A generalized toxicity classification model for 7 different oxide nanomaterials is presented in this study. A data set extracted from multiple literature sources and screened by physicochemical property based quality scores were used for model development. Moreover, a few more preprocessing techniques, such as synthetic minority over-sampling technique, were applied to address the imbalanced class problem in the data set. Then, classification models using four different algorithms, such as generalized linear model, support vector machine, random forest, and neural network, were developed and their performances were compared to find the best performing preprocessing methods as well as algorithms. The neural network model built using the balanced data set was identified as the model with best predictive performance, while applicability domain was defined using k-nearest neighbours algorithm. The analysis of relative attribute importance for the built neural network model identified dose, formation enthalpy, exposure time, and hydrodynamic size as the four most important attributes. As the presented model can predict the toxicity of the nanomaterials in consideration of various experimental conditions, it has the advantage of having a broader and more general applicability domain than the existing quantitative structure-activity relationship model.

Array-based gas sensors now offer the potential of a robust analytical approach to odor measurement for medical use. We are developing a fast reliable method for detection of microbial infection by monitoring the headspace from the infected wound. In this paper, we present initial results obtained from wound-state monitoring for burn patients using an electronic nose incorporating an automated solid-phase microextraction (SPME) desorption system to enable the system to be used for clinical validation. SPME preconcentration is used for sampling of the headspace air and the response of the sensor module to variable concentrations of volatiles emitted from SPME fiber is evaluated. Gas chromatography-mass spectrometry studies prove that living bacteria, the typical infectious agents in clinical practice, can be distinguished from each other by means of a limited set of key volatile products. Principal component analysis results give the first indication that infected patients may be distinguished from uninfected patients. Microbial laboratory analysis using clinical samples verifies the performance of the system.

Applications of machine learning techniques for the prediction of nanotoxicity are expected to reduce time and cost of nanosafety assessments. However, due to the rapid increases in literature data quantity and heterogeneity on nanomaterials, efficient screening of data based on their quality and completeness are becoming more important for the development of reliable nanostructure–activity relationship (nanoSAR) models. Herein, we have curated a nanosafety dataset of metallic NPs, with 2005 rows and 31 columns extracted from literature data mining of 63 published articles and gap filling by adapting data from manufacturer specification or references on the same nanomaterials. By using PChem scores based on physicochemical data quality and completeness, five datasets with different qualities and degrees of completeness were generated and used for the development of toxicity classification models of metallic NPs. Comparisons of these models, built with support vector machine and random forest algorithms, confirmed us that the datasets with higher quality and completeness (i.e., higher PChem score) produced better performing nanoSAR models than those with lower PChem scores. Further analysis of relative attribute importance showed that the physicochemical properties, core size and surface charge, and the experimental conditions of toxicity assays, dose and cell lines, are the four most important attributes to the toxicity of metallic NPs.

This study presents a safety management model for hydrogen refueling stations, integrating digital twin technology and artificial intelligence (AI) to enhance operational safety. Given the risks associated with high-pressure gas handling and potential fires from hydrogen leaks, real-time safety monitoring is crucial. The proposed model is based on a digital twin, a virtual replica of the physical system using real-time data, including temperature, pressure, and state of charge, collected from an actual hydrogen refueling station in Samcheok, Gangwon Province. Out of nine tested machine learning and deep learning algorithms, the convolutional neural network (CNN) demonstrated the highest performance (accuracy: 1, F1 score: 0.993) for risk prediction. Using AI libraries like Scikit-Learn and TensorFlow, the model achieved prediction times of 68 milliseconds, enabling decision-making at intervals of 1 s. Developed with the Unity 3D modeling tool, the digital twin visualizes predicted risk situations, allowing users to quickly identify and respond to potential hazards. This approach offers a robust solution for improving the safety of hydrogen refueling stations.

The early detection and timely treatment are the most important factors for improving the outcome of patients with sepsis. Sepsis-related clinical score, such as SIRS, SOFA and LODS, were defined to identify patients with suspected infection and to predict severity and mortality. A few hematological parameters associated with organ dysfunction and infection were included in the score although various clinical pathology parameters (hematology, serum chemistry and plasma coagulation) in blood sample have been found to be associated with outcome in patients with sepsis. The investigation of the parameters facilitates the implementation of a complementary model for screening sepsis to existing sepsis clinical criteria and other laboratory signs. In this study, statistical analysis on the multiple clinical pathology parameters obtained from two groups, patients with sepsis and patients with fever, was performed and the complementary model was elaborated by stepwise parameter selection and machine learning. The complementary model showed statistically better performance (AUC 0.86 vs. 0.74–0.51) than models built up with specific hematology parameters involved in each existing sepsis-related clinical score. Our study presents the complementary model based on the optimal combination of hematological parameters for sepsis screening in patients with fever.