SPKS: Surgical Procedural Knowledge Sentences dataset

SPKS is a textual dataset of the surgical robotic field consisting of 1958 sentences (37022 words and 3999 unique words) manually annotated as procedural and non-procedural by an expert annotator. To the best of our knowledge, SPKS is the first dataset in the literature containing procedural annotated sentences from the surgical robotic sector. We believe it is an indispensable resource for anyone who wants to test their classification algorithms in order to detect procedural knowledge in surgical written texts. The sentences are taken from different sources, and cover various robotic surgery procedures in urology, gynecology, gastrointestinal procedures, and thoracic procedures. The construction of the dataset is described in the following associated publication (c.f. Sections "Dataset" and "Preprocessing the dataset"): Bombieri, M., Rospocher, M., Dall’Alba, D., Fiorini, P. Automatic detection of procedural knowledge in robotic-assisted surgical texts. International Journal of Computer Assisted Radiology and Surgery (2021). DOI: 10.1007/s11548-021-02370-9