No abstract

Flexible pressure sensors have attracted intense attention because of their widespread applications in electronic skin, human−machine interfaces, and healthcare monitoring. Conductive porous structures are always utilized as active layers to improve the sensor sensitivities. However, flexible pressure sensors derived from traditional foaming techniques have limited structure designability. Besides, random pore distribution causes difference in structure and signal repeatability between different samples even in one batch, therefore limiting the batch production capabilities. Herein, we introduce a structure designable lattice structure pressure sensor (LPS) produced by bottom-up digital light processing (DLP) 3D printing technique, which is capable of efficiently producing 55 high fidelity lattice structure models in 30 min. The LPS shows high sensitivity (1.02 kPa −1 ) with superior linearity over a wide pressure range (0.7 Pa to 160 kPa). By adjusting the design parameters such as lattice type and layer thickness, the electrical sensitivities and mechanical properties of LPS can be accurately controlled. In addition, the LPS endures up to 60000 compression cycles (at 10 kPa) without any obvious electrical signal degradation. This benefits from the firm carbon nanotubes (CNTs) coating derived from high-energy ultrasonic probe and the subsequent thermal curing process of UV-heat dual-curing photocurable resin. For practical applications, the LPS is used for real time pulse monitoring, voice recognition and Morse code communication. Furthermore, the LPS is also integrated to make a flexible 4 × 4 sensor arrays for detecting spatial pressure distribution and a flexible insole for foot pressure monitoring.

No abstract

No abstract

BackgroundSepsis-associated acute kidney injury (SA-AKI) is common in critically ill patients, which is associated with significantly increased mortality. Existing mortality prediction tools showed insufficient predictive power or failed to reflect patients' dynamic clinical evolution. Therefore, the study aimed to develop and validate machine learning-based models for real-time mortality prediction in critically ill patients with SA-AKI.MethodsThe multi-center retrospective study included patients from two distinct databases. A total of 12,132 SA-AKI patients from the Medical Information Mart for Intensive Care IV (MIMIC-IV) were randomly allocated to the training, validation, and internal test sets. An additional 3,741 patients from the eICU Collaborative Research Database (eICU-CRD) served as an external test set. For every 12 h during the ICU stays, the state-of-the-art eXtreme Gradient Boosting (XGBoost) algorithm was used to predict the risk of in-hospital death in the following 48, 72, and 120 h and in the first 28 days after ICU admission. Area under the receiver operating characteristic curves (AUCs) were calculated to evaluate the models' performance.ResultsThe XGBoost models, based on routine clinical variables updated every 12 h, showed better performance in mortality prediction than the SOFA score and SAPS-II. The AUCs of the XGBoost models for mortality over different time periods ranged from 0.848 to 0.804 in the internal test set and from 0.818 to 0.748 in the external test set. The shapley additive explanation method provided interpretability for the XGBoost models, which improved the understanding of the association between the predictor variables and future mortality.ConclusionsThe interpretable machine learning XGBoost models showed promising performance in real-time mortality prediction in critically ill patients with SA-AKI, which are useful tools for early identification of high-risk patients and timely clinical interventions.

Acute kidney injury (AKI) is commonly present in critically ill patients with sepsis. Early prediction of short-term reversibility of AKI is beneficial to risk stratification and clinical treatment decision. The study sought to use machine learning methods to discriminate between transient and persistent sepsis-associated AKI. Septic patients who developed AKI within the first 48 h after ICU admission were identified from the Medical Information Mart for Intensive Care III database. AKI was classified as transient or persistent according to the Acute Disease Quality Initiative workgroup consensus. Five prediction models using logistic regression, random forest, support vector machine, artificial neural network and extreme gradient boosting were constructed, and their performance was evaluated by out-of-sample testing. A simplified risk prediction model was also derived based on logistic regression and features selected by machine learning algorithms. A total of 5984 septic patients with AKI were included, 3805 (63.6%) of whom developed persistent AKI. The artificial neural network and logistic regression models achieved the highest area under the receiver operating characteristic curve (AUC) among the five machine learning models (0.76, 95% confidence interval [CI] 0.74–0.78). The simplified 14-variable model showed adequate discrimination, with the AUC being 0.76 (95% CI 0.73–0.78). At the optimal cutoff of 0.63, the sensitivity and specificity of the simplified model were 63% and 76% respectively. In conclusion, a machine learning-based simplified prediction model including routine clinical variables could be used to differentiate between transient and persistent AKI in critically ill septic patients. An easy-to-use risk calculator can promote its widespread application in daily clinical practice.

No abstract

The dissemination of Klebsiella pneumoniae carbapenemases (KPCs) among Gram-negative bacteria is an important threat to global health. However, KPC-producing bacteria from environmental samples are rarely reported. This study aimed to elucidate the underlying resistance mechanisms of three carbapenem-resistant Aeromonas taiwanensis isolates recovered from river sediment samples. Pulsed-field gel electrophoresis (PFGE) and whole genome sequencing (WGS) analysis indicated a close evolutionary relationship among A. taiwanensis isolates. S1-PFGE, Southern blot and conjugation assays confirmed the presence of blaKPC–2 and qnrS2 genes on a non-conjugative plasmid in these isolates. Plasmid analysis further showed that pKPC-1713 is an IncP-6 plasmid with a length of 53,205 bp, which can be transformed into DH5α strain and mediated carbapenems and quinolones resistance. The plasmid backbone of p1713-KPC demonstrated 99% sequence identity to that of IncP-6-type plasmid pKPC-cd17 from Aeromonas spp. and IncP-6-type plasmid: 1 from Citrobacter freundii at 74% coverage. A 14,808 bp insertion sequence was observed between merT gene and hypothetical protein in p1713-KPC, which include the quinolone resistance qnrS2 gene. Emergence of plasmid-borned blaKPC and qnrS2 genes from A. taiwanensis isolates highlights their possible dissemination into the environment. Therefore, potential detection of such plasmids from clinical isolates should be closely monitored.