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.

One-dimensional nanomaterials with controlled morphology have received considerable attention as chemical sensors.

The efficient and reliable monitoring of acetic acid is significant to environmental protection and human healthcare. LaFeO3 is a potential sensing material for acetic acid with its good sensitivity and high plasticity. To further improve the sensing properties of LaFeO ₃ to meet the requirements of applications, we successfully utilized the facile electrospinning technique to fabricate a series of acetic acid-sensitive Ag-doped (0-5 mol%) LaFeO ₃ nanotubes. The systematic characterization shows that the appropriate content (4 mol%) of Ag doping can effectively ameliorate the material morphology to realize loose porous structures. Meanwhile, the sensitization effect of Ag and ameliorated morphology significantly enhance the gas sensing properties of LaFeO ₃ to acetic acid vapor. The optimal Ag-doped LaFeO ₃ (4 mol%) loose nanotubes-based gas sensor results in a detection limit of 0.5 ppm and 3.6-fold enhancement of the response to 100 ppm acetic acid compared with the pure LaFeO ₃ compact nanotubes at a low operating temperature (150°C). It also exhibits excellent selectivity to acetic acid and good long-term stability. Therefore, Ag-doped LaFeO ₃ can be regarded as a promising material for sensing acetic acid in practical applications. Finally, the mechanism of enhanced gas-sensing properties is discussed.

A highly sensitive xylene sensor based on Cr-doped NiO nanotubes was presented, which was prepared using an electrospinning process.