RESUMO
Background: This present work focused on predicting prognostic outcome of inpatients developing acute exacerbation of chronic obstructive pulmonary disease (AECOPD), and enhancing patient monitoring and treatment by using objective clinical indicators. Methods: The present retrospective study enrolled 322 AECOPD patients. Registry data downloaded based on COPD Pay-for-Performance Program database from January 2012 to December 2018 were used to check whether the enrolled patients were eligible. Our primary and secondary outcomes were ICU admission and in-hospital mortality, respectively. The best feature subset was chosen by recursive feature elimination. Moreover, seven machine learning (ML) models were trained for forecasting ICU admission among AECOPD patients, and the model with the most excellent performance was used. Results: According to our findings, random forest (RF) model showed superb discrimination performance, and the values of area under curve (AUC) were 0.973 and 0.828 in training and test cohorts, separately. Additionally, according to decision curve analysis, the net benefit of RF model was higher when differentiating patients with a high risk of ICU admission at a <0.55 threshold probability. Moreover, the ML-based prediction model was also constructed to predict in-hospital mortality, and it showed excellent calibration and discrimination capacities. Conclusion: The ML model was highly accurate in assessing the ICU admission and in-hospital mortality risk for AECOPD cases. Maintenance of model interpretability helped effectively provide accurate and lucid risk prediction of different individuals.
RESUMO
OBJECTIVE: Lonicera japonica Thunb (LJT) is a commonly used herbal soup to treat inflammation-related diseases. However, the effect of LJT on ALI is unknown. The present study was aimed at investigating the protective effects of LJT extract (LTE) and its active ingredient luteolin (Lut) on lipopolysaccharide (LPS)-stimulated ALI and investigate its potential mechanism. MATERIALS AND METHODS: The effects of LTE and Lut were explored in an ALI mouse model induced by intraperitoneal injection of lipopolysaccharide (LPS). Besides, the LPS-induced inflammation model in BEAS-2B cells was used to clarify the underlying mechanisms. The ALI pathological changes in lung tissues were tested through Haematoxylin and eosin (HE) staining. The apoptosis of cells in lung tissue and the cell model in vitro was evaluated by TUNEL assays, respectively. Meanwhile, the viability of cells in vitro was evaluated by Cell Counting Kit-8 (CCK-8) assay. The levels/concentrations of tumor necrosis factor-α (TNF-α), interleukin-6 (IL-6), IL-1ß and IL-10 in BALF were detected by enzyme-linked immunosorbent assay (ELISA). Besides, through quantitative real-time polymerase chain reaction (qRT-PCR) and Western blotting, the expression of the above-mentioned inflammatory factors and key factors in the NF-κB signaling pathway was examined. The distribution of inflammatory factors in tissue was observed through immunohistochemistry (IHC) assays . RESULTS: In relative to LPS-stimulated group, the in vivo study showed that LTE and different concentrations of Lut dramatically alleviated LPS-evoked lung pathological injury and lung edema based on the changes in total protein levels and lung wet/dry (W/D) ratio in the bronchoalveolar lavage fluid (BALF) from ALI mice. LTE and different concentrations of Lut also suppressed the inflammatory response, as reflected by the variations of neutrophil accumulation and the production of proinflammatory and anti-inflammatory cytokines in the lung tissues and BALF of ALI mice. The in vitro research also demonstrated that LTE and Lut visibly facilitated cell viability and restrained the apoptosis of BEAS-2B cells stimulated by LPS. Lut hindered LPS-inducible activation of NF-κB pathway in BEAS-2B cells. CONCLUSION: The present study proved that LTE might suppress LPS-induced acute injury and inflammation in mice and BEAS-2B cells through the Lut-caused suppression of NF-κB signal path (Figure 1).