Search

Hemodynamic parameters derived from pulse wave analysis have been shown to predict long-term outcomes in patients with heart failure (HF). Here we aimed to develop a deep-learning based algorithm that incorporates pressure waveforms for the identification and risk stratification of patients with HF. The first study, with a case–control study design to address data imbalance issue, included 431 subjects with HF exhibiting typical symptoms and 1545 control participants with no history of HF (non-HF). Carotid pressure waveforms were obtained from all the participants using applanation tonometry. The HF score, representing the probability of HF, was derived from a one-dimensional deep neural network (DNN) model trained with characteristics of the normalized carotid pressure waveform. In the second study of HF patients, we constructed a Cox regression model with 83 candidate clinical variables along with the HF score to predict the risk of all-cause mortality along with rehospitalization. To identify subjects using the HF score, the sensitivity, specificity, accuracy, F1 score, and area under receiver operating characteristic curve were 0.867, 0.851, 0.874, 0.878, and 0.93, respectively, from the hold-out cross-validation of the DNN, which was better than other machine learning models, including logistic regression, support vector machine, and random forest. With a median follow-up of 5.8 years, the multivariable Cox model using the HF score and other clinical variables outperformed the other HF risk prediction models with concordance index of 0.71, in which only the HF score and five clinical variables were independent significant predictors (p < 0.05), including age, history of percutaneous coronary intervention, concentration of sodium in the emergency room, N-terminal pro-brain natriuretic peptide, and hemoglobin. Our study demonstrated the diagnostic and prognostic utility of arterial waveforms in subjects with HF using a DNN model. Pulse wave contains valuable information that can benefit the clinical care of patients with HF. [ABSTRACT FROM AUTHOR]

Little is known about genes that induce stem cells differentiation into astrocytes. We previously described that heat shock protein 27 (HSP27) downregulation is directly related to neural differentiation under chemical induction in placenta-derived multipotent stem cells (PDMCs). Using this neural differentiation cell model, we cross-compared transcriptomic and proteomic data and selected 26 candidate genes with the same expression trends in both omics analyses. Those genes were further compared with a transcriptomic database derived from Alzheimer's disease (AD). Eighteen out of 26 candidates showed opposite expression trends between our data and the AD database. The mRNA and protein expression levels of those candidates showed downregulation of HSP27, S100 calcium-binding protein A16 (S100A16) and two other genes in our neural differentiation cell model. Silencing these four genes with various combinations showed that co-silencing HSP27 and S100A16 has stronger effects than other combinations for astrocyte differentiation. The induced astrocyte showed typical astrocytic star-shape and developed with ramified, stringy and filamentous processes as well as differentiated endfoot structures. Also, some of them connected with each other and formed continuous network. Immunofluorescence quantification of various neural markers indicated that HSP27 and S100A16 downregulation mainly drive PDMCs differentiation into astrocytes. Immunofluorescence and confocal microscopic images showed the classical star-like shape morphology and co-expression of crucial astrocyte markers in induced astrocytes, while electrophysiology and Ca2+ influx examination further confirmed their functional characteristics. In conclusion, co-silencing of S100A16 and HSP27 without chemical induction leads to PDMCs differentiation into functional astrocytes. [ABSTRACT FROM AUTHOR]