Explaining a model predicting quality of surgical practice: a first presentation to and review by clinical experts

LapEx: A new multimodal dataset for context recognition and practice assessment in laparoscopic surgery

In Surgical Data Science (SDS), there is an increasing demand for large, realistic annotated datasets to facilitate the development of machine learning techniques. However, in laparoscopic surgery, most publicly available datasets focus on low-granularity procedural annotations (such as phases or steps) and image segmentation of instruments or specific organs, often using animal models that lack clinical realism. Furthermore, annotation variability is seldom evaluated. In this work, we compiled 30 sleeve gastrectomy procedures and performed three levels of annotations for a specific step of this procedure (the fundus dissection): a procedural annotation of fine-grained activities, a semantic segmentation of the laparoscopic images, and the assessment of a surgical skill, specifically the quality of exposition of the surgical scene. We also conducted a comprehensive annotation variability analysis, highlighting the complexity of these tasks and providing a baseline for evaluating machine learning models. The dataset is publicly available and serves as a valuable resource for advancing SDS research.

Essential properties and explanation effectiveness of explainable artificial intelligence in healthcare: A systematic review

Background

Significant advancements in the field of information technology have influenced the creation of trustworthy explainable artificial intelligence (XAI) in healthcare. Despite improved performance of XAI, XAI techniques have not yet been integrated into real-time patient care.

Objective

The aim of this systematic review is to understand the trends and gaps in research on XAI through an assessment of the essential properties of XAI and an evaluation of explanation effectiveness in the healthcare field.

Methods

A search of PubMed and Embase databases for relevant peer-reviewed articles on development of an XAI model using clinical data and evaluating explanation effectiveness published between January 1, 2011, and April 30, 2022, was conducted. All retrieved papers were screened independently by the two authors. Relevant papers were also reviewed for identification of the essential properties of XAI (e.g., stakeholders and objectives of XAI, quality of personalized explanations) and the measures of explanation effectiveness (e.g., mental model, user satisfaction, trust assessment, task performance, and correctability).

Results

Six out of 882 articles met the criteria for eligibility. Artificial Intelligence (AI) users were the most frequently described stakeholders. XAI served various purposes, including evaluation, justification, improvement, and learning from AI. Evaluation of the quality of personalized explanations was based on fidelity, explanatory power, interpretability, and plausibility. User satisfaction was the most frequently used measure of explanation effectiveness, followed by trust assessment, correctability, and task performance. The methods of assessing these measures also varied.

Conclusion

XAI research should address the lack of a comprehensive and agreed-upon framework for explaining XAI and standardized approaches for evaluating the effectiveness of the explanation that XAI provides to diverse AI stakeholders.