Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Oct 18, 2022
Date Accepted: Aug 21, 2023
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Artificial intelligence for risk prediction in shared decision making for knee replacement surgery: A qualitative study
ABSTRACT
Background:
The use of artificial intelligence (AI) is increasing in decision-making around knee replacement surgery and this technology holds promise to improve prediction of patient outcomes. Ambiguity surrounds the definition of AI and there are mixed views on its application to the clinical setting.
Objective:
To explore knee replacement patients’ understanding of AI and its potential benefits and pitfalls in the context of shared clinical decision-making.
Methods:
Qualitative study involving primary knee replacement patients at a tertiary referral centre for joint replacement surgery. Participants were purposively selected based on age and sex. Semi-structured interviews explored participants’ understanding of AI and opinions on its use in shared clinical decision-making. Data collection and reflexive thematic analysis took place concurrently. Recruitment continued until thematic saturation was reached.
Results:
Thematic saturation was achieved with 20 participants: 11 (55%) women, 11 (55%) with a substantial post-operative complication, and median age 66 years. Three themes captured the participants’ understanding of AI and their perceptions of its use in shared clinical decision-making. The theme 'Expectations' captured participants’ views of themselves as individuals with the right to self-determination as they seek therapeutic solutions tailored to their circumstances, needs, and desires, including whether to use AI at all. The theme 'Empowerment' highlighted the potential for AI to enable patients to develop realistic expectations and equip them with personalised risk information to discuss in shared decision-making conversations with the surgeon. The theme 'Partnership' captured the importance of symbiosis between AI and clinician because AI has varied levels of interpretability and lacks understanding of human emotions and empathy.
Conclusions:
Knee replacement patients in this study had varied levels of familiarity with AI and diverse conceptualisations of its definition and capabilities. Educating patients about AI, through non-technical explanations and illustrative scenarios, could help to inform their decision to use it for risk prediction in the shared decision-making process with their surgeon. Surgeons may play a key role in finding a place for AI in the clinical setting as uptake of this technology in healthcare continues to grow.
Citation
