The current standard treatment regimen for patients with cervical cancer consists of a combination of radiotherapy and chemotherapy. However, the serious side effects often encountered with chemotherapy drugs greatly limits the effective doses that can be delivered, and hence the treatment of cervical cancer still faces strong challenges. In this study, carbon nanodots, nanodrugs with anti-cervical cancer activity and with negligible toxicity, were prepared from the precursor herbal extract ginsenoside Rg1. The surface of the Rg1 carbon nanodots is rich in hydrophilic functional groups, resulting in good dispersion in aqueous media and high biocompatibility. In Vitro experiments show that the Rg1 carbon nanodots have significant cytostatic and pro-apoptotic effects on HeLa cells, and could inhibit their migration and invasion. Experiments in tumor-bearing nude mice show that the Rg1 carbon nanodots could significantly inhibit tumor growth. Through qPCR validation, the Rg1 carbon nanodots were shown to enhance HeLa cell apoptosis, by regulating the expression levels of Cyto c, Caspase-9, Caspase-3, Bax, and Bcl-2, induce G2/M phase arrest by regulating CDK 1 and Cyclin B1 expression, and inhibit tumor cell migration by modulating CDH1 and β-catenin. Since the precursor Rg1 is a natural herbal extract, negligible toxic side effects were observed in nude mice. The work demonstrates that Rg1 carbon nanodots can be expected to become a potential nanomedicine against human cervical cancer with negligible toxic side effects and excellent therapeutic effects.

This study applies optimization-based algorithm to develop combination classification methods. We propose a genetic algorithm-based combination classification method of multiple decision trees to improve predictive accuracy, optimize classification rules, and interpret classification results. The basic algorithm for decision tree has been constructed in a top-down recursive divide-and-conquer manner. Based on different split measures (attribute selection measures), different decision tree algorithms can be produced, and then multiple decision trees can be formed. We proposed the parallel combination model of multiple decision trees. On top of the combination model, multiple decision trees are parallel combined. Each decision tree produces its own classification rules according to training samples from which one can present the classification result using probability distribution of target class label. At the bottom, the classification result of each decision tree serves as the input for combination algorithm in producing classification result and rules for the combination model. Combination algorithm adopts weighted summation of the outputs of probability measurement levels from individual decision trees, while genetic algorithm optimizes connection weight matrix. Finally the target class label with the largest probability output value is selected as the decision result for combination classification methods. The proposed method is applied to the issues of customer credit rating assessment and customer response behaviour pattern recognition in CRM. From the simulation results it is concluded that the proposed method has higher predictive accuracy than single decision tree. Moreover, it retains good interpretability and optimizes classification rules.