Primary liver cancer is a malignant tumor with high morbidity and mortality in the world, and it is also a common malignant tumor of digestive tract in China. With the development of medical technology and the deepening of minimally invasive concept, minimally invasive therapy has gradually become the main treatment of liver cancer. Through the visual analysis of Cite Space bibliometrics study, the authors visually show the basic knowledge structure and evolution in the field of minimally invasive treatment of liver cancer, and explore the frontier hotspots and future development trends, so as to provide reference for scientific research and application in this field.

Primary liver cancer (hereinafter referred to as liver cancer) is one of the most common and deadly malignancies, posing a serious threat to human health. In recent years, advance-ments in artificial intelligence (AI) have opened up possibilities for the comprehensive enhancement of liver cancer diagnosis and treatment. AI technologies in liver cancer mainly include the machine learning (ML) and the deep learning (DL) models, with DL being a subtype of ML based on neural network structures. The application of ML and DL models in liver cancer has demonstrated tremen-dous potential, but there are still many issues that need to be addressed, including enhancing the generalizability and interpretability of results. The authors elaborate on the application progress of AI in the field of liver cancer in recent years, and explore the current challenges and future explora-tion directions.

Objective: To establish and evaluate a multiplex PCR method for rapid identification of Mycobacterium species in order to provide an approach for rapid diagnosis of pathogens causing tuberculosis. Methods: Four genes including 16S rRNA, Rv0577, RD9 and mtbk_20680 were selected to establish the multiplex PCR method. Specific primers were designed and the reaction system and conditions were optimized. The sensitivity and specificity of the multiplex PCR method were evaluated through identifying Mycobacterium africanum (M.africanum), Mycobacterium bovis (M.bovis), M. bovis BCG, seven common non-tuberculosis Mycobacterium (NTM), seven reference species of common respiratory bacteria and 93 clinical strains of Mycobacterium tuberculosis (MTB) isolated from patients with tuberculosis in Gansu Province of China. Results: The fragments of 16S rRNA, Rv0577, RD9 and mtbk_20680 genes were 543 bp, 786 bp, 369 bp and 231 bp in length, respectively. MTB strains of the Beijing genotype were positive for all of the four genes, while the non-Beijing genotype strains were negative for mtbk_20680. M. africanum, M. bovis and M. bovis BCG strains were negative for 16S rRNA and Rv0577. NTM strains only carried 16S rRNA and none of four genes were detected in the seven species of respiratory bacteria. Among the 93 clinical MTB strains, 80 (86.02%) belonged to the Beijing genotype and the other 13 (13.98%) were non-Beijing genotype strains. The specificity of the multiplex PCR method was 100%. Conclusions The established multiplex PCR method could accurately distinguish Mycobacterium, Mycobacterium tuberculosis complex (MTBC), NTM, MTB, and Beijing and non-Beijing genotype MTB with high sensitivity and specificity.

Objective: Autoregressive integrated moving average (ARIMA) model was used to predict the incidence of tuberculosis in China from 2018 to 2019, providing references for the prevention and control of pulmonary tuberculosis. Methods: The monthly incidence data of tuberculosis in China were collected from January 2005 to December 2017. R 3.4.4 software was used to establish the ARIMA model, based on the monthly incidence data of tuberculosis from January 2005 to June 2017. Both predicted and actual data from July to December 2017 were compared to verify the effectiveness of this model, and the number of tuberculosis cases in 2018-2019 also predicted. Results: From 2005 to 2017, a total of 13 022 675 cases of tuberculosis were reported, the number of pulmonary tuberculosis patients in 2017 was 33.68% lower than that in 2005, and the seasonal character was obvious, with the incidence in winter and spring was higher than that in other seasons. According to the incidence data from 2005 to 2017, we established the model of ARIMA (0,1,2)(0,1,0)₁₂. The relative error between the predicted and actual values of July to December 2017 fitted by the model ranged from 1.67% to 6.80%, and the predicted number of patients in 2018 and 2019 were 789 509 and 760 165 respectively. Conclusion The ARIMA (0, 1, 2)(0, 1, 0)₁₂ model well predicted the incidence of tuberculosis, thus can be used for short-term prediction and dynamic analysis of tuberculosis in China, with good application value.