Deconstructing self-fulfilling outcome measures in infertility treatment.

The typical outcome measure in infertility treatment is the (cumulative) healthy live birth rate per patient or per cycle. This means that those who end the treatment trajectory with a healthy baby in their arms are considered to be successful and those who do not are considered to have failed. In this article, we argue that by adopting the healthy live birth standard as the outcome measure that defines a successful fertility treatment, it becomes an interpretative self-fulfilling prophecy: those who achieve the goal consider themselves successful and those who do not consider themselves failures. This is regardless of the fact that having children is only one out of many ways to alleviate the suffering related to infertility and that stopping fertility treatment can also be a positive decision to move on to other goals, rather than a form of "giving up," "dropping out," "nonadherence," or failure. We suggest that those seeking fertility treatment would be served better by an alternative outcome measure, which can be equally self-fulfilling, according to which a successful treatment is one in which people leave the clinic released from the suffering that accompanied their status as infertile when they first entered the clinic. This new outcome measure still implies that walking out with a healthy baby is a positive outcome. What changes is that walking out without a baby can also be a positive outcome, rather than being marked exclusively as a failure.

A translational perspective towards clinical AI fairness.

Artificial intelligence (AI) has demonstrated the ability to extract insights from data, but the fairness of such data-driven insights remains a concern in high-stakes fields. Despite extensive developments, issues of AI fairness in clinical contexts have not been adequately addressed. A fair model is normally expected to perform equally across subgroups defined by sensitive variables (e.g., age, gender/sex, race/ethnicity, socio-economic status, etc.). Various fairness measurements have been developed to detect differences between subgroups as evidence of bias, and bias mitigation methods are designed to reduce the differences detected. This perspective of fairness, however, is misaligned with some key considerations in clinical contexts. The set of sensitive variables used in healthcare applications must be carefully examined for relevance and justified by clear clinical motivations. In addition, clinical AI fairness should closely investigate the ethical implications of fairness measurements (e.g., potential conflicts between group- and individual-level fairness) to select suitable and objective metrics. Generally defining AI fairness as "equality" is not necessarily reasonable in clinical settings, as differences may have clinical justifications and do not indicate biases. Instead, "equity" would be an appropriate objective of clinical AI fairness. Moreover, clinical feedback is essential to developing fair and well-performing AI models, and efforts should be made to actively involve clinicians in the process. The adaptation of AI fairness towards healthcare is not self-evident due to misalignments between technical developments and clinical considerations. Multidisciplinary collaboration between AI researchers, clinicians, and ethicists is necessary to bridge the gap and translate AI fairness into real-life benefits.

AI and machine learning in resuscitation: Ongoing research, new concepts, and key challenges.

Aim: Artificial intelligence (AI) and machine learning (ML) are important areas of computer science that have recently attracted attention for their application to medicine. However, as techniques continue to advance and become more complex, it is increasingly challenging for clinicians to stay abreast of the latest research. This overview aims to translate research concepts and potential concerns to healthcare professionals interested in applying AI and ML to resuscitation research but who are not experts in the field. Main text: We present various research including prediction models using structured and unstructured data, exploring treatment heterogeneity, reinforcement learning, language processing, and large-scale language models. These studies potentially offer valuable insights for optimizing treatment strategies and clinical workflows. However, implementing AI and ML in clinical settings presents its own set of challenges. The availability of high-quality and reliable data is crucial for developing accurate ML models. A rigorous validation process and the integration of ML into clinical practice is essential for practical implementation. We furthermore highlight the potential risks associated with self-fulfilling prophecies and feedback loops, emphasizing the importance of transparency, interpretability, and trustworthiness in AI and ML models. These issues need to be addressed in order to establish reliable and trustworthy AI and ML models. Conclusion: In this article, we overview concepts and examples of AI and ML research in the resuscitation field. Moving forward, appropriate understanding of ML and collaboration with relevant experts will be essential for researchers and clinicians to overcome the challenges and harness the full potential of AI and ML in resuscitation.

Can we learn from hidden mistakes? Self-fulfilling prophecy and responsible neuroprognostic innovation.

A self-fulfilling prophecy (SFP) in neuroprognostication occurs when a patient in coma is predicted to have a poor outcome, and life-sustaining treatment is withdrawn on the basis of that prediction, thus directly bringing about a poor outcome (viz. death) for that patient. In contrast to the predominant emphasis in the bioethics literature, we look beyond the moral issues raised by the possibility that an erroneous prediction might lead to the death of a patient who otherwise would have lived. Instead, we focus on the problematic epistemic consequences of neuroprognostic SFPs in settings where research and practice intersect. When this sort of SFP occurs, the problem is that physicians and researchers are never in a position to notice whether their original prognosis was correct or incorrect, since the patient dies anyway. Thus, SFPs keep us from discerning false positives from true positives, inhibiting proper assessment of novel prognostic tests. This epistemic problem of SFPs thus impedes learning, but ethical obligations of patient care make it difficult to avoid SFPs. We then show how the impediment to catching false positive indicators of poor outcome distorts research on novel techniques for neuroprognostication, allowing biases to persist in prognostic tests. We finally highlight a particular risk that a precautionary bias towards early withdrawal of life-sustaining treatment may be amplified. We conclude with guidelines about how researchers can mitigate the epistemic problems of SFPs, to achieve more responsible innovation of neuroprognostication for patients in coma.

Prognostication of patients in coma after cardiac arrest: Public perspectives.

AIM: To elicit preferences for prognostic information, attitudes towards withdrawal of life-sustaining treatment (WLST) and perspectives on acceptable quality of life after post-anoxic coma within the adult general population of Germany, Italy, the Netherlands and the United States of America. METHODS: A web-based survey, consisting of questions on respondent characteristics, perspectives on quality of life, communication of prognostic information, and withdrawal of life-sustaining treatment, was taken by adult respondents recruited from four countries. Statistical analysis included descriptive analysis and chi2-tests for differences between countries. RESULTS: In total, 2012 respondents completed the survey. In each country, at least 84% indicated they would prefer to receive early prognostic information. If a poor outcome was predicted with some uncertainty, 37-54% of the respondents indicated that WLST was not to be allowed. A conscious state with severe physical and cognitive impairments was perceived as acceptable quality of life by 17-44% of the respondents. Clear differences between countries exist, including respondents from the U.S. being more likely to allow WLST than respondents from Germany (OR = 1.99, p < 0.001) or the Netherlands (OR = 1.74, p < 0.001) and preferring to stay alive in a conscious state with severe physical and cognitive impairments more than respondents from Italy (OR = 3.76, p < 0.001), Germany (OR = 2.21, p < 0.001), or the Netherlands (OR = 2.39, p < 0.001). CONCLUSIONS: Over one-third of the respondents considered WLST unacceptable when there is any remaining prognostic uncertainty. Respondents had a more positive perspective on acceptable quality of life after coma than what is currently considered acceptable in medical literature. This indicates a need for a closer look at the practice of WLST based on prognostic information, to ensure responsible use of novel prognostic tests.