Surgical data science: The new knowledge domain.

Area of Science:

• Surgical/Interventional Data Science (SDS)
• Health Informatics
• Medical Technology

Background:

• Healthcare, particularly surgery, is advancing with technology, necessitating better data utilization.
• Conventional research methods like registry studies have limitations in data scope, analysis, and translation.
• There's a need for advanced approaches to improve the quality and value of surgical care.

Purpose of the Study:

• To introduce Surgical/Interventional Data Science (SDS) as a transformative approach for improving surgical care pathways.
• To highlight SDS's potential in measuring, modeling, and quantifying surgical processes for better decision-making.
• To outline how SDS can enhance patient safety, quality, and value in interventional healthcare.

Main Methods:

• Utilizing pervasive data throughout the surgical care pathway (pre-, intra-, post-operative).
• Developing tools to measure, model, and quantify patient health states and outcomes.
• Integrating data science expertise into clinical research teams and fostering collaboration.

Main Results:

• Preliminary results show SDS can improve prediction of surgical complications using complex data.
• SDS can support intra-operative decision-making and enhance collaboration between clinicians and technology.
• SDS offers potential for objective assessments and automated coaching in surgical education.

Conclusions:

• Surgical/Interventional Data Science (SDS) is crucial for future evidence-based improvements in surgical care.
• Realizing SDS's full potential requires a cultural shift towards data integration and expertise assimilation.
• Collaboration with industry is key for optimal design, translation, and commercialization of SDS tools.