Health-related quality of life in post-infectious bronchiolitis obliterans: agreement between children and their proxy

A long short-term memory-fully connected (LSTM-FC) neural network for predicting the incidence of bronchopneumonia in children

Bronchopneumonia is the most common infectious disease in children, and it seriously endangers children's health. In this paper, a deep neural network combining long short-term memory (LSTM) layers and fully connected layers was proposed to predict the prevalence of bronchopneumonia in children in Chengdu based on environmental factors and previous prevalence rates. The mean square error (MSE), mean absolute error (MAE), and Pearson correlation coefficient (R) were used to detect the performance of the deep learning model. The values of MSE, MAE, and R in the test dataset are 0.0051, 0.053, and 0.846, respectively. The results show that the proposed model can accurately predict the prevalence of bronchopneumonia in children. We also compared the proposed model with three other models, namely, a fully connected (FC) layer neural network, a random forest model, and a support vector machine. The results show that the proposed model achieves better performance than the three other models by capturing time series and mitigating the lag effect.

Health-related quality of life in patients with bronchiolitis obliterans

INTRODUCTION

Bronchiolitis obliterans (BO) is mainly caused by infections and hematopoietic stem cell transplantation (HSCT). This study aimed to investigate the health-related quality of life (HRQOL) of children with BO compared to the healthy children and also to assess the HRQOL according to the etiology.

METHODS

Postinfectious (group 1) and post-HSCT BO (group 2) patients and healthy children were included in the study. HRQOL was assessed by the Short Form-36 (SF-36) and St George's Respiratory Questionnaire (SGRQ). Correlations between demographic and clinical characteristics, pulmonary function tests, high-resolution chest tomography scores, and HRQOL were assessed.

RESULTS

Thirty-seven postinfectious and post-HSCT BO patients and 34 healthy children were included in the study. Mean age was 13.8 ± 0.7 years. Mean forced vital capacity and forced expiratory volume₁ were 60.7 ± 2.7% predicted, and 49.8 ± 3.1% predicted, respectively. The SF-36 scores were lower in BO patients compared to healthy children (P < .01). Patients with better lung functions had higher SF-36 scores, but lower SGRQ. The number of inhaled therapies, acute exacerbations, hospitalizations were inversely correlated with SF-36. A positive correlation was found between these parameters and total SGRQ scores (r = .507, P = .02; r = .409, P = .12; r = .326, P = .049, respectively). SF-36 scores were better in group 1 for subscales of physical role functioning and social role functioning compared to group 2. (P = .01, P = .01, respectively).

CONCLUSION

The HRQOL of patients with BO measured by SF-36 was low compared to healthy children. SF-36 scores were more affected in post-HSCT BO patients. HRQOL of children with chronic lung disease should be taken into consideration in the management of these patients.