New RNN Algorithms for Different Time-Variant Matrix Inequalities Solving Under Discrete-Time Framework.

A series of discrete time-variant matrix inequalities is generally regarded as one of the challenging problems in science and engineering fields. As a discrete time-variant problem, the existing solving schemes generally need the theoretical support under the continuous-time framework, and there is no independent solving scheme under the discrete-time framework. The theoretical deficiency of solving scheme greatly limits the theoretical research and practical application of discrete time-variant matrix inequalities. In this article, new discrete-time recurrent neural network (RNN) algorithms are proposed, analyzed, and investigated for solving different time-variant matrix inequalities under the discrete-time framework, including discrete time-variant matrix vector inequality (discrete time-variant MVI), discrete time-variant generalized matrix inequality (discrete time-variant GMI), discrete time-variant generalized-Sylvester matrix inequality (discrete time-variant GSMI), and discrete time-variant complicated-Sylvester matrix inequality (discrete time-variant CSMI), and all solving processes are based on the direct discretization thought. Specifically, first of all, four discrete time-variant matrix inequalities are presented as the target problems of these researches. Second, for solving such problems, we propose corresponding discrete-time recurrent neural network (RNN) (DT-RNN) algorithms (termed DT-RNN-MVI algorithm, DT-RNN-GMI algorithm, DT-RNN-GSMI algorithm, and DT-RNN-CSMI algorithm), which are different from the traditional DT-RNN design thought because second-order Taylor expansion is applied to derive the DT-RNN algorithms. This creative process avoids the intervention of continuous-time framework. Then, theoretical analyses are presented, which show the convergence and precision of the DT-RNN algorithms. Abundant numerical experiments are further carried out, which further confirm the excellent properties of the DT-RNN algorithms.

Bedside electrical impedance tomography to assist the management of pulmonary embolism: A case report.

Background: Pulmonary embolism (PE) is a common worldwide disease with high mortality. Timely diagnosis and management of PE could significantly improve clinical outcomes. Electrical impedance tomography (EIT) is a novel noninvasive technique to monitor lung perfusion and help detect PE at the bedside. Here we present a case of clinical management of subsegmental PE with the help of the bilateral ventilation and perfusion(V/Q) asymmetry EIT image. Case presentation: A 72-year-old cancer patient with respiratory failure and acute kidney injury in the intensive care unit was suspected of PE based on his clinical manifestation. The contraindication of computed tomography pulmonary angiography (CTPA) for PE diagnosis prevented escalating anticoagulation therapy. Besides EIT ventilation and perfusion monitoring showed an abnormal asymmetry V/Q match between the bilateral lungs which promoted our decision to start systemic continuous anticoagulation therapy and improved the patient clinically. The following CTPA which clarified the diagnosis of PE suggests that the patient has benefited from our decision. Conclusion: For critically ill patients with suspected PE, the asymmetry of the EIT V/Q image may provide crucial objective information for clinical management.

Artificial Intelligence in Intensive Care Medicine: Bibliometric Analysis.

BACKGROUND: Interest in critical care-related artificial intelligence (AI) research is growing rapidly. However, the literature is still lacking in comprehensive bibliometric studies that measure and analyze scientific publications globally. OBJECTIVE: The objective of this study was to assess the global research trends in AI in intensive care medicine based on publication outputs, citations, coauthorships between nations, and co-occurrences of author keywords. METHODS: A total of 3619 documents published until March 2022 were retrieved from the Scopus database. After selecting the document type as articles, the titles and abstracts were checked for eligibility. In the final bibliometric study using VOSviewer, 1198 papers were included. The growth rate of publications, preferred journals, leading research countries, international collaborations, and top institutions were computed. RESULTS: The number of publications increased steeply between 2018 and 2022, accounting for 72.53% (869/1198) of all the included papers. The United States and China contributed to approximately 55.17% (661/1198) of the total publications. Of the 15 most productive institutions, 9 were among the top 100 universities worldwide. Detecting clinical deterioration, monitoring, predicting disease progression, mortality, prognosis, and classifying disease phenotypes or subtypes were some of the research hot spots for AI in patients who are critically ill. Neural networks, decision support systems, machine learning, and deep learning were all commonly used AI technologies. CONCLUSIONS: This study highlights popular areas in AI research aimed at improving health care in intensive care units, offers a comprehensive look at the research trend in AI application in the intensive care unit, and provides an insight into potential collaboration and prospects for future research. The 30 articles that received the most citations were listed in detail. For AI-based clinical research to be sufficiently convincing for routine critical care practice, collaborative research efforts are needed to increase the maturity and robustness of AI-driven models.

Fluorescent metabolic labeling-based quick antibiotic susceptibility test for anaerobic bacteria.

Because of the advancements in medicine and science, the numbers of patients surviving complicated diseases are continuously increasing, which in turn leads to elevated chances of anaerobic infections by endogenous bacteria. Traditional growth yield-based antibiotic susceptibility tests (ASTs) against anaerobic bacteria are very time-consuming (≥48 h) and labor intensive, which delays the timely guidance of antibiotic prescription and increases the mortality of patients. Inspired by a fluorescent d-amino acid (FDAA) labeling-based AST (FaAST) that we recently developed for quick determination of aerobic bacteria's susceptibilities, here we report an accurate and fast AST method for anaerobic pathogens. Based on flow cytometry analysis of anaerobes that have been treated with various doses of antibiotics and metabolically labeled with FDAA, the intensities of which can reflect their affected metabolic status by the drugs, the MICs of each drug can then be determined. The whole process can be completed in 5 h. After testing 40 combinations of the representative anaerobic bacteria and antibiotics, our method demonstrates a high susceptibility category accuracy of 95.0%. This FaAST-based protocol is helpful in accurately and quickly guiding antibiotic decisions when treating critical infections caused by anaerobic bacteria.

Correction: Fluorescent metabolic labeling-based quick antibiotic susceptibility test for anaerobic bacteria.

[This corrects the article DOI: 10.1039/D2CB00163B.].

d-Amino Acid-Based Metabolic Labeling Enables a Fast Antibiotic Susceptibility Test of Both Isolated Bacteria and Bronchoalveolar Lavage Fluid.

The threat of multidrug-resistant bacteria has escalated rapidly, increasing the demand for accurate antibiotic susceptibility tests (ASTs). Traditional bacterial growth yield-based ASTs often take overnight to report, delaying the timely guidance of antibiotic use. Here, a fluorescent d-amino acid (FDAA) labeling-based AST (FaAST) is reported, which can quickly provide accurate minimum inhibitory concentrations (MICs). The FDAA-labeling signals that reflect the bacterial metabolic status underlie the flow cytometry-based strategy for MIC determination. Resistant bacteria show a reluctant decline in FDAA-labeling (inhibited metabolism) after treatment with the corresponding antibiotics, whereas susceptible bacteria demonstrate quick responses to low doses of drugs. The MICs are determined based on the changing trends in labeling. After testing 23 clinical isolates and laboratory strains of the most critical drug-resistant bacteria against a panel of representative antibiotics, FaAST shows a high susceptibility category with an accuracy of 98.13%. Moreover, FaAST can also make quick and accurate diagnosis against bronchoalveolar lavage fluids collected from hospital-acquired pneumonia patients, saving 2-4 days in guiding antibiotic use for this life-threatening infection. Thus, the speed, accuracy, and broad applicability of FaAST will be valuable in informing antibiotic decisions when treating critical infections caused by drug-resistant bacteria.