Academic machine learning researchers' ethical perspectives on algorithm development for health care: a qualitative study.

OBJECTIVES: We set out to describe academic machine learning (ML) researchers' ethical considerations regarding the development of ML tools intended for use in clinical care. MATERIALS AND METHODS: We conducted in-depth, semistructured interviews with a sample of ML researchers in medicine (N = 10) as part of a larger study investigating stakeholders' ethical considerations in the translation of ML tools in medicine. We used a qualitative descriptive design, applying conventional qualitative content analysis in order to allow participant perspectives to emerge directly from the data. RESULTS: Every participant viewed their algorithm development work as holding ethical significance. While participants shared positive attitudes toward continued ML innovation, they described concerns related to data sampling and labeling (eg, limitations to mitigating bias; ensuring the validity and integrity of data), and algorithm training and testing (eg, selecting quantitative targets; assessing reproducibility). Participants perceived a need to increase interdisciplinary training across stakeholders and to envision more coordinated and embedded approaches to addressing ethics issues. DISCUSSION AND CONCLUSION: Participants described key areas where increased support for ethics may be needed; technical challenges affecting clinical acceptability; and standards related to scientific integrity, beneficence, and justice that may be higher in medicine compared to other industries engaged in ML innovation. Our results help shed light on the perspectives of ML researchers in medicine regarding the range of ethical issues they encounter or anticipate in their work, including areas where more attention may be needed to support the successful development and integration of medical ML tools.

Negative association of perceived risk and willingness to participate in innovative psychiatric research protocols.

Psychiatric researchers grapple with concerns that individuals with mental illness may be less likely to appreciate risks of research participation, particularly compared to people not suffering from mental illness. Therefore, empirical studies that directly compare the perspectives of such individuals are needed. In addition, it is important to evaluate perspectives regarding varied types of research protocols, particularly as innovative psychiatric research protocols emerge. In this pilot study, respondents with a mood disorder (n = 25) as well as respondents without a mood disorder (n = 55) were recruited using Amazon's Mechanical Turk (MTurk) platform. These respondents were surveyed regarding four psychiatric research projects (i.e., experimental medication [pill form]; non-invasive magnetic brain stimulation; experimental medication [intravenous infusion]; and implantation of a device in the brain). Regardless of health status, respondents rated the four research protocols as somewhat to highly risky. The brain-device implant protocol was seen as the most risky, while the magnetic brain stimulation project was viewed as "somewhat risky". Respondents, on average and regardless of health status, rated their willingness at or below "somewhat willing." Respondents were least willing to participate in the brain-device implant protocol, whereas they were "somewhat willing" to participate in the magnetic brain stimulation protocol. Trust in medical research was negatively associated with perceived risk of research protocols. Perceived risk was negatively associated with willingness to participate, even when adjusting for potential confounders, suggesting that attunement to risk crosses diagnostic, gender, and ethnic categories, and is more salient to research decision-making than trust in medical research and dispositional optimism. The findings of this study may offer reassurance about the underlying decision-making processes of individuals considering participation in innovative neuroscience studies.