With the continuous deepening of the concept of precision diagnosis and treatment for lung cancer, how to achieve higher efficiency and accuracy in the screening, diagnosis, and treatment pathways in clinical practice has become an important issue that urgently needs to be overcome. The current clinical difficulty lies in the fact that despite continuous advancements in imaging and molecular diagnostic technologies, there are still limitations in manual efficiency and subjective experience when it comes to massive data analysis and multi-scale feature extraction. Artificial intelligence (AI), especially algorithm systems based on deep learning, is an innovative technology capable of deeply empowering medical big data. This method utilizes algorithms such as convolutional neural networks, combined with radiomics, pathomics, and multi-modal data fusion analysis, demonstrating immense potential in early precise detection and benign-malignant differentiation of pulmonary nodules, digital pathological subtype recognition and non-invasive prediction of driver genes, precise 3D surgical planning and automatic delineation of radiotherapy target volumes, as well as dynamic risk warning during follow-up. This innovative technology provides a brand-new solution for realizing intelligent and individualized lung cancer diagnosis and treatment models. This consensus, based on the latest evidence from evidence-based medicine and combined with the development trends in the AI field and real-world clinical needs, was ultimately formed by gathering the consensus opinions of multidisciplinary experts in radiology, pathology, thoracic surgery, and other fields. The main content covers the application specifications of AI in the three core scenarios of lung cancer screening, diagnosis, and treatment, the technical standards for data collection and algorithm validation, as well as the ethical and regulatory challenges faced at the current stage. It aims to clarify the applicable boundaries of AI as a clinical auxiliary decision support tool, providing scientific guidance and standardized exploration directions for peers currently engaged in or planning to carry out AI-assisted clinical diagnosis, treatment, and translation of lung cancer.

Aim To explore the feasibility of the micro- dynamic chromogenic method for quantitative detection of bacterial endotoxin in recombinant novel coronavirus vaccine ( CHO cell).Methods The micro-dynamic color method of Limulus reagent was used to establish a bacterial endotoxin standard curve.The dilution factor was determined through interference pre -experiment, the recoverv rate of the endotoxin added to the test so- J lution was determined, and the interference test to complete the quantitative detection test of the bacterial endotoxin content in the test product was performed, and the results were compared with those of the gel-clot method.Results Hie linear range of the concentration of the standard curve was 0.02 to 2.0 EU • mL 1 , and the regression equation of the standard curve was lgT =-0.302 7 lgC +2.858 7( r = 0.998 9).When recombinant novel coronavirus vaccine ( CHO cell) was cliluted 40 times or below, the micro -dynamic chromogenic reagent did not interfere with the bacterial endotoxin agglutination reaction, and the recovery rate was 50% to 200%.The test results were consistent with the gel- clot method.Conclusions The micro-dynamic chromogenic method can be used for the quantitative detection of bacterial endotoxins in recombinant novel coronavirus vaccine ( CHO cell) with accurate results, high sensitivity, and process monitoring.

Objective: To develop autoverification rules to assistant the verification of biochemical results, based on laboratory information management system. Methods: Designed six kinds of autoverification logic rules according to the guidelines of Clinical and Laboratory Standards Institute (CLSI) AUTO-10A and Accreditation Criteria for the Quality and Competence of Medical Laboratories(ISO15189: 2012), based on in-control of the Internal Quality Control. Those rules inculds: logic disorder rules, critical value rules, warning value rules, delta check rules, relevant contradictions rules, abnormal mode rules, etc. Those rules was setted up in laboratory information management system of Dian Diagnostics. From October 2016 to April 2017, The status of autoverification was checked according to the items and bar code, and compared with clinical diagnostic and manual review. Results: The passing rate of autoverification is over 65% when counted according to tests and is 45% when counted according to sample code, the coincidence rate is 92% with clinical diagnosis.In passing results of autoverification, the coincidence rate is 97.48% to 100% when campared with manual verification, and in not-passing results, the coincidence rate is 82.98% to 85.21%. Conclusion (1)Autoverification can verify half of routine biochemical test results by setting intelligent logics and rules. (2)Autoverification rules must be verified by a certain amount of test results before they can be formally applied. (3)Autoverification could improve the speed and efficiency of post-test steps.(Chin J Lab Med, 2018, 41: 547-553)