# Generative Artificial Intelligence for Data Analysis: A Randomised Controlled Trial in a Public Health Research Institute

## TL;DR

A study tested if using generative AI like ChatGPT helps public health researchers analyze data better or faster than traditional tools.

## Contribution

A randomized trial comparing GenAI-integrated analysis with traditional tools in epidemiological data analysis.

## Key findings

- No significant difference in task scores between GenAI and traditional tools.
- Integrated GenAI analysis was significantly faster than traditional methods.

## Abstract

To assess the competence of students and academic staff to use generative artificial intelligence (GenAI) as a tool in epidemiological data analyses in a randomised controlled trial (RCT).

We invited postgraduate students and academic staff at the Swiss Tropical and Public Health Institute to the RCT. Participants were randomized to analyse a simulated cross-sectional dataset using ChatGPT’s code interpreter (integrated analysis arm) vs. a statistical software (R/Stata) with ChatGPT as a support tool (distributed analysis arm). The primary outcome was the trial task score (out of 17, using an assessment rubric). Secondary outcome was the time to complete the task.

We invited 338 and randomized 31 participants equally to the two study arms and 30 participants submitted results. Overall, there was no statistically significant difference in mean task scores between the distributed analysis arm (8.5, ±4.6) and the integrated analysis arm (9.4, ±3.8), with a mean difference of 0.93 (p = 0.55). Mean task completion time was significantly shorter in the integrated analysis arm compared to the distributed analysis arm.

While ChatGPT offers advantages, its effective use requires a careful balance of GenAI capabilities and human expertise.