Interobserver Variability Study

The  Problem:

As is well known, the interpretation of KI67 can vary among observers, which may lead to inconsistent diagnoses and delays in healthcare delivery. Our objective is to research and quantify this variability, assessing the impact of artificial intelligence tools on optimizing and improving the accuracy of diagnostic results.

Study Design:

Phase 1 – Interobserver Evaluation: Each pathologist will analyze 25 pre-selected and categorized images, following standardized criteria for KI67 assessment.

Phase 2 – AI Tool Testing: Professionals will be invited to participate in the evaluation of an application developed by Digpatho, which uses state-of-the-art algorithms to assist pathologists in KI67 analysis, complementing – not replacing – their professional judgment.

Your Contribution:

Image Analysis: Active participation in Phase 1 by analyzing the 25 assigned images.

Image Submission: To expand the dataset for the development of our AI tool, participants are invited to share additional images from their own cases. This step is voluntary.

All images will be fully anonymized and used exclusively for scientific purposes, ensuring the confidentiality and privacy of all patients.

Please note that this study has been approved by the Ethics Committee of the Faculty of Medical Sciences at the National University of Córdoba, guaranteeing adherence to principles of confidentiality, anonymity, and good research practices.