Article Text
Statistics from Altmetric.com
Pozzi provides a thought-provoking account of how machine-learning clinical prediction models (such as Prediction Drug Monitoring Programmes (PDMPs)) may exacerbate testimonial injustice.1 In this response, I generalise Pozzi’s concerns about PDMPs to traditional models of clinical practice and question the claim that inaccurate clinicians are necessarily preferential to inaccurate machine-learning models. I then explore Pozzi’s concern that such models may deprive patients of a right to ‘convey information’. I suggest that machine-learning tools may be used to enhance, rather than frustrate, this right, through the perspective of hermeneutical justice.
A false equivalence?
Pozzi objects to the introduction of machine-learning risk prediction tools in clinical care, due to their being ‘epistemically opaque’, often inaccurate, and a threat to patients’ testimonial justice. Through the example of psychiatry, I suggest this stance idealises traditional models of clinical practice. I propose that clinicians’ judgements are often equally vulnerable to opaque subjectivity, bias and epistemic injustice. For instance, the use of clinical observation or collateral interviewing might be conceptualised as a threat to testimonial justice, by neglecting patients’ own perspectives or voices. In practice, clinical risk prediction often follows inconsistent and somewhat subjective clinical heuristics, which are difficult to summarise or evaluate. Further, although Pozzi diminishes machine-learning …
Footnotes
Twitter @george_gillett
Contributors Sole contributor.
Funding The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.
Competing interests None declared.
Provenance and peer review Not commissioned; internally peer reviewed.
Linked Articles
- Feature article
Read the full text or download the PDF:
Other content recommended for you
- Epistemic injustice in healthcare encounters: evidence from chronic fatigue syndrome
- Epistemic injustice, children and mental illness
- Epistemic injustice in psychiatric practice: epistemic duties and the phenomenological approach
- Evidence, ethics and the promise of artificial intelligence in psychiatry
- Patients, clinicians and open notes: information blocking as a case of epistemic injustice
- Further remarks on testimonial injustice in medical machine learning: a response to commentaries
- Consistency of variety of machine learning and statistical models in predicting clinical risks of individual patients: longitudinal cohort study using cardiovascular disease as exemplar
- Machine learning in medicine: should the pursuit of enhanced interpretability be abandoned?
- Use of machine learning in osteoarthritis research: a systematic literature review
- Where is knowledge from the global South? An account of epistemic justice for a global bioethics