Application of time-frequency domain and deep learning fusion feature in non-invasive diagnosis of congenital heart disease-related pulmonary arterial hypertension.

Pulmonary arterial hypertension associated with congenital heart disease (CHD-PAH) is a fatal cardiovascular disease. A novel method for non-invasive initial diagnosis of the CHD-PAH was put forward in this work. First, original heart sounds were segmented into each cardiac cycle by using double-threshold adaptive method. According to clinical auscultation, the pathological information of CHD-PAH is concentrated in S2, so the time-frequency features in both of an entire cardiac cycle and S2 were extracted. Then the time-frequency features combine with the deep learning features to form a feature vector. It is the fusion feature, which will be input into a classifier. Finally, the majority voting algorithm was used to obtain the optimal classification results. A classification accuracy of 88.61% was achieved using this novel method. Three points are essential: •A double-threshold adaptive method is used to segment heart sound into each cardiac cycle.•The time-frequency domain features in both of an entire cardiac cycle and S2 were extracted, which are combined with deep learning features to form the fusion feature.•The XGBoost was used as three-class classifier for the classification of normal, CHD and CHD-PAH. The majority voting algorithm was used to obtain the optimal classification results.

Bioorthogonal in situ assembly of nanomedicines as drug depots for extracellular drug delivery.

Developing precise nanomedicines to improve the transport of anticancer drugs into tumor tissue and to the final action site remains a critical challenge. Here, we present a bioorthogonal in situ assembly strategy for prolonged retention of nanomedicines within tumor areas to act as drug depots. After extravasating into the tumor site, the slightly acidic microenvironment induces the exposure of cysteine on the nanoparticle surface, which subsequently undergoes a bioorthogonal reaction with the 2-cyanobenzothiazole group of another neighboring nanoparticle, enabling the formation of micro-sized drug depots to enhance drug retention and enrichment. This in situ nanoparticle assembly strategy remarkably improves the antimetastatic efficacy of extracellular-targeted drug batimastat, and also leads to the simultaneous enhanced retention and sustained release of multiple agents for combined cocktail chemoimmunotherapy to finally elicit a potent antitumor immune response. Such in situ assembly of nanomedicines represents a generalizable strategy towards extracellular drug delivery and cocktail chemoimmunotherapy.

Mitophagy-Related Gene Signature for Prediction Prognosis, Immune Scenery, Mutation, and Chemotherapy Response in Pancreatic Cancer.

Mitophagy is a conserved cellular process that plays a vital role in maintaining cellular homeostasis by selectively removing dysfunctional mitochondria. Notwithstanding that growing evidence suggests that mitophagy is implicated in pancreatic tumorigenesis, the effect of mitophagy-related genes on pancreatic cancer (PC) prognosis and therapeutic response remains largely unknown. In this study, we sought to construct a mitophagy-related gene signature and assessed its ability to predict the survival, immune activity, mutation status, and chemotherapy response of PC patients. During the screening process, we identified three mitophagy-related genes (PRKN, SRC, VDAC1) from The Cancer Genome Atlas (TCGA) cohort and a 3-gene signature was established. The prognostic model was validated using an International Cancer Genome Consortium (ICGC) cohort and two Gene Expression Omnibus (GEO) cohorts. According to the median risk score, PC patients were divided into high and low-risk groups, and the high-risk group correlated with worse survival in the four cohorts. The risk score was then identified as an independent prognostic predictor, and a predictive nomogram was constructed to guide clinical decision-making. Remarkably, enhanced immunosuppressive levels and higher mutation rates were observed in patients from the high-risk group, which may account for their poor survival. Furthermore, we found that high-risk patients were more sensitive to paclitaxel and erlotinib. In conclusion, a mitophagy-related gene signature is a novel prognostic model that can be used as a predictive indicator and allows prognostic stratification of PC patients.