Work

Physicians’ Perspectives on Predictive Uncertainty in Machine Learning Models

Year: 2026

Type: book-chapter

Abstract: We examined clinicians' perspectives on predictive uncertainty displayed alongside risk predictions using semi-structured interviews in a postoperative delirium dashboard prototype. While clinicians recognized the value of uncertainty information, they struggled to interpret it without clear context, underscoring the need for transparent, human-centered visualisation of predictive uncertainty.

Source: Studies in health technology and informatics

DOI: 10.3233/shti260277

Authors: Nicolas Frey, Niklas Giesa, Louis Agha-Mir-Salim, Felix Balzer

Institution: Charité - Universitätsmedizin Berlin

Language: English

Topic: Artificial Intelligence in Healthcare and Education

Subfield: Health Informatics

Field: Medicine

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: hybrid

OpenAlex ID: W7161999562

FWCI:

Cites:

Cited by:

Related to: