# Exploring Oral Cavity Cancer in the United Arab Emirates (UAE)

## TL;DR

This study examines oral cavity cancer in the UAE and compares the survival outcomes of four treatment approaches.

## Contribution

The study highlights the importance of considering both statistical significance and effect size in evaluating treatment efficacy for oral cavity cancer.

## Key findings

- No statistically significant difference in survival was found among the four treatment groups.
- A medium effect size of 0.59 suggests a moderate difference in survival between the groups.
- The results emphasize the need to consider both statistical significance and effect size in clinical research.

## Abstract

Background

This study delves into the demographics and clinical characteristics of oral cavity tumors in the context of the United Arab Emirates. It further investigates the efficacy of four different treatment modalities in impacting patient survival rates. It aims to understand if any treatments significantly improve survival compared to others.

Methodology

To assess the survival outcomes across the different treatment groups, the study employed the log-rank test, a non-parametric statistical test widely used in survival analysis. The sample consisted of patients from the electronic medical records assigned to one of the following four treatment groups: radiotherapy only (RT), radiotherapy with surgery and chemotherapy (RT+S+C), radiotherapy with surgery (RT+S), and, finally, radiotherapy with chemotherapy including immunotherapy (RT+C). Data collection involved tracking survival times from the initiation of treatment until the last follow-up period or the occurrence of an event (e.g., death). The statistical analysis was conducted using the chi-squared statistic to determine the distribution of survival times across the groups, providing a quantitative measure of the difference between the observed and expected survival. The Kaplan-Meier curve was plotted for the cohort divided into four groups.

Results

The log-rank test yielded a p-value of 0.321019, suggesting no statistically significant difference in survival among the treatment groups at the 5% significance level. The chi-squared statistic was 3.498018, within the 95% acceptance region, further corroborating the null hypothesis of no significant survival difference across the groups. Despite this, an observed medium effect size of 0.59 indicates a moderate difference in survival between the groups.

Conclusions

The findings illustrate that while there is no statistically significant difference in survival rates among the four treatment groups, the medium effect size observed suggests a moderate difference in survival. This emphasizes the need to consider the statistical significance and effect size in clinical research, as they provide different insights into treatment efficacy.