Construction and evaluation of prognostic models of ECMO in elderly patients with cardiogenic shock based on BP neural network, random forest, and decision tree.

OBJECTIVE: To analyze the predictive effect of a back propagation (BP) neural network, random forest (RF) and decision tree model on the prognosis of elderly patients with cardiogenic shock after extracorporeal membrane oxygenation (ECMO). METHODS: This is a retrospective analysis of the clinical data of elderly patients with cardiogenic shock (258 cases) who underwent ECMO in People's Hospital of Guangxi Zhuang Autonomous Region from January 2016 to January 2022. All patients were followed up for 6 months after ECMO treatment. The prognosis was evaluated, and the prognostic factors were analyzed. BP neural network, RF and decision tree were used to establish predictive models, and the predictive performance of the models was evaluated. RESULTS: Among the 258 elderly patients with cardiogenic shock, 52 (20.16%) died 6 months after the ECMO treatment. Based on BP neural network, RF, and decision tree, predictive models for the prognosis and death of elderly patients with cardiogenic shock were constructed. A test set was used to predict the performance of the three models. The results showed that the predictive performances of the three models were all more than 80.00%. The accuracy, sensitivity, and specificity of the RF model were 0.987, 1.000, and 0.929 respectively, which were higher than those of the decision tree model. The area under the receiver operating characteristic curve (AUC) of the RF model was 1.000, which was higher than 0.916 for the decision tree model. DeLong test showed that there was a significant difference in the AUC of the RF model compared to the decision tree test set (D=-2.063, P=0.042 < 0.05). CONCLUSION: The predictive performance is good in all the three models, which have a high application value for prognosis of ECMO in elderly patients with cardiogenic shock. In clinical practice, predictive models should be selected according to the actual situation, so clinicians and patients can make decisions.

[Association of 5-hydroxytryptamine transporter gene polymorphism with asthma and comorbid depression].

OBJECTIVE: To explore the molecular genetic mechanism of complicating depression in asthma by detecting two gene polymorphisms of 5-hydroxytryptamine transporter (5-HTTLPR/Stin2) gene. METHODS: One hundred fifty-six adults with asthma were collected, and divided into group of asthma with depression (HAMD score > or = 8) and group of asthma without depression or single asthma (HAMD score <8) according to the score of Hamilton depression scale (HAMD). A total of 508 adults with depression alone and 433 healthy individuals were enrolled as controls. The target gene fragments containing the polymorphic regions of 5-HTTLPR and Stin2 were amplified by polymerase chain reaction (PCR). The amplified fragments were then analyzed using agarose gel electrophoresis (AGE) and motored molecular imaging system. RESULTS: The frequencies of genotype and allele distribution of the Stin2 polymorphism showed that males with genotype Stin2.12/Stin2.10 and allele Stin2.10 had higher risk for asthma than the others (Stin2.12/Stin2.10: OR = 2.291, 95% CI: 1.195 and 4.390; Stin2.10: OR = 1.942, 95% CI: 1.069-3.527). No significant difference was found in the frequencies of genotype and allele distribution of the 5-HTTLPR locus between the asthma and healthy control groups and the two stratified by gender. CONCLUSION: The Stin2 polymorphism may play a role in the onset of male asthma. There might be association between the genetic pathogenesis of asthma and depression.

[The study on relationship between negative mood states and asthma control and quality of life].

OBJECTIVE: To explore the relationship between psychological status including depression and anxiety, and asthma control and quality of life. METHODS: A brief, structured psychiatric interview using the Hamilton depression scale (HAMD) and the Hamilton anxiety scale (HAMA) were applied to 156 consecutive adults with confirmed, physician-diagnosed asthma. Asthma control and asthma-related quality of life were assessed using the asthma control questionnaire (ACQ) and the asthma quality of life questionnaire (AQLQ). Detection of FEV1, FVC and PEF with standard spirometry for all patients was conducted. The patients were divided into depression (DG), anxiety (AG), depression and anxiety (ADG), and non depression and/or non anxiety (NADG) groups according to the scores for depression and anxiety degree. Level of asthma control, quality of life and pulmonary function of different groups were compared and a multiple regression model was set for the analisis. RESULTS: Sixty five percent of patients (n=101) had symptoms of depression or anxiety (18% had depression, 5% had anxiety, and 42% had both). Analyses revealed independent effects for depression but not anxiety, on total ACQ and AQLQ scores (both P<0.05). Moreover, there was no interaction effects on anxiety and depression coupled with anxiety. CONCLUSION: It suggests that depression but not anxiety, is associated with worse asthma control and asthma-related quality of life. Physicians should consider the differential impact of negative mood states when assessing levels of asthma control and quality of life.