External validation of a machine learning model to predict hemodynamic instability in intensive care unit.

BACKGROUND: Early prediction model of hemodynamic instability has the potential to improve the critical care, whereas limited external validation on the generalizability. We aimed to independently validate the Hemodynamic Stability Index (HSI), a multi-parameter machine learning model, in predicting hemodynamic instability in Asian patients. METHOD: Hemodynamic instability was marked by using inotropic, vasopressor, significant fluid therapy, and/or blood transfusions. This retrospective study included among 15,967 ICU patients who aged 20 years or older (not included 20 years) and stayed in ICU for more than 6 h admitted to Taipei Veteran General Hospital (TPEVGH) between January 1, 2010, and March 31, 2020, of whom hemodynamic instability occurred in 3053 patients (prevalence = 19%). These patients in unstable group received at least one intervention during their ICU stays, and the HSI score of both stable and unstable group was calculated in every hour before intervention. The model performance was assessed using the area under the receiver operating characteristic curve (AUROC) and was compared to single indicators like systolic blood pressure (SBP) and shock index. The hemodynamic instability alarm was set by selecting optimal threshold with high sensitivity, acceptable specificity, and lead time before intervention was calculated to indicate when patients were firstly identified as high risk of hemodynamic instability. RESULTS: The AUROC of HSI was 0.76 (95% CI, 0.75-0.77), which performed significantly better than shock Index (0.7; 95% CI, 0.69-0.71) and SBP (0.69; 95% CI, 0.68-0.70). By selecting 0.7 as a threshold, HSI predicted 72% of all 3053 patients who received hemodynamic interventions with 67% in specificity. Time-varying results also showed that HSI score significantly outperformed single indicators even up to 24 h before intervention. And 95% unstable patients can be identified more than 5 h in advance. CONCLUSIONS: The HSI has acceptable discrimination but underestimates the risk of stable patients in predicting the onset of hemodynamic instability in an external cohort.

Correlation between cardiac resynchronization response and pulmonary artery hemodynamic parameters / 中南大学学报(医学版)

OBJECTIVES@#To evaluate the response to cardiac resynchronization therapy (CRT) and the correlation between CRT and pulmonary artery hemodynamic parameters.@*METHODS@#The patients with chronic heart failure indicator for CRT were enrolled. The left ventricular end-systolic volume (LVESV) was measured by echocardiography and New York Heart Association (NYHA) classification was evaluated between one week before and six months after CRT. Mean pulmonary artery pressure (mPAP), pulmonary artery systolic pressure (PASP) and pulmonary vascular resistance (PVR) were measured by right heart catheterization. Left ventricular reverse remodeling (LVRR) is defined as a decrease of 15% or more in LVESV at the 6th month after CRT; Clinical response is defined as a decrease of NYHA classification at or above grade 1 at the 6th month after CRT. Pulmonary hypertension (PH) was defined as mPAP≥25 mmHg. According to the response, patients were divided into 3 groups: group A (LVRR+clinical response), group B (no LVRR+clinical response) and group C (no LVRR+no clinical response). The changes of NYHA classification, echocardiographic and pulmonary hemodynamic parameters were observed in the 3 groups. The Kaplan-Meier survival curve was used to analyze the differences in all-cause mortality, combined end-point events of death or re-hospitalization due to heart failure among different groups.@*RESULTS@#A total of 45 patients with CRT implantation [aged (63.27±9.55) years, 36 males] were included. The average follow-up period was (33.76±11.50) months. Thirty-one patients (68.89%) were in group A, 9 of whom with PH. Eight patients (17.78%) were in group B, 7 of whom with PH. Six patients were in group C, all with PH. Cardiac function including NYHA classification, echocardiographic and pulmonary hemodynamic parameters had been significantly improved in group A after CRT implantation (0.05). There were no significant changes in NYHA classification, echocardiographic and pulmonary hemodynamic parameters in group C (>0.05). Compared with group C, group A and group B had lower all-cause mortality (=0.005) and lower incidence of composite endpoint events (=0.001).@*CONCLUSIONS@#Patients with LVRR and clinical response after CRT have a good prognosis. Patients with clinical response but without LVRR have a better prognosis than those without clinical response and LVRR, which may be related to the decrease of pulmonary hemodynamic parameters such as mPAP and TPG.

Association study of LIS1 and TSNAX genes with bipolar disorder in Chinese Han population / 中华医学遗传学杂志

<p><b>OBJECTIVE</b>To assess the association of neural development-related genes LIS1and TSNAX with bipolar disorder in a Chinese Han population.</p><p><b>METHODS</b>Three hundred and eight five patients (including 188 males and 197 females) from Guangzhou Brain Hospital with bipolar disorder meeting the Diagnostic and Statistic Manual of Bipolar Disorder (BDI) (Fourth Edition) criteria and 475 healthy controls from the local community were recruited. Ten single nucleotide polymorphisms (SNPs) of the LIS1 and TSNAX genes were genotyped by GoldenGate genotyping assay on an Illumina Beadstation 500 machine. Association analyses of SNPs and haplotypes were performed with Plink 1.07 software.</p><p><b>RESULTS</b>Analysis of the total sample has failed to find any association of SNP or haplotype of the two genes with BDI (P> 0.05). When patients were divided into subgroups with or without psychotic symptom, no significant association of the two genes was found with psychotic BDI or non-psychotic BDI (P> 0.05). No significant association was found between any SNP and haplotype of two genes and female BDI or male BDI, nor were significant association found between age of onset and LIS1 and TSNAX gene polymorphisms.</p><p><b>CONCLUSION</b>Our results indicated that LIS1 and TSNAX genes are not associated with susceptibility to bipolar I disorder in Chinese Han population.</p>