Statistical method use in public health research

Type and approach of hysterectomy and oncological survival of women with stage II cancer of endometrium: a large retrospective cohort study

Objective

To explore the association between the Type and approach of hysterectomy and oncological survival of women with stage II cancer of the endometrium.

Patients and methods

684 women with stage II endometrial cancer were included. Eligible cases were grouped by type of hysterectomy (simple hysterectomy or radical hysterectomy)and approach of hysterectomy (laparoscopy or laparotomy). The baseline characteristics were compared among groups. The survival outcomes (disease-free survival and overall survival) were calculated and compared among groups, and the underlying confounding factors were adjusted by the Cox proportional hazard regression analysis.

Results

The radical hysterectomy group and the simple hysterectomy group had 217 cases and 467 cases, respectively. Between the groups, the difference in 5-year disease-free survival (87.3% versus 87.9%, HR=0.97, P=0.87) and 5-year overall survival (83.8% versus 83.8%, HR=0.95, P=0.95) was not statistically significant. The laparotomy group and the laparoscopy group had 277 cases and 407 cases, respectively. Between the groups, the difference in 5-year disease-free survival (88.7% versus 87.1%, HR=1.22, P=0.34) and 5-year overall survival (85.5% versus 82.7%, HR=1.00, P=0.99) was not statistically significant.

Conclusion

For long-term oncological survival, radical hysterectomy is not superior to total hysterectomy in stage II endometrial cancer. Also, for stage II cancer of the endometrium, laparoscopic hysterectomy is as oncologically safe as open hysterectomy.

How Can Quantitative Analysis Be Used to Improve Occupational Health without Reinforcing Social Inequalities? An Examination of Statistical Methods

Taking account of sex and gender in occupational health studies poses statistical challenges. Other sociodemographic variables, such as racialization, class, and age, also affect the relations between workplace exposures and health and interact with sex and gender. Our objective was to perform a critical review of conventional and emerging statistical tools, examining whether each analysis takes account of sociodemographic variables (1) in a way that contributes to identification of critical occupational determinants of health (2) while taking account of relevant population characteristics to reflect intersectional approaches to health and (3) using sample sizes and population characteristics available to researchers. A two-step search was conducted: (1) a scientific watch concerning the statistical tools most commonly used in occupational health over the past 20 years; (2) a screening of the 1980-2022 literature with a focus on emerging tools. Our examination shows that regressions with adjustment for confounders and stratification fail to reveal the sociodemographic mechanisms that interact with occupational health problems, endangering the identification of occupational risks. Multilevel (notably MAIHDA) analyses, decision tree, cluster, and latent analyses are useful methods to consider when seeking to orientate prevention. Researchers should consider methods that adequately reveal the mechanisms connecting sociodemographic variables and occupational health outcomes.

Statistical methods and software used in nutrition and dietetics research: A review of the published literature using text mining

AIM

Dietitians must be statistically literate to effectively interpret the scientific literature underpinning the discipline. Despite this, no study has been conducted that objectively identifies common statistical methods and packages specific to current nutrition and dietetics literature. This study aimed to identify statistical methods and software frequently used in nutrition and dietetics research.

METHODS

A text mining approach using the bag-of-words method was applied to a random sample of articles obtained from all journals in the 'Nutrition and Dietetics' subject category within the SCImago Journal and Country Rank portal and published in 2018. A list of 229 statistical terms and 19 statistical software packages was developed to define the search terms to be mined. Statistical information from the methods section of included articles was extracted into Microsoft Excel (2016) for data cleaning. Statistical analyses were conducted in R (Version 3.6.0) and Microsoft Excel (2016).

RESULTS

Seven hundred and fifty-seven journal articles were included. Numerical descriptive statistics were the most common statistical method group, appearing in 83.2% of articles (n = 630). This was followed by specific hypothesis tests (68.8%, n = 521), general hypothesis concepts (58.4%, n = 442), regression (44.4%, n = 336), and ANOVA (30.8%, n = 233). IBM SPSS statistics was the most common statistical software package, reported in 41.7% of included articles.

CONCLUSION

These findings provide useful information for educators to evaluate current statistics curricula and develop short courses for continuing education. They may also act as a starting point for dietitians to educate themselves on typical statistical methods they may encounter.

Understanding the literature: Complexity of statistical methods used in high-impact cardiothoracic surgery research

OBJECTIVE

Biostatistics are frequently used in research published in the domain of cardiothoracic surgery. The objective of this study was to describe the scope of statistical techniques reported in the literature and to highlight implications for editorial review and critical appraisal.

METHODS

Original research articles published between January and April 2017 in the Journal of Thoracic and Cardiovascular Surgery, Annals of Thoracic Surgery, and the European Journal of Cardio-Thoracic Surgery were examined. For each article, the statistical method(s) reported were recorded and categorized by complexity.

RESULTS

We reviewed 293 articles that reported 1068 statistical methods. The mean number of different statistical methods reported per article was 3.6 ± 1.9, with variation by subspecialty and journal. The most common statistical methods were contingency tables (in 59% of articles), t tests (49%), and survival methods (49%). Only 4% of articles used descriptive statistics alone. An introductory level of statistical knowledge was deemed sufficient for understanding 16% of articles, whereas for the remainder a higher level of knowledge would be needed.

CONCLUSIONS

Contemporary cardiothoracic surgery research frequently requires the use of complex statistical methods. This was evident across articles for all cardiothoracic surgical subspecialties as reported in 3 high-impact journals. Routine review of manuscript submissions by biostatisticians is needed to ensure the appropriate use and reporting of advanced statistical methods in cardiothoracic surgery research.