrators), giving a response rate of 96.5%. Overall, awareness of clinical information related to COVID-19, importance of personal hygiene and isolation policy was high among the respondents. No statistical difference of scores on knowledge of COVID-19, IPC and relevant practice between the tertiary and peripheral hospitals. Among all respondents, middle-ranked health care personnel were most knowledgeable and achieved the highest score. Conclusions: Majority of pediatric HCW showed good recognition and practice in infection protection and control measures. The online training was able to achieve its aim to enhance knowledge and awareness and could have contributed to the zero infection rate among HCW caring for confirmed COVID-19 cases in Shanghai.