Introduction: As the integration of Artificial Intelligence (AI) in healthcare continues to advance, the need
for rigorous study design and research protocols tailored to diagnostic and prognostic studies becomes
paramount.
Aim: The primary objective of this work is to highlight the biostatistician’s point of view about the key
points of the research protocol involving AI.
Methods: Assessing the current state-of-the-art guidelines, we outline the methodological challenges faced
by biostatisticians when collaborating on research protocols in the era of AI-driven medical research.
Results: The proposed overview on research protocol involving AI elucidates key considerations in study
design, encompassing evaluations of data quality, analysis of biases, methodological approaches, determination
of sample size, and validation strategies tailored specifically to AI applications. This position
paper underscores the pivotal role of strong statistical frameworks in ensuring the reliability, validity, and
applicability of findings derived from AI-based diagnostic and prognostic models. Moreover, the paper
seeks to highlight the critical importance of incorporating transparent reporting standards to enhance the
reproducibility and clarity of AI-driven studies.
Conclusions: By offering a comprehensive biostatistician’s viewpoint, this paper strives to significantly
contribute to the methodological progression of diagnostic and prognostic studies in the era of Artificial
Intelligence.
