Skip to main content

German surgeons' perspective on the application of artificial intelligence in clinical decision-making.

International journal of computer assisted radiology and surgery

Authors: Jonas Henn, Tijs Vandemeulebroucke, Simon Hatterscheidt, Jonas Dohmen, Jörg C Kalff, Aimee van Wynsberghe, Hanno Matthaei

PURPOSE: Artificial intelligence (AI) is transforming clinical decision-making (CDM). This application of AI should be a conscious choice to avoid technological determinism. The surgeons' perspective is needed to guide further implementation.

METHODS: We conducted an online survey among German surgeons, focusing on digitalization and AI in CDM, specifically for acute abdominal pain (AAP). The survey included Likert items and scales.

RESULTS: We analyzed 263 responses. Seventy-one percentage of participants were male, with a median age of 49 years (IQR 41-57). Seventy-three percentage of participants carried out a senior role, with a median of 22 years of work experience (IQR 13-28). AI in CDM was seen as helpful for workload management (48%) but not for preventing unnecessary treatments (32%). Safety (95%), evidence (94%), and usability (96%) were prioritized over costs (43%) for the implementation. Concerns included the loss of practical CDM skills (81%) and ethical issues like transparency (52%), patient trust (45%), and physician integrity (44%). Traditional CDM for AAP was seen as experience-based (93%) and not standardized (31%), whereas AI was perceived to assist with urgency triage (60%) and resource management (59%). On median, generation Y showed more confidence in AI for CDM (P = 0.001), while participants working in primary care hospitals were less confident (P = 0.021).

CONCLUSION: Participants saw the potential of AI for organizational tasks but are hesitant about its use in CDM. Concerns about trust and performance need to be addressed through education and critical evaluation. In the future, AI might provide sufficient decision support but will not replace the human component.

© 2025. The Author(s).

PMID: 39907950

Participating cluster members