Partnering With Generative Artificial Intelligence for Quantitative Data Analysis in Nursing Research: A Practical Workflow for Ethical Collaboration

Abstract

Reproducibility and replicability are our scientific and ethical mandate, and the foundation of trust in nursing science and research. Both rest on transparent documentation of how data were actually analyzed. The rising use of generative artificial intelligence (GenAI) in research intersects with this mandate, with the potential to either support or undermine it, yet practical guidance for conducting GenAI-assisted quantitative analysis remains limited. This gap is particularly relevant for nurse scientists, who increasingly work with complex, biologically-informed datasets spanning genomics, symptoms, and patient outcomes. To address this gap, we present a practice-based guide for partnering with GenAI in quantitative data analysis in nursing research, grounded in a nursing-focused genomic research example. We cover GenAI literacy spanning three dimensions (technical, practical, and ethical) and a two-phase workflow for human-GenAI collaboration spanning planning and pre-specification through code development, formal analysis, translation, and human review and disclosure of GenAI use. The core principle is using GenAI as a tool, not a decision-maker, as scientific integrity requires that humans retain interpretive authority. We further propose a synthetic-data-first approach as a privacy safeguard. We illustrate these concepts through a genetics example, though the principles and workflow generalize to many quantitative nursing research contexts.