A foundation for evaluating the surgical artificial intelligence literature

Daniel A Hashimoto ¹, Sai Koushik Sambasastry ², Vivek Singh ³

⁰Penn Computer Assisted Surgery and Outcomes Laboratory, Department of Surgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA; School of Engineering and Applied Science, University of Pennsylvania, Philadelphia, PA, USA; Global Surgical AI Collaborative, Toronto, ON, USA.

European Journal of Surgical Oncology : the Journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology +

|

February 15, 2024

View abstract on PubMed

Summary

This guide helps surgeons understand artificial intelligence (AI) in surgery. It provides a framework for critically evaluating AI research, ensuring safe and effective application in surgical practice.

Area Of Science

Medical Informatics
Surgical Technology
Artificial Intelligence in Medicine

Background

The increasing integration of artificial intelligence (AI) into surgical applications necessitates a specialized understanding for surgeons.
Surgeons require foundational knowledge to critically assess AI-related scientific literature, product claims, and regulatory landscapes.

Purpose Of The Study

To provide surgeons with a comprehensive framework for evaluating scientific manuscripts that utilize AI.
To equip surgeons with the necessary tools to appraise the quality and applicability of AI in surgical practice.

Main Methods

The guide offers a glossary of common artificial intelligence terms.
It includes an overview of prerequisite knowledge for understanding AI methodologies.
Recommendations are provided for evaluating key manuscript elements, including data quality, methodology, and reproducibility.

Main Results

The framework enables surgeons to assess the quality of training data for AI algorithms.
It facilitates evaluation of the appropriateness of methodological approaches in AI research.
The guide aids in assessing the potential for reproducibility and applicability of AI in surgical settings.

Conclusions

This resource empowers surgeons to critically appraise AI in surgical literature and practice.
It addresses considerations for generalizability and scalability of AI solutions in surgery.
Enhanced understanding promotes the responsible and effective adoption of AI in surgical fields.

Keywords:

Algorithms Artificial intelligence Computer vision Data science Deep learning Machine learning