Machine Learning (ML) is on the rise in medicine, promising improved diagnostic, therapeutic and prognostic clinical tools. While these technological innovations are bound to transform health care, they also bring new ethical concerns to the forefront. One particularly elusive challenge regards discriminatory algorithmic judgements based on biases inherent in the training data. A common line of reasoning distinguishes between justified differential treatments that mirror true disparities between socially salient groups, and unjustified biases which do not, leading to misdiagnosis and erroneous (...) treatment. In the curation of training data this strategy runs into severe problems though, since distinguishing between the two can be next to impossible. We thus plead for a pragmatist dealing with algorithmic bias in healthcare environments. By recurring to a recent reformulation of William James’s pragmatist understanding of truth, we recommend that, instead of aiming at a supposedly objective truth, outcome-based therapeutic usefulness should serve as the guiding principle for assessing ML applications in medicine. (shrink)

Background Though artificial intelligence holds great value for healthcare, it may also amplify health inequalities through risks of bias. In this paper, we explore bias risks in targeted medicines manufacturing. Targeted medicines manufacturing refers to the act of making medicines targeted to individual patients or to subpopulations of patients within a general group, which can be achieved, for example, by means of cell and gene therapies. These manufacturing processes are increasingly reliant on digitalised systems which can be controlled by artificial (...) intelligence algorithms. Whether and how bias might turn up in the process, however, is uncertain due to the novelty of the development. Methods Examining stakeholder views across bioethics, precision medicine, and artificial intelligence, we document a range of opinions from eleven semi-structured interviews about the possibility of bias in AI-driven targeted therapies manufacturing. Result Findings show that bias can emerge in upstream (research and development) and downstream (medicine production) processes when manufacturing targeted medicines. However, interviewees emphasized that downstream processes, particularly those not relying on patient or population data, may have lower bias risks. The study also identified a spectrum of bias meanings ranging from negative and ambivalent to positive and productive. Notably, some participants highlighted the potential for certain biases to have productive moral value in correcting health inequalities. This idea of “corrective bias” problematizes the conventional understanding of bias as primarily a negative concept defined by systematic error or unfair outcomes and suggests potential value in capitalizing on biases to help address health inequalities. Our analysis also indicates, however, that the concept of “corrective bias” requires further critical reflection before they can be used to this end. (shrink)

Many countries currently invest in technologies and data infrastructures to foster precision medicine (PM), which is hoped to better tailor disease treatment and prevention to individual patients. But who can expect to benefit from PM? The answer depends not only on scientific developments but also on the willingness to address the problem of structural injustice. One important step is to confront the problem of underrepresentation of certain populations in PM cohorts via improved research inclusivity. Yet, we argue that the perspective (...) needs to be broadened because the (in)equitable effects of PM are also strongly contingent on wider structural factors and prioritization of healthcare strategies and resources. When (and before) implementing PM, it is crucial to attend to how the organisation of healthcare systems influences who will benefit, as well as whether PM may present challenges for a solidaristic sharing of costs and risks. We discuss these issues through a comparative lens of healthcare models and PM-initiatives in the United States, Austria, and Denmark. The analysis draws attention to how PM hinges on—and simultaneously affects—access to healthcare services, public trust in data handling, and prioritization of healthcare resources. Finally, we provide suggestions for how to mitigate foreseeable negative effects. (shrink)