Objective When making causal inferences in observational studies, in order to improve the robustness of the results of observational studies, statistical analysis techniques are often used to estimate the impact of unmeasured potential confounding factors. By systematically reviewing the application progress of the E-value, one of the sensitivity analysis methods, the advantages and limitations of using the E-value were discussed, to provide references for the application, reporting and interpretation of the E-value. Methods In the PubMed database, E-value was used as a keyword for title, abstract and key paper citation retrieval, and the literature that used the E-value analysis method for sensitivity analysis during 2016-2021 was screened. Results The E-value was widely used not only in cohort studies (n=215) and case-control studies (n=15), but also in cross-sectional studies (n=28), randomized controlled trials (n=6) and meta-analysis (n=16). The E-value was often combined with other sensitivity analysis methods, such as hierarchical analysis, instrumental variables, and multiple statistical regression models that correct different covariates, to further explore the reliability and robustness of the results. Conclusion When the E-value is used to evaluate the confounding factors in observational studies, the confidence interval and P value can be combined to evaluate the sensitivity of the results more comprehensively.
ObjectiveTo systematically review the effectiveness of breastfeeding duration and intensity in reducing the risk of overweight or obesity among offspring exposed to intrauterine hyperglycemia. MethodsThe PubMed, EMbase, Web of Science, CBM, WanFang Data, CNKI and VIP databases were electronically searched to collect observational studies on the associations of breastfeeding with the risk of overweight or obesity among offspring exposed to intrauterine hyperglycemia from inception to September 25th, 2021. Two reviewers independently screened the literature, extracted data and assessed the risk of bias of the included studies. Stata 16.0 software was used for the meta-analysis. ResultsA total of 12 657 participants from 13 observational studies were included. The results of meta-analysis showed that breastfeeding could reduce the risk of overweight or obesity among offspring exposed to intrauterine hyperglycemia (OR=0.67, 95%CI 0.53 to 0.84, P=0.001). Subgroup analysis revealed a protective effect of breastfeeding for both 1-6 months (OR=0.53, 95%CI 0.37 to 0.75, P<0.001) and ≥6 months (OR=0.56, 95%CI 0.46 to 0.69, P<0.001); however, breastfeeding shorter than one month was suggested to increase the risk of overweight or obesity (OR=2.15, 95%CI 1.41 to 3.27, P<0.001). ConclusionAvailable evidence suggests that breastfeeding for more than one month is effective in reducing the risk of overweight or obesity in offspring exposed to intrauterine hyperglycemia, and women with hyperglycemia should be encouraged to breastfeed their offspring for at least 1 month to achieve the effect. Due to the limited quantity and quality of the included studies, more high-quality studies are needed to verify the above conclusion.
ObjectiveTo evaluate the association between H2RA and the risk of hip fracture by performing a meta-analysis. MethodsWe searched CNKI, PubMed and EMbase from inception to September 19th 2016, to collect case-control studies or cohort studies reporting the risk of hip fracture with H2RA. Two reviewers independently screened literature, extracted data and assessed the risk of bias of included studies. Then meta-analysis was performed using Stata 13 software. ResultsEleven studies involving 206 276 hip fracture cases were included. The result of meta-analysis showed that patients receiving H2RA therapy had approximately 1.12 times the risk of developing hip fracture compared with nonusers (OR=1.12 95%CI 1.02 to 1.24, P=0.022). Subgroup analyses by interval time indicated that the risk appeared greater with the continuous users (OR=1.11, 95%CI 1.01 to 1.24, P=0.039) whereas the discontinuous users was not significantly associated with hip fracture risk. ConclusionH2RA therapy may be associated with an increased risk of hip fracture. For patients with intermittent medication, the side effect may disappear by discontinuation of PPI use for at least 30 days, but the study did not find time-effect relationship or dose-effect relationship. Considering the limitations of this study, more rigorous clinical trials evaluating the potential side-effect of H2RA are needed.
Propensity score methods belong to an analytical approach by incorporating the measured covariates and mimicking randomization to enhance the comparability between groups, hence reducing the impact of potential confounding in observational studies. Propensity score methods have been increasingly used in observational studies. This paper illustrates the principle and the methods based on the propensity score, in combination with its application in observational studies. It also compares results from propensity score methods with those from multivariable regression and randomized controlled trials. It was found that currently there has been a lack of recommendations for the selection of propensity score methods. Differences may exist when comparing results from propensity score methods with findings from typical regression analyses and randomized controlled trials.
The necessity and methods of systematic review or Meta-analysis of observational studies were introduced. The difference between the systematic review or Meta-analysis of observational studies and randomized controlled trials was also described.
The level of evidence in randomized controlled studies is high. However, it cannot be widely applied due to its high cost, external authenticity, ethics and other reasons. The traditional observational studies reduce the internal authenticity due to various confounding factors, and the level of evidence is low. Regression discontinuity design (RDD) is a design that observes and compares outcome of object around the threshold under practical clinical conditions. Its capability to adjust confounding factors is second only to that of randomized control studies. It can be used in cases where the intervention (or exposure) is directly related to the value of a continuous variable. For instance, whether an HIV patient needs antiretroviral treatment mainly depends on whether the CD4 cell count is lower than 200/μL. Because the measurement of continuous variables has random error, whether intervention is given near the threshold or is close to random, the baseline of patients in the intervention group and non-intervention group near the threshold should be balanced and comparable. Based on this assumption, the causal effect of intervention (or exposure) and outcome can be estimated by comparing the outcomes of populations near the threshold. RDD is mainly applicable to the study of classification outcomes in medicine, among which two-stage least square method, likelihood ratio based estimation method and Bayesian method are more commonly used model estimation methods. However, the application conditions of RDD and the requirement of sample size limit its extensive application in medicine. With the improvement of data accessibility and the development of real world research, RDD will be more widely used in clinical research.
ObjectiveTo assess whether pre-operative use of infliximab (IFX) will increase the risk of post-operative infectious complications in patients with inflammatory bowel disease (IBD). MethodsPubmed, Web of Science, CBM, CNKI and Wanfang database were searched for all the trials that investigated the effects of infliximab on postoperative infectious complication rates in patients with IBD between January 1990 and April 2013. Two reviewers independently screened the literature according to the inclusion and exclusion criteria, extracted data and assessed the quality of the included studies. Then, meta-analysis was performed using RevMan 5.1 software. ResultsTotally, 14 cohort studies were finally included in the review. There was no significant difference on infectious complications [RR=0.99, 95%CI (0.47, 2.07), P=0.97] between IFX groups and control groups with ulcerative colitis. The same results were found in patients with Crohn's disease on infectious complications [RR=1.32, 95%CI (0.87, 1.98), P=0.19]. ConclusionPre-operative infliximab use is safe and does not increase the risk of post-operative infectious complications in patients with IBD.
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.
Objective To evaluate the role of systematic lymphadenectomy (SL) vs. unsystematic lymphadenectomy (USL) for improving overall survival (OS) in epithelial ovarian cancer (EOC). Methods The databases such as PubMed, EMbase, The Cochrane Library, Evidence-Based Medicine Reviews (EBMR), CBM, CNKI and VIP were searched between January 1, 1995 and December 31, 2010, the randomized controlled trials (RCTs) and observational studies on SL vs. USL in treating EOC were included. Based on Cochrane handbook, the data were extracted, the methodological quality was assessed, and then meta-analyses were conducted by using RevMan 5.0 software. Results The total 13 studies involving 22 796 patients were included, including 5 420 patients in the SL group, and the other 17 376 patients in the USL group. Two of the 13 studies were RCTs, and the other 11 were observational studies (including 2 studies retrieved from SEER data). The analyses on 2 RCTs showed that compared with USL, a) SL could not improve 5-PFS (OR=0.70, 95%CI 0.40 to 1.22, P=0.21) in early-stage EOC (FIGO I to II), but it did improve 5-PFS (OR=0.62, 95%CI 0.40 to 0.96, P=0.03) in advanced-stage EOC (FIGO III to IV); b) SL could not improve 5-OS in both early-stage EOC (OR=0.84; 95%CI 0.44 to1.58, P=0.58) and advanced-stage EOC (OR=0.93, 95%CI 0.64 to 1.37, P=0.73); and c) SL could not improve 5-OS in both early-stage (OR=0.84, 95%CI 0.44 to 1.58, P=0.58) and advanced-stage (OR=0.93, 95%CI 0.64 to 1.37, P=0.73) of EOC patients who had optimal tumor dubulking surgery. The analyses on observational studies showed that compared with USL, a) SL could not improve 5-PFS in both early-stage EOC (OR=0.38, 95%CI 0.08 to 1.74, P=0.21) and advanced-stage (OR=2.88, 95%CI 0.95 to 8.72, P=0.06) EOC; b) Whether SEER impacts were excluded or not, SL did improve 5-OS in both early-stage EOC (OR=0.54, 95%CI 0.46 to 0.63, Plt;0.000 01) and advanced-stage (OR=0.47, 95%CI 0.43 to 0.52, Plt;0.000 01) EOC; and c) For EOC patients who had optimal tumor dubulking surgery, SL could not improve 5-OS in early-stage (OR=0.32, 95% CI 0.02 to 6.19, P=0.45), but it did improve 5-OS in advanced-stage (OR=0.53, 95%CI 0.32 to 0.88, P=0.01). Conclusion These findings suggest that maybe SL can improve 5-PFS and 5-OS in EOC. However, the efficacy of SL on 5-PFS and 5-OS is still undetermined, so more relevant studies are required for further investigating the role of SL in EOC.
Randomized controlled trials are considered as the gold standard for determining the causality, and are usually used to evaluate the efficacy and safety of medical interventions. However, in some cases it is not feasible to conduct a randomized controlled trial. In recent years, a framework called “target trial emulation study” has been formally established to guide the design and analysis of observational studies based on real-world data. This framework provides an effective method for causal inference based on observational studies. In order to facilitate domestic scholars to understand and apply the framework to solve related clinical problems, this article introduces it from the basic concept, framework structure and implementation steps, development status, and prospects.