Artificial intelligence has been extensively applied in healthcare services recently, and clinical decision support systems driven by artificial intelligence are one of the applications. Early-stage clinical evaluation of artificial intelligence (AI)-based clinical decision support systems lies between preclinical development (in silico), offline validation, and large-scale trials, but few AI-related clinical studies have addressed human factors evaluations and reported the implementation environment, user characteristics, selection process and algorithm identification of AI systems. In order to bridge the development-to-implementation gap in clinical artificial intelligence and to promote the transparent and standardized reporting of early-stage clinical studies of AI-based decision support systems. A reporting guideline for the developmental and exploratory clinical investigations of decision support systems driven by artificial intelligence (DECIDE-AI) was published in 2022. This paper aimed to interpret the background, development process and key items of the DECIDE-AI guideline and promote its understanding as well as dissemination in China.
Dose-response meta-analysis serves an important role in investigating the dose-response relationship between independent variables (e.g. dosage) and disease outcomes. Traditional dose-response meta-analysis model is based on one independent variable to consider its own dose-specific effect on the outcome. However, for drug clinical trials, it generally involves two-dimensions of the treatment, such as dosage and course of treatment. These two-dimensions tend to be associated with each other. When neglecting their correlations, the results may be at risk of bias. Moreover, taking account of the "combined effect” of dosage and time on outcome has more clinical value. Therefore, in this article, based on traditional dose-response meta-analysis model, we propose a three-dimension model for dose-response meta-analysis which considers both the effect of dosage and time, to provide a solution for the above-mentioned problems in a traditional model.
Objective To investigate the methodological characteristics of observational studies on the correlation between drug exposure during pregnancy and birth defects. Methods The PubMed database was searched from January 1, 2020 to December 31, 2020 to identify observational studies investigating the correlation between drug use during pregnancy and birth defects. Literature screening and data extraction were conducted by two researchers and statistical analysis was performed using R 3.6.1 software. Results A total of 40 relevant articles were identified, of which 8 (20.0%) were published in the four major medical journals and their sub-journals, 21 (42.5%) were conducted in Europe and the United States, and 4 were conducted (10.0%) in China. Cohort studies (30, 75.0%) and case-control studies (10, 25%) were the most commonly used study designs. Sixteen studies (40.0%) did not specify how the databases were linked. Sixteen studies (40.0%) did not report a clear definition of exposure, while 17 studies (42.5%) defined exposure as prescribing a drug that could not be guaranteed to have been taken by the pregnant women, possibly resulting in misclassification bias. Six studies (15.0%) did not report the diagnostic criteria for birth defects and 18 studies (45.0%) did not report the types of birth defects. In addition, 33 studies (82.5%) did not control for confounding factors in the study design, while only 19 studies (47.5%) considered live birth bias. Conclusion Improvements are imperative in reporting and conducting observational studies on the correlation between drug use during pregnancy and birth defects. This includes the methods for linking data sources, definition of exposure and outcomes, and control of confounding factors. Methodological criteria are needed to improve the quality of these studies to provide higher quality evidence for policymakers and researchers.
Traditional Chinese medicine (TCM) has a long history. In the process of fighting against diseases, TCM has formed a unique theoretical system and the way to think and diagnose. The holistic thinking, and the treatment according to syndrome differentiation are the most prominent characteristics of TCM, which matches with advanced medical concept and direction. The clinical efficacy has always been the basis for the advancement of TCM. However, issues such as the lagging behind of modern research on the evaluation of TCM curative effect, as well as lacking high-quality scientific research evidence, impede the development and promotion of the TCM toward the world. To address the above problems, recent progress in real-word study (RWS) has provided the opportunity for TCM researches, especially for the post-marketing evaluation of Chinese patent medicine (CPM). The formulation of this technical guidance for RWS of CPM is helpful to researchers in carrying out standardized, reasonable and scientific researches, to improve the quality of production and use of real-word evidence, and to promote the advancement of the TCM industry.
ObjectiveTo understand the distribution of demographic sociological characteristics and co-morbidities among primiparous and multiparous pregnant women under the China's universal two-child policy, to provide baseline data for clinical high-risk management and medical resources allocation.MethodsWe included pregnant women from 24 hospitals in 16 provinces (municipality, autonomous region) of China and collected their demographic sociological characteristics and obstetrics information by questionnaires between September 19th, and November 20th, 2016. Then, we used descriptive analysis to present the distribution of demographic sociological characteristics and pregnancy co-morbidities among primiparous and multiparous women and compared differences between groups by t test or Chi-square test.ResultsAmong 12 403 investigated pregnant women, 8 268 (66.7%) were primiparous and 4 135 (33.3%) were multiparous, with highest proportion in East (931/2 008, 46.4%) and lowest in Northeast (385/2 179, 17.7%). Multiparous women, comparing to primiparous women, were more likely to be elderly than 35 years (accounting for 30.6% vs. 6.5%), lower educated with high school or below (29.7% vs. 16.9%), occupied in physical labor or unemployed (49.2% vs. 42.5%), non-local residents (12.7% vs. 10.5%), family annual income higher than 120 thousand yuan (41.3% vs. 33.3%), pre-pregnancy body mass index≥24 kg/m2 (13.6% vs. 9.9%), history of artificial abortions (44.9% vs. 24.0%), or pregnancies≥4 times (23.8% vs. 3.1%) and were less likely to receive assisted reproductive technology (2.3% vs. 4.7%). The most common co-morbidities were gynecology disease (5.5%), thyroid disease (5.4% in all women), blood system disease (5.0%), digestive system disease (4.2%) and hepatitis B infection (2.5%). Multiparous women, comparing to primiparous women, had higher proportions with blood system disease (5.7% vs. 4.7%), hepatitis B infection (3.1% vs. 2.2%) and chronic hypertension (0.6% vs. 0.2%), but lower proportions with thyroid diseases, polycystic ovary syndrome, and immune system diseases, whose distribution also showed regional differences.ConclusionThere existed distribution differences regarding demographic sociological characteristics and co-morbidities proportions between primiparous and multiparous women. Therefore, we should improve clinical risk management and medical resources allocation based on pregnant women’s baseline and gestational characteristics.