Surgical data science - from concepts toward clinical translation

Abstract

Recent developments in data science in general and machine learning in particular have transformed the way experts envision the future of surgery. Surgical Data Science (SDS) is a new research field that aims to improve the quality of interventional healthcare through the capture, organization, analysis and modeling of data. While an increasing number of data-driven approaches and clinical applications have been studied in the fields of radiological and clinical data science, translational success stories are still lacking in surgery. In this publication, we shed light on the underlying reasons and provide a roadmap for future advances in the field. Based on an international workshop involving leading researchers in the field of SDS, we review current practice, key achievements and initiatives as well as available standards and tools for a number of topics relevant to the field, namely (1) infrastructure for data acquisition, storage and access in the presence of regulatory constraints, (2) data annotation and sharing and (3) data analytics. We further complement this technical perspective with (4) a review of currently available SDS products and the translational progress from academia and (5) a roadmap for faster clinical translation and exploitation of the full potential of SDS, based on an international multi-round Delphi process.

Keywords: Artificial intelligence; Clinical translation; Computer aided surgery; Deep learning; Surgical data science.

Fig. 1.

Building blocks of a surgical data science (SDS) system. Perception: Relevant data is perceived by the system (Section 3). In this context, effectors include humans and/or devices that manipulate the patient including surgeons, operating room (OR) team, anesthesia team, nurses and robots. Sensors are devices for perceiving patient- and procedure-related data such as images, vital signals and motion data from effectors. Data about the patient includes preoperative images and laboratory data, for example. Domain knowledge serves as the basis for data interpretation (Section 4). It comprises factual knowledge, such as previous findings from studies, clinical guidelines or hospital-specific standards related to the clinical workflow as well as practical knowledge from previous procedures. Interpretation: The perceived data is interpreted in a context-aware manner (Section 5) to provide real-time assistance (Section 6). Applications of SDS are manifold, ranging from surgical education to various clinical tasks, such as early detection, diagnosis, and therapy assistance.