Objective To investigate the specific variables and influence factors of Harris scores in follow-up data of patients with internal fixation of femoral neck fracture. Methods From May 1999 to May 2004, 99 cases of femoral neck fracture receiving close reduction with cannulated screw and having complete follow-up data were evaluated in terms of age, sex, type of bone fracture (Garden classification), reduction time, reduction qual ity (Garden indicators), time of full weight-loading, removal of internal fixation, traction before operation, side of bone fracture, necrosis of femoral head, duration of follow-up and Harris score during follow-up period. Univariate and multivariate were analyzed by SPSS14.0 and SAS8.2. Results P-P probabil ity plot and normal test revealed the Harris scores were non-normal distribution (W=0.757 09, P=0.000 1). By nonparametric test in univatiate analysis, the following variables in Harris scores were of statistic significance: the time of reduction (U=— 2.289, P=0.022), the Garden classifaction (H=16.943, P=0.001), the time of full weight-bearing (U=— 3.069, P=0.002), the qual ity of reduction (U=— 3.448, P=0.001) and the necrosis of femoral head (U=— 4.723, P=0.000).By the analysis of correlation, the following variables in Harris scores were of statistic significance: Garden classification(rs=— 0.412, P=0.000), the time of reduction (rs=— 0.231, P=0.021), the qual ity of reduction (rs=— 0.348, P=0.000), the time of full weight-bearing (rs=— 0.310, P=0.002), and the necrosis of femoral head (rs=— 0.477, P=0.000). By the univariate logistic regression analysis, the following variables in Harris scores were of statistic significance: Garden classification (P=0.000 1), the time of reduction (P=0.012 6), the qual ity of reduction (P=0.000 3), the time of full weight-bearing (P=0.003 2), the traction before operation (P=0.049 2) and the necrosis of femoral head (P=0.000 1). By the multivariate logistic regression analysis, the influence factors of Harris scores rank included the necrosis of femoral head (P=0.000 1), the time of reduction (P=0.028 2), and Garden classification (P=0.000 7). Conclusion Harris scores is of non-normal distribution, and the necrosis of femoral head is the most important factor influencing the function after applying internal fixation with cannulated screws to femoral neck fracture.
Cluster randomized trial (CRT) is one of the most common design for complex intervention. This paper mainly introduced:the definition of CRT, two designs of CRT including the completely randomization and the restricted randomization (such as stratified randomization and matching randomization), and the statistical analysis methods (such as the general statistical analysis and mixed effect model/multi-level model). This paper also introduced how to estimate the sample size of a CRT, how to report a CRT, and how to apply it into a clinical or community study.
An N-of-1 trial was conducted in a single patient. Statistical analysis is one of the most important parts of N-of-1 trials. The methods of statistical analysis for N-of-1 trials were reported in some reviews. However, there was still a lack of comparative analysis of these methods. In this study, we introduced the characteristics of statistical methods commonly used as well as some statistical problems which should be paid attention in N-of-1 trials. It is useful to provide some reference for statistical methods in order to high quality N-of-1 trials.
Research of generating real-world evidence using real world data has attracted considerable attention globally. Outcome research of treatment based on existing health and medical data or registries has become one of the most important topics. However, there exists certain confusions in this line of research on how to design and implement appropriate statistical analysis. Therefore, in the fourth chapter of the series technical guidance to develop real world evidence by China REal world data and studies Alliance (ChinaREAL), we aim to provide an guidance on statistical analysis in the study to assess therapeutic outcomes based on existing health and medical data or registries.In this chapter, we first emphasize the significance of pre-specified statistical analysis plan, recommending key components of the statistical analysis plan. We then summarize the issue of sample size calculation in this content and clarify the interpretation of statistical p-value. Secondly, we recommend procedures to be considered to tackle the issue related to the selection bias, information bias and most importantly, confounding bias. We discuss the multivariable regression analysis as well as the popular causal inference models. We also suggest that careful consideration should be made to deal with missing data in real-world databases. Finally, we list core content of the statistical report.
Epigenetics refers to the modification effect of external and internal environmental factors on genes under the premise of the unaltered genetic sequence, leading to changes in gene expression level or function, and thereby affecting various phenotypes or disease outcomes. In recent years, epigenetics has attracted increasing attention. Among them, DNA methylation has been shown to be closely related to human development and the development of disease. However, the high-dimensional omics data generated by genome-wide methylation detection can comprehensively reflect the overall and local epigenetic modifications at the genome level, which has become one of the main research contents in this field. Based on genome-wide methylation chip data, this paper summarized the quality control process of this omics data, common epigenetic omics correlation statistical analysis methods and ideas, and visualization realization of main results based on SAS JMP Genomics 10 software, so as to provide reference for similar studies.
ObjectiveTo explore the abilities of thesis writing of postgraduate medical freshpeople and their factors, and provide a basis for postgraduate education and course design of thesis writing.MethodsA designed questionnaire was administered to postgraduate medical freshpeople enrolled in West China Medical School of Sichuan University in 2020. The general characteristics, current status of skills or experiences related to thesis writing, and abilities including literature retrieval and reading, statistical analysis, diagramming, research paper writing, and journal selection and submission of the postgraduates were collected in September 2020. Logical regression was conducted to analyze the factors affecting the abilities of thesis writing.ResultsA total of 503 valid questionnaires were collected. Over one half of the graduate students (58.3%) were satisfied with the ability of literature retrieval and reading, with the highest score among the five abilities [median (lower quartile, upper quartile) was 3 (2, 3)]. Less than 20% of the students were satisfied with the remaining four abilities, with the lowest scores in the abilities of diagramming, research paper writing, and journal selection and submission [each median (lower quartile, upper quartile) was 1 (1, 2)]. Research experience and acknowledge of reporting guidelines were independent factors for all abilities related to thesis writing (P<0.05). Proficiency in statistical software was an independent factor for the abilities of data statistical analysis, diagramming, research paper writing, and journal selection and submission (P<0.05). Having published scientific paper was an independent factor for ability of journal selection and submission [odds ratio=4.695, 95% confidence interval (2.166, 10.180), P<0.001].ConclusionsThe postgraduate medical freshpeople of West China Medical School are not satisfied with the ability of statistical analysis, diagramming, paper writing, or journal selection and submission. Attention should be paid to research practice and learning of reporting guidelines, while statistical courses and diagramming courses should be set up expressly.
The correct and reasonable statistical analysis method can make the results of comparative diagnosis test accuracy more convincing. In this paper, the accuracy of diagnostic tests is divided into 2 forms: binary-scale outcomes and ordinal-scale/continuous-scale outcomes. Taking diagnostic indicators such as sensitivity, specificity, receiver operating characteristic (ROC) curves and area under curve (AUC) values as entry points, combined with examples, this paper introduced how to compare the diagnostic results of tests by parameter estimation and hypothesis testing, with the aim of providing references for the comparative diagnosis test accuracy.
The utilisation of statistical analysis plan (SAP) has the potential to enhance the reliability, transparency, and impartiality of statistical analysis procedures in the context of clinical studies. These plans are primarily designed for late phase clinical studies, namely phase Ⅱ and phase Ⅲ randomised controlled trials. The extended SAP reporting guidelines for early phase clinical studies, i.e., phase Ⅰ clinical studies and phase Ⅱ non-randomised controlled trials, have been expanded from the original reporting guidelines in six key areas: trial purpose, design, Bayesian statistics, data simulation, sample size, and the application of ICH E9 (R1). The expanded reporting guidelines facilitate the standardisation of SAP for early phase clinical trials, enhance the transparency and reproducibility of early phase clinical studies, and thereby improve the quality of early phase clinical studies. This, in turn, plays a pivotal role in later phase clinical studies.