It is a significant challenge to improve the blood-brain barrier (BBB) permeability of central nervous system (CNS) drugs in their development. Compared with traditional pharmacokinetic property tests, machine learning techniques have been proven to effectively and cost-effectively predict the BBB permeability of CNS drugs. In this study, we introduce a high-performance BBB permeability prediction model named balanced-stacking-learning based BBB permeability predictor(BSL-B3PP). Firstly, we screen out the feature set that has a strong influence on BBB permeability from the perspective of medicinal chemistry background and machine learning respectively, and summarize the BBB positive(BBB+) quantification intervals. Then, a combination of resampling algorithms and stacking learning(SL) algorithm is used for predicting the BBB permeability of CNS drugs. The BSL-B3PP model is constructed based on a large-scale BBB database (B3DB). Experimental validation shows an area under curve (AUC) of 97.8% and a Matthews correlation coefficient (MCC) of 85.5%. This model demonstrates promising BBB permeability prediction capability, particularly for drugs that cannot penetrate the BBB, which helps reduce CNS drug development costs and accelerate the CNS drug development process.
ObjectiveTo evaluate the methodological quality of cross-sectional surveys about Chinese medicine syndrome in a population at potential risk of cerebrovascular diseases. Methods The CNKI, WanFang Data, CBM and PubMed databases were electronically searched to collect cross-sectional surveys about Chinese medicine syndromes in a population at potential risk of cerebrovascular diseases from inception to December, 2022. The methodological quality was assessed using the JBI scale. Results A total of 105 studies were included. The average reporting rate of JBI was 52.06%, and the items with the highest scores included "sufficient coverage of the identified sample in data analysis" (100%), "description of study subjects and setting" (92.38%), and "using valid methods for the identification of the condition" (86.67%). Items with the lowest scores included "adequate sample size" (13.33%), "adequate response rate or low response rate managed appropriately" (14.29%), and "study participants recruited in an appropriate way" (20.95%). Subgroup analysis suggested that type of publication and number of implementation centers were potential factors influencing methodology quality (P<0.05). Conclusion The methods essential to a cross-sectional survey such as sampling, sample size calculation and handling with the response rate, and the syndrome diagnosis scales specific to Chinese medicine require further improvement.
Objective To evaluate the reporting quality of rapid guidelines on Chinese medicine responding to public health emergencies. Methods The databases of PubMed, Embase, CNKI, CBM, WanFang Data, and preprint platforms were electronically searched. A supplementary search was performed by navigating the websites and Wechat public platforms specific to guideline development and dissemination, health and medical governing bodies, and academic organizations of Chinese medicine. Only guidelines published within three months after the onset of acute respiratory infectious diseases were eligible. The database search settings were as follows: SARS guidelines up to May 2003, H1N1 guidelines up to August 2009, and COVID-19 guidelines up to April 2020. The report quality was assessed using the Reporting Items for practice Guidelines in HealThcare (RIGHT) and its extension for traditional Chinese medicine (TCM). Results A total of 50 rapid guidelines on Chinese medicine responding to public health emergencies were included, indicating a growing trend in the number of guidelines. The RIGHT items most frequently reported were item 1c (n=46, 92.00%), item 7a (n=47, 94.00%), item 13a (n=49, 98.00%). The items extended to TCM was generally frequently reported (≥50%). However, the ten key items related to evidence, recommendations, funding, and the declaration and management of interest were rarely reported. Conclusion Enhancing the reporting quality of rapid guidelines on Chinese medicine in response to public health emergencies requires methodological solutions. The development of such guideline reporting standards should consider the unique characteristics of public health emergencies and the special nature of Chinese medicine evidence.