Standardized Reporting of Machine Learning Applications in Urology: The STREAM-URO Framework

Area of Science:

• Urology
• Medical Informatics
• Artificial Intelligence

Background:

• Machine learning (ML) applications in urology lack standardized reporting guidelines.
• Inconsistent reporting hinders study quality, reproducibility, and peer review.
• There is a need for a framework to guide ML study reporting in urology.

Purpose of the Study:

• Introduce the Standardized Reporting of Machine Learning Applications in Urology (STREAM-URO) framework.
• Provide recommendations for reporting ML studies in urology.
• Enhance the quality, reproducibility, and interpretability of ML research in urology.

Main Methods:

• Development of the STREAM-URO framework through expert consensus and literature review.
• Inclusion of key recommendations covering data, model development, validation, and reporting.
• Focus on practical guidelines for researchers and reviewers.

Main Results:

• The STREAM-URO framework provides a comprehensive set of reporting recommendations.
• The framework aims to streamline the peer review process for ML studies.
• Implementation of STREAM-URO is expected to improve ML study quality and comparability.

Conclusions:

• The STREAM-URO framework is essential for advancing ML in urology.
• Standardized reporting will foster higher quality research and better clinical integration.
• Adoption of STREAM-URO will enhance ML literacy and engagement within the urological community.