Search

BackgroundWithout timely diagnosis and treatment, tachycardia, also called tachyarrhythmia, can cause serious complications such as heart failure, cardiac arrest, and even death. The predictive performance of conventional clinical diagnostic procedures needs improvement in order to assist physicians in detecting risk early on. ObjectiveWe aimed to develop a deep tachycardia onset prediction (TOP-Net) model based on deep learning (ie, bidirectional long short-term memory) for early tachycardia diagnosis with easily accessible data. MethodsTOP-Net leverages 2 easily accessible data sources: vital signs, including heart rate, respiratory rate, and blood oxygen saturation (SpO2) acquired continuously by wearable embedded systems, and electronic health records, containing age, gender, admission type, first care unit, and cardiovascular disease history. The model was trained with a large data set from an intensive care unit and then transferred to a real-world scenario in the general ward. In this study, 3 experiments incorporated merging patients’ personal information, temporal memory, and different feature combinations. Six metrics (area under the receiver operating characteristic curve [AUROC], sensitivity, specificity, accuracy, F1 score, and precision) were used to evaluate predictive performance. ResultsTOP-Net outperformed the baseline models on the large critical care data set (AUROC 0.796, 95% CI 0.768-0.824; sensitivity 0.753, 95% CI 0.663-0.793; specificity 0.720, 95% CI 0.645-0.758; accuracy 0.721; F1 score 0.718; precision 0.686) when predicting tachycardia onset 6 hours in advance. When predicting tachycardia onset 2 hours in advance with data acquired from our hospital using the transferred TOP-Net, the 6 metrics were 0.965, 0.955, 0.881, 0.937, 0.793, and 0.680, respectively. The best performance was achieved using comprehensive vital signs (heart rate, respiratory rate, and SpO2) statistical information. ConclusionsTOP-Net is an early tachycardia prediction model that uses 8 types of data from wearable sensors and electronic health records. When validated in clinical scenarios, the model achieved a prediction performance that outperformed baseline models 0 to 6 hours before tachycardia onset in the intensive care unit and 2 hours before tachycardia onset in the general ward. Because of the model’s implementation and use of easily accessible data from wearable sensors, the model can assist physicians with early discovery of patients at risk in general wards and houses.

The aim of this study was to investigate the core components and mechanism of action of Rosa roxburghii fruit flavonoids in the intervention of ulcerative colitis (UC) using network pharmacology and molecular docking. We extracted flavonoids from R. roxburghii fruit by an ethanol-cellulase method and used liquid chromatography-mass spectrometry (LC-MS) to identify the major chemical components of the flavonoid extract, and then we selected 34 active flavonoid components and 146 targets in the intervention of UC on an analytical platform and constructed a “R. roxburghii flavonoids-active components-intersecting targets-UC” network. The results of gene ontology pathway analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis showed that the intervention of R. roxburghii flavonoids in UC mainly involved the arachidonic acid signaling pathway, the nuclear factor-kappa B signaling pathway, and cancer pathways. Molecular docking was performed on the major active ingredients and the key targets selected from the network, with docking energies all less than −6.0 kcal/mol, indicating a strong binding affinity between the core active ingredients and the key targets for UC treatment. So, the network analysis results are reliable. The results of animal experiments showed that intervention with R. roxburghii flavonoids could effectively alleviate the body mass loss and colon pathological changes of UC mice, and significantly inhibit the expression of inflammatory cytokines such as tumour necrosis factor-α, interleukin (IL)-1β and IL-6 in the UC model group (P < 0.05). The results of Western blot showed that R. roxburghii flavonoids could effectively inhibit the expression of the key target proteins associated with the metabolic pathway of arachidonic acid, such as cyclooxygenase-2 and 5-lipoxygenase. In conclusion, R. roxburghii flavonoids can intervene in UC through a multi-component, multi-target and multi-pathway mechanism. The results of this research can provide a theoretical basis for the development and utilization of functional foods from R. roxburghii.

With the social and economic development and the improvement of people’s living standards, people have put forward higher requirements for the governance of the ecological environment, and the goals for the management of local landscapes are becoming more and more diversified. This paper constructs a dynamic and coordinated GRL governance model according to the characteristics of local landscape language. It uses the gray correlation model to explore the correlation between the constituent factors of the damaging ecological environment effect. Taking the loess hills landscape of S province as the research object, the governance effect of ecological environment construction on vegetation, soil, and landscape patterns is explored. The study shows that after the environmental environment management, the number of landscape patches in the region increased by 18, and the fragmentation index of each landscape increased by 0.0475 Block / km2 on average, which increased the spatial structure complexity of the landscape. The study’s findings can provide theoretical guidance for managing local landscape language comprehensively and have a specific scientific basis.