A new nine-point checklist has been introduced in Veterinary Pathology to improve the reporting quality of studies using artificial intelligence (AI) for automated image analysis (AIA). The checklist addresses growing concerns about reproducibility and transparency as AI tools become more prevalent in pathology research.
Developed by veterinary pathologists, machine learning experts, and journal editors, the checklist highlights key methodological details for manuscripts, including dataset creation, model training, performance evaluation, and AI system interaction. The goal is to promote clear communication and reduce cognitive and algorithmic bias. Transparent reporting and readily available supporting data, such as training datasets and source code, are crucial for validation and broader application of AI tools in routine pathology workflows.
