![]() ![]() However, translating these ML models from the bench to the bedside to support clinical stakeholders during routine care brings substantial challenges, among other reasons, because of the high stakes involved in most decisions that impact human lives. There have been considerable research thrusts to develop Machine Learning (ML) models in the healthcare domain that assist clinical stakeholders 1. Following these guidelines increases the likelihood that the algorithms afford transparency and enable stakeholders to capitalize on the benefits of transparent ML. The INTRPRT guideline suggests human-centered design principles, recommending formative user research as the first step to understand user needs and domain requirements. To alleviate these shortcomings in forthcoming research, we introduce the INTRPRT guideline, a design directive for transparent ML systems in medical image analysis. These shortcomings put contemporary research on transparent ML at risk of being incomprehensible to users, and thus, clinically irrelevant. Only a few studies validated transparency claims through empirical user evaluations. Despite the different roles and knowledge of ML developers and end users, no study reported formative user research to inform the design and development of transparent ML models. Current techniques in transparent ML are dominated by computational feasibility and barely consider end users, e.g. ![]() We identified 2508 records and 68 articles met the inclusion criteria. To investigate the state of transparent ML in medical image analysis, we conducted a systematic review of the literature from 2012 to 2021 in PubMed, EMBASE, and Compendex databases. ![]() Following human-centered design principles in highly specialized and high stakes domains, such as medical image analysis, is challenging due to the limited access to end users and the knowledge imbalance between those users and ML designers. ![]() Thus, prototyping and user evaluations are critical to attaining solutions that afford transparency. From a human-centered design perspective, transparency is not a property of the ML model but an affordance, i.e., a relationship between algorithm and users. Transparency in Machine Learning (ML), often also referred to as interpretability or explainability, attempts to reveal the working mechanisms of complex models. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |