Safety design guidelines for clinician–AI interaction in computer-aided diagnosis systems using system-theoretic framework with explainability validation

Yuki Hagiwara, Katherine Fitch, Mario Trapp · 2026

Read Safety design guidelines for clinician–AI interaction in computer-aided diagnosis systems using system-theoretic framework with explainability validation by Yuki Hagiwara, Katherine Fitch, Mario Trapp (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13421477.txt.

Description

Hagiwara and colleagues present a 2026 paper on making computer-aided diagnosis tools safer when doctors work beside artificial intelligence. The authors use a systems method, STPA, which traces how control actions in a work process can turn unsafe, and add checks on whether system explanations hold up.

The analysis flagged hazards such as automation bias, where doctors accept a system answer too readily, and misread explanations that bend judgment without being noticed. From each unsafe action the team derived design guidelines that builders can trace back to a named hazard. The guidelines push for clear transparency, explanations that stay coherent, and trust that matches the tool's real skill. The result is a practical bridge between safety analysis and product design for diagnosis tools, where a wrong call can cause serious harm to patients.

Catalog record

CREATORYuki Hagiwara, Katherine Fitch, Mario Trapp
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE71 KB
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13421477

Browse the full library · About the Tower of Babel