Chronic kidney disease (CKD) is a global health problem with high morbidity and mortality rate, and it induces other diseases. Since there are no obvious symptoms during the early stages of CKD, patients often fail to notice the disease. Early detection of CKD enables patients to receive timely treatment to ameliorate the progression of this disease. Machine learning models can effectively aid clinicians achieve this goal due to their fast and accurate recognition performance. In this study, we propose a machine learning methodology for diagnosing CKD. The CKD data set was obtained from the University of California Irvine (UCI) machine learning repository, which has a large number of missing values. KNN imputation was used to fill in the missing values, which selects several complete samples with the most similar measurements to process the missing data for each incomplete sample. Missing values are usually seen in real-life medical situations because patients may miss some measurements for various reasons. After effectively filling out the incomplete data set, six machine learning algorithms (logistic regression, random forest, support vector machine, k-nearest neighbor, naive Bayes classifier and feed forward neural network) were used to establish models. Among these machine learning models, random forest achieved the best performance with 99.75% diagnosis accuracy. By analyzing the misjudgments generated by the established models, we proposed an integrated model that combines logistic regression and random forest by using perceptron, which could achieve an average accuracy of 99.83% after ten times of simulation. Hence, we speculated that this methodology could be applicable to more complicated clinical data for disease diagnosis.

Rapid diagnosis of diseases at their initial stage is critical for effective clinical outcomes and promotes general public health. Classical in vitro diagnostics require centralized laboratories, tedious work and large, expensive devices. In recent years, numerous electrochemical biosensors have been developed and proposed for detection of various diseases based on specific biomarkers taking advantage of their features, including sensitivity, selectivity, low cost and rapid response. This article reviews research trends in disease-related detection with electrochemical biosensors. Focus has been placed on the immobilization mechanism of electrochemical biosensors, and the techniques and materials used for the fabrication of biosensors are introduced in details. Various biomolecules used for different diseases have been listed. Besides, the advances and challenges of using electrochemical biosensors for disease-related applications are discussed.

It is a major challenge to effectively inhibit microbial pathogens in the treatment of infectious diseases. Research on the application of nanomaterials as antibacterial agents has evidenced their great potential for the remedy of infectious disease. Among these nanomaterials, carbon quantum dots (CQDs) have attracted much attention owing to their unique optical properties and high biosafety. In this work, P-doped CQDs were prepared by simple hydrothermal treatment of m-aminophenol and phosphoric acid with fluorescence emission at 501 nm when excited at 429 nm. The P-doped CQDs showed effective antibacterial activity against Escherichia coli (E. coli) and Staphylococcus aureus (S. aureus). The minimal inhibitory concentrations (MICs) of P-doped CQD were 1.23 mg/mL for E. coli and 1.44 mg/mL for S. aureus. Furthermore, the morphologies of E. coli cells were damaged and S. aureus became irregular when treated with the P-doped CQDs. The results of zeta potential analysis demonstrated that the P-doped CQDs inhibit antibacterial activity and destroy the structure of bacteria by electronic interaction. In combination, the results of this study indicate that the as-prepared P-doped CQDs can be a promising candidate for the treatment of bacterial infections.

Emotion is a human attitude experience and corresponding behavioral response to objective things. Effective emotion recognition is important for the intelligence and humanization of brain-computer interface (BCI). Although deep learning has been widely used in emotion recognition in recent years, emotion recognition based on electroencephalography (EEG) is still a challenging task in practical applications. Herein, we proposed a novel hybrid model that employs generative adversarial networks to generate potential representations of EEG signals while combining graph convolutional neural networks and long short-term memory networks to recognize emotions from EEG signals. Experimental results on DEAP and SEED datasets show that the proposed model achieved the promising emotion classification performance compared with the state-of-the-art methods.