Artificial Intelligence You Can Trust: What Matters Beyond Performance When Applying Artificial Intelligence to Renal Histopathology?

Abstract

Although still in its infancy, artificial intelligence (AI) analysis of kidney biopsy images is anticipated to become an integral aspect of renal histopathology. As these systems are developed, the focus will understandably be on developing ever more accurate models, but successful translation to the clinic will also depend upon other characteristics of the system.In the extreme, deployment of highly performant but “black box” AI is fraught with risk, and high-profile errors could damage future trust in the technology. Furthermore, a major factor determining whether new systems are adopted in clinical settings is whether they are “trusted” by clinicians. Key to unlocking trust will be designing platforms optimized for intuitive human-AI interactions and ensuring that, where judgment is required to resolve ambiguous areas of assessment, the workings of the AI image classifier are understandable to the human observer. Therefore, determining the optimal design for AI systems depends on factors beyond performance, with considerations of goals, interpretability, and safety constraining many design and engineering choices.In this article, we explore challenges that arise in the application of AI to renal histopathology, and consider areas where choices around model architecture, training strategy, and workflow design may be influenced by factors beyond the final performance metrics of the system.

ChatGPT vs. Bard: A Comparative Study

“…ChatGPT has recently undergone an update, transitioning from GPT-3.5 to GPT-4, while Bard has embraced the PALM model [1] and also developing the PaLM 2 [148][149], moving on from LaMDA [22]. The quality of responses generated by these models depends on their underlying architecture and size [150]. So, as the models grow in parameters, their ability to comprehend human language improves exponentially.…”

Second Opinion in the Italian Organ Procurement Transplantation: The Pathologist Is In

“…However, successful translation to the transplant community will also depend upon other system characteristics. The key to unlocking trust will be designing platforms or tools optimized for intuitive human–AI interactions and ensuring that, where judgment is required to resolve ambiguous assessment areas, the tool’s working mode is understandable to the human observer [ 42 ]. The goal is to release targeted and “real intelligence” algorithms for organ donor assessment parameters, such as fibrosis, inflammation, and steatosis.…”

Artificial Intelligence in the Pathology of Gastric Cancer

“…Another important consideration in AI pathology is whether the AI-standalone interpretation can be utilized as a confirmative diagnostic tool without a pathologist’s reading. Despite the sophistication of the algorithm, the mainstay of DL algorithms remains recognized as a “black box” and can be affected by the Clever Hans effect [ 96 97 98 ]; this hinders the analysis of errors even by software developers and cannot account for the legal issues. Therefore, supervision by pathologists is required for AI-based pathological analysis systems [ 99 ].…”