Development and application of a deep learning-based comprehensive early diagnostic model for chronic obstructive pulmonary disease.

BACKGROUND: Chronic obstructive pulmonary disease (COPD) is a frequently diagnosed yet treatable condition, provided it is identified early and managed effectively. This study aims to develop an advanced COPD diagnostic model by integrating deep learning and radiomics features. METHODS: We utilized a dataset comprising CT images from 2,983 participants, of which 2,317 participants also provided epidemiological data through questionnaires. Deep learning features were extracted using a Variational Autoencoder, and radiomics features were obtained using the PyRadiomics package. Multi-Layer Perceptrons were used to construct models based on deep learning and radiomics features independently, as well as a fusion model integrating both. Subsequently, epidemiological questionnaire data were incorporated to establish a more comprehensive model. The diagnostic performance of standalone models, the fusion model and the comprehensive model was evaluated and compared using metrics including accuracy, precision, recall, F1-score, Brier score, receiver operating characteristic curves, and area under the curve (AUC). RESULTS: The fusion model exhibited outstanding performance with an AUC of 0.952, surpassing the standalone models based solely on deep learning features (AUC = 0.844) or radiomics features (AUC = 0.944). Notably, the comprehensive model, incorporating deep learning features, radiomics features, and questionnaire variables demonstrated the highest diagnostic performance among all models, yielding an AUC of 0.971. CONCLUSION: We developed and implemented a data fusion strategy to construct a state-of-the-art COPD diagnostic model integrating deep learning features, radiomics features, and questionnaire variables. Our data fusion strategy proved effective, and the model can be easily deployed in clinical settings. TRIAL REGISTRATION: Not applicable. This study is NOT a clinical trial, it does not report the results of a health care intervention on human participants.

Prolonged parent-child separation and pain in adolescence: The role of HPA-axis genetic variations.

BACKGROUND: Increasing evidence has demonstrated that childhood adversity was a predictor of pain and hypothalamic-pituitary-adrenal (HPA) axis genetic variation is associated with pain risk. This study aims to explore possible effects of prolonged childhood separation from parents and HPA polygenic risk score (PRS) on pain among adolescents in rural China. METHOD: We used data from 219 adolescents in rural area of Fuyang city, Anhui province, China. Parent-child separation was collected through interview and pain intensity was reported using the 11-point Numerical Rating Scale. SNP genotyping was performed using an improved multiplex ligation detection reaction (iMLDR) technique. The PRS was computed based on 3 single nucleotide polymorphisms (SNPs) in 2 genes (FKBP5 and NR3C1) related to HPA-axis stress reactivity. RESULTS: Pain among adolescents separated from both parents scored higher compared to those without parent-child separation, however, this association was only observed in adolescents with moderate to high tertiles of PRS groups (parent-child separation in moderate group vs. no parent-child separation in moderate group: 3.07 vs. 1.57, P < 0.001; parent-child separation in highest group vs. no parent-child separation in highest group: 3.02 vs. 1.26, P < 0.001; parent-child separation in lowest group vs. no parent-child separation in lowest group: 2.34 vs. 1.25, P = 0.225). After controlled for demographic characteristics, psychopathological symptoms, adverse childhood experiences, parental warmth, prolonged childhood parent-child separation increased pain scores by 1.52 points (95% CI:0.72, 2.33) and 1.72 points (95% CI:1.13, 2.31) in moderate and high PRS groups, respectively. CONCLUSION: Our findings suggest that adolescents separated from both parents while carrying more risk alleles related to HPA-axis stress reactivity are at heightened risk of pain.

Association between prolonged separation from parents and allostatic load among children in China.

OBJECTIVE: To capture the association of exposure to prolonged separation from both parents early in life and allostatic load (AL), a measure of biological multi-system dysregulation. METHODS: We used data from 557 7-12-year-old children enrolled in rural area of Chizhou city, Anhui Province, China. We computed an AL score based on eleven biomarkers representing four regulatory systems: immune/inflammatory system (high sensitivity C-reactive protein); metabolic system (body mass index; high density lipoprotein; low density lipoprotein, total cholesterol; triglycerides; fasting glucose; glycated hemoglobin; insulin) and cardiovascular system (systolic and diastolic blood pressure). Child's experiences of parent-child separation were collected a brief online questionnaire by parents of children. RESULTS: More than 1 in 3 of our participants separated with both parents at age 6 or younger and nearly 1 in 10 persistently separated from both parents after birth. The AL score was significantly higher among children separated from both parents during early childhood (3.25 ± 1.98) or persistently since birth (3.48 ± 1.92), compared with those who did not separated from both parents (2.34 ± 1.53, F = 12.992, P<0.001). After adjustment of demographic covariates, body mass index as well as parent frequency of communication and parental warmth, children who separated from both parents in early childhood (ß = 0.84, 95%CI:0.40, 1.28, P < 0.001) or persistently into adolescence (ß = 1.27, 95%CI:0.43, 2.12, P = 0.003) evinced the highest levels of AL. CONCLUSION: This study is the first to show an association between prolonged parent-child separation and physiological wear-and-tear as measured by AL, which provides potential insights into the biological mechanisms underpinning long-term health outcomes in contexts of parent-child separation.