Proceedings from the 2022 ACR-RSNA Workshop on Safety, Effectiveness, Reliability, and Transparency in AI

Despite the surge in AI development for healthcare applications, particularly for medical imaging applications, there has been limited adoption of such AI tools into clinical practice. During a one-day workshop in November, 2022, co-organized by the American College of Radiology (ACR) and the Radiological Society of North America (RSNA), participants outlined experiences and problems with implementing AI in clinical practice, defined the needs of various stakeholders in the AI ecosystem, and elicited potential solutions and strategies related to the safety, effectiveness, reliability, and transparency of AI algorithms. Participants included radiologists from academic and community radiology practices, informatics leaders responsible for AI implementation, regulatory agency employees, and specialty society representatives. The major themes that emerged fell into two categories: 1) AI product development and 2) implementation of AI-based applications in clinical practice. In particular, participants highlighted key aspects of AI product development to include clear clinical task definitions; well-curated data from diverse geographic, economical, and healthcare settings; standards and mechanisms to monitor model reliability; and transparency regarding model performance, both in controlled and real-world settings. For implementation, participants emphasized the need for strong institutional governance; systematic evaluation, selection, and validation methods carried out by local teams; seamless integration into the clinical workflow; performance monitoring and support by local teams; performance monitoring by external entities; and alignment of incentives through credentialing and reimbursement. Participants predicted that clinical implementation of AI in radiology will continue to be limited until the safety, effectiveness, reliability, and transparency of such tools are more fully addressed.

Age-dependent genetic and environmental variance of semen quality in Nordic Holstein bulls

The aim of this study was to estimate genetic and environmental parameters, across bull's age, for semen quality traits including pre- and postcryopreservation semen concentration, sperm motility, and sperm viability as well as ejaculate volume and number of doses per ejaculate. A data set on 96,595 ejaculates from 2,831 Nordic Holstein bulls collected between 2006 and 2019 was used. Genetic and environmental parameters were estimated using a random regression model and applying the average-information REML approach. Spline functions were chosen to fit the additive genetic and permanent environmental effects across bull's age, and the optimal number of knots was chosen using cross validation. Residual variance heterogeneity was assumed in different bull age classes. The estimated repeatabilities of semen quality traits ranged from 0.16 to 0.85 across different ages of bulls. The estimated heritabilities of semen quality traits ranged from 0.02 to 0.56 across different ages of bulls. The results indicate possibilities for genetic improvement of semen quality traits through selective breeding.