We aimed to build up multiple machine learning models to predict 30-days mortality, and 3 complications including septic shock, thrombocytopenia, and liver dysfunction after open-heart surgery. ...Patients who underwent coronary artery bypass surgery, aortic valve replacement, or other heart-related surgeries between 2001 and 2012 were extracted from MIMIC-III databases. Extreme gradient boosting, random forest, artificial neural network, and logistic regression were employed to build models by utilizing fivefold cross-validation and grid search. Receiver operating characteristic curve, area under curve (AUC), decision curve analysis, test accuracy, F1 score, precision, and recall were applied to access the performance. Among 6844 patients enrolled in this study, 215 patients (3.1%) died within 30 days after surgery, part of patients appeared liver dysfunction (248; 3.6%), septic shock (32; 0.5%), and thrombocytopenia (202; 2.9%). XGBoost, selected to be our final model, achieved the best performance with highest AUC and F1 score. AUC and F1 score of XGBoost for 4 outcomes: 0.88 and 0.58 for 30-days mortality, 0.98 and 0.70 for septic shock, 0.88 and 0.55 for thrombocytopenia, 0.89 and 0.40 for liver dysfunction. We developed a promising model, presented as software, to realize monitoring for patients in ICU and to improve prognosis.
This study evaluated the relationship between hyperuricemia at admission and the clinical prognosis of patients with sepsis. The data were obtained from the Intensive Care Medical Information ...Database III. The patients were divided into a normal serum uric acid group and a hyperuricemia group. The main outcome was 90-day mortality, and the secondary outcomes were hospital mortality, 30-day mortality, and acute kidney injury. Propensity score matching was used to balance the baseline characteristics of the groups. Our study retrospectively included 954 patients. Before and after propensity score matching, the incidence of AKI, the 30-day and 90-day mortality rates were significantly higher in the hyperuricemia group. Cox regression analysis showed that hyperuricemia was significantly associated with 90-day mortality (HR 1.648, 95% CI 1.215-2.234, p = 0.006), and hyperuricemia was significantly associated with the incidence of AKI (HR 1.773, 95% CI 1.107-2.841, p = 0.017). The Kaplan-Meier survival curve showed that the 90-day survival rate was significantly lower in the hyperuricemia group. In patients with sepsis in the intensive care unit, hyperuricemia was significantly associated with increased risk 90-day all-cause mortality and the incidence of AKI.
Abstract Human mobility in an urban area is complicated; the origins, destinations, and transportation modes of each person differ. The quantitative description of urban human mobility has recently ...attracted the attention of researchers, and it highly related to urban science problems. Herein, combined with physics inspiration, we introduce a revised electric circuit model (RECM) in which moving people are regarded as charged particles and analogical concepts of electromagnetism such as human conductivity and human potential enable us to capture the characteristics of urban human mobility. We introduce the unit system, ensure the uniqueness of the calculation result, and reduce the computation cost of the algorithm to 1/10,000 compared with the original ECM, making the model more universal and easier to use. We compared features including human conductivity and potential between different major cities in Japan to show our improvement of the universality and the application range of the model. Furthermore, based on inspiration of physics, we propose a route generation model (RGM) to simulate a human flow pattern that automatically determines suitable routes between a given origin and destination as a source and sink, respectively. These discoveries are expected to lead to new approaches to the solution of urban science problems.
Energy conservation has become one of the priorities in manufacturing industries, while the energy efficiency at process level may provide deep understanding of the energy consumption during the ...manufacturing process. Hot-wire laser welding of double galvanized high-strength steel DP800 has a wide range of potential applications in the automobile manufacturing field. Based on the introduction of equivalent laser power, a mathematical model was developed to obtain the energy efficiency of hot-wire laser welding. The results of theoretical calculation and experimental verification indicate that the optimum pre-heating temperature range of the welding wire in hot-wire laser welding is from 600 to 800 °C. The preheating temperature of the welding wire increases almost parabolically with the heating current. Furthermore, the developed technique can be used to realize a maximum energy savings of 16% over cold-wire laser welding. The conclusions allowed to formulate the energy efficiency evaluation as green manufacturing of novel process is concerned.
•An energy efficiency model was developed for hot-wire laser welding.•An energy savings of 16% in the hot-wire laser welding process was realized over cold-wire laser welding.•A model was formulated to calculate the preheating temperature of the welding wire.
Modeling uncertainties are a major concern in vehicle path tracking control. As a practical engineering system, the uncertainties in vehicle lateral dynamics can be time-varying while bounded and ...have certain distributions wherein. The fuzzy set theory can effectively describe system uncertainties in terms of boundary and distribution. Contrary to fuzzy logic-based approaches, this article puts forward an explicit multiparameter optimal robust control law to ensure the uniform boundedness and ultimate uniform boundedness of the closed-loop path tracking dynamical system. Then, the tracking performance as well as the control cost is quantified as cost functions using fuzzy set theories. Finally, an optimization problem is established in the content of cooperative game to seek the optimal values for the tunable parameters. Simulations are conducted using CarSim and Simulink under double lane change and serpentine driving conditions. The results show that the proposed robust optimal control exhibits superior tracking performance.
A dual-functional lanthanide-MOF nanocomposite probe was designed and constructed for the detection of ascorbic acid (AA). The magnetically functionalized hydroxyapatite nanowires are selected as the ...carriers and simultaneously loaded with ciprofloxacin (CIP) and terbium metal organic framework to form the internal reference fluorescence probe nanocomposite (Fe
3
O
4
-HAPNWs-Tb/MOF-CIP). This dual-functional lanthanide-MOF probe not only combines the respectively unique fluorescence properties of lanthanide MOFs and CIP, but also takes full advantage of the rapid separation properties of the magnetic component. Structural and spectroscopic characterization results have demonstrated the successful synthesis of probe material and the fluorescence mechanism. At a suitable excitation wavelength (295 nm), the probe can simultaneously emit characteristic fluorescence of CIP (445 nm) and Tb
3+
(543 nm). In the presence of AA, the ratio of
I
543
/
I
445
decreases rapidly with increasing of AA concentration. The linear range of determination is 0.3–40 μM with a detection limit of 20.4 nM. The contents of AA in vitamin C tablets and four fruit juice samples were detected by the composite probe. The spiked recoveries ranged from 82.6 to 104.2% with relative standard deviations (RSD) less than 2.1%, revealing the practical application value of the developed sensor in healthcare and food fields.
Graphical Abstract
A novel internal reference fluorescence sensor (Fe O -HAPNWs-Tb/MOF-CIP) was constructed for detecting ascorbic acid by solvothermal and self-assembly techniques, showing excellent selectivity and sensitivity based on the different responses of Tb/MOF and CIP to the target
Photorealistic rendering of the virtual world is an important and classic problem in the field of computer graphics. With the development of GPU hardware and continuous research on computer graphics, ...representing and rendering virtual scenes has become easier and more efficient. However, there are still unresolved challenges in efficiently rendering global illumination effects. At the same time, machine learning and computer vision provide real-world image analysis and synthesis methods, which can be exploited by computer graphics rendering pipelines. Deep learning-enhanced rendering combines techniques from deep learning and computer vision into the traditional graphics rendering pipeline to enhance existing rasterization or Monte Carlo integration renderers. This state-of-the-art report summarizes recent studies of deep learning-enhanced rendering in the computer graphics community. Specifically, we focus on works of renderers represented using neural networks, whether the scene is represented by neural networks or traditional scene files. These works are either for general scenes or specific scenes, which are differentiated by the need to retrain the network for new scenes.
Molecular recognition is fundamental to the specific interactions between molecules, of which the best known examples are antibody-antigen binding and cDNA hybridization. Reversible manipulation of ...the molecular recognition events is still a very challenging topic, and such studies are often performed at the molecular level. An important consideration is the collection of changes at the molecular level to provide macroscopic observables. This research makes use of photoresponsive molecular recognition for the fabrication of novel photoregulated dynamic materials. Specifically, a dynamic hydrogel was prepared by grafting azobenzene-tethered ssDNA and its cDNA to the hydrogel network. The macroscopic volume of the hydrogel can be manipulated through the photoreversible DNA hybridization controlled by alternate irradiation of UV and visible light. The effects of synthetic parameters including the concentration of DNA, polymer monomer, and permanent cross-linker are also discussed.
The coupling, nonlinearity, and uncertainty characteristics of vehicle dynamics make the accurate longitudinal and lateral control of an automated and connected vehicle platoon a tough task. Little ...research has been conducted to fully address the characteristics. By using the ideology of constraint-following control this article proposes an integrated longitudinal and lateral adaptive robust control methodology for a vehicle platoon with a bidirectional communication topology. The platoon control objectives contain the path tracking stability, the platoon internal stability, and the string stability. First, we establish the nonlinear kinematics path tracking model and the coupled vehicle longitudinal and lateral dynamical model that contains time-varying uncertainties. Second, we design a series of nonlinear equality constraints that directly guarantee the control objectives based on the kinematic relations. On this basis, an adaptive robust constraint-following control is proposed. It is shown that the control guarantees the uniform boundedness and the uniform ultimate boundedness of the constraint-following error and the uncertainty estimation error. Finally, simulation results are provided to validate the effectiveness of the proposed methodology.
A novel chromatography stationary phase with a quasi-graphitized carbon modified shell has been developed. Coal pitch was directly carbonized on the surface of porous silica with in-situ ...carbonization. The carbonized coal pitch coating exhibits some degree of graphitization with a 78 nm-thick layer on the surface of silica and a 0.5 nm-thick layer on the inner surface of the mesopores. Based on the special structure of the graphitized carbon coating, the novel stationary phase can provide multiple interactions such as hydrophobic interaction, π-π interaction and dipole-dipole interaction. The novel composite material exhibited unique separation selectivity and excellent separation efficiency for polar compounds, including imidazoles, nucleosides and pesticides. Besides, the packed column also exhibited great repeatability with the RSDs of the retention time of nucleosides between 0.07%-0.50% (n = 5). Finally, satisfied result was achieved in the separation of fullerenes on the new column, suggesting the great potential in the industrial-scale purification of fullerenes.
A novel quasi-graphitized carbon/silica composite material was used as stationary phase for liquid chromatography. Display omitted
PDF
