Practical Guide to Use of Simulation and Video Data

Ce dossier présente un ensemble de guides pratiques concernant l'intelligence artificielle et les sources de données massives dans la recherche en chirurgie

Résumé en anglais

Surgical performance assessment has evolved to include quantitative metrics (eg, tool movements) and qualitative assessments based on objective data (eg, video-based assessment [VBA]). Simulation-based performance assessment combined with biotrackers and other approaches has opened the door to capturing surgeon-specific data, such as heart rate variability, electroencephalographic data, and nontechnical skills assessment, in standardized settings, thus enhancing the quality and objectivity of the data. Multimodal data can offer a comprehensive view of surgeons’ performance, shedding light on stress, attention, and other influencing factors. However, these data also require careful consideration due to their sensitive nature (eg, patient and surgeon privacy) and unique data forms (eg, unstructured data, such as video, audio, and waveforms). Biases and pitfalls in data interpretation may lead to inappropriate and inaccurate assumptions and applications. This guide offers key considerations researchers must address when using these data (Box).