Mayli Mertens

Risk prediction in emergency medicine (EM) holds unique challenges due to issues surrounding urgency, blurry research-practise distinctions, and the high-pressure environment in emergency departments (ED). Artificial intelligence (AI) risk prediction tools have been developed with the aim of streamlining triaging processes and mitigating perennial issues affecting EDs globally, such as overcrowding and delays. The implementation of these tools is complicated by the potential risks associated with over-triage and under-triage, untraceable false positives, as well as the potential for the biases of healthcare professionals toward technology leading to the incorrect usage of such tools. This paper explores risk surrounding these issues in an analysis of a case study involving a machine learning triage tool called the Score for Emergency Risk Prediction (SERP) in Singapore. This tool is used for estimating mortality risk in presentation at the ED. After two successful retrospective studies demonstrating SERP’s strong predictive accuracy, researchers decided that the pre-implementation randomised controlled trial (RCT) would not be feasible due to how the tool interacts with clinical judgement, complicating the blinded arm of the trial. This led them to consider other methods of testing SERP’s real-world capabilities, such as ongoing-evaluation type studies. We discuss the outcomes of a risk–benefit analysis to argue that the proposed implementation strategy is ethically appropriate and aligns with improvement-focused and systemic approaches to implementation, especially the learning health systems framework (LHS) to ensure safety, efficacy, and ongoing learning.

This article first describes the mechanism of any self-fulfilling prophecy through discussion of its four conditions: credibility, employment, employment sensitivity, and realization. Each condition is illustrated with examples specific to the medical context. The descriptive account ends with the definition of self-fulfilling prophecy and an expansion on collective self-fulfilling prophecies. Second, the normative account then discusses the moral relevance of self-fulfilling prophecies in medicine. A self-fulfilling prophecy is typically considered problematic when the prediction itself changes the predicted outcome to match the prediction (transformative self-fulfillment). I argue that also self-fulfilling prophecies that do not change the outcome but change the ways in which the outcome was realized (operative self-fulfillment), have significant ethical and epistemic ramifications. Because it is difficult to distinguish, retrospectively, between a transformative and an operative self-fulfilling prophecy, and thus between a false or true positive, it becomes equally difficult to catch mistakes. Moreover, since the prediction necessarily turns out true, there is never an error signal warning that a mistake might have been made. On the contrary, accuracy is seen as the standard for quality assurance. As such, self-fulfilling prophecies inhibit our ability to learn, inviting repetition and exacerbation of mistakes. With the rise of automated diagnostic and prognostic procedures and the increased use of machine learning and artificial intelligence for the development of predictive algorithms, attention to self-fulfilling feedback loops is especially warranted. This account of self-fulfilling prophecies is practically relevant for medical research and clinical practice. With it, researchers and practitioners can detect and analyze potential self-fulfilling mechanisms in any medical case and take responsibility for their ethical and epistemic implications.

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 self-fulfilling prophecy is, roughly, a prediction that brings about its own truth. Although true predictions are hard to fault, self-fulfilling prophecies are often regarded with suspicion. In this article, we vindicate this suspicion by explaining what self-fulfilling prophecies are and what is problematic about them, paying special attention to how their problems are exacerbated through automated prediction. Our descriptive account of self-fulfilling prophecies articulates the four elements that define them. Based on this account, we begin our critique by showing that typical self-fulfilling prophecies arise due to mistakes about the relationship between a prediction and its object. Such mistakes—along with other mistakes in predicting or in the larger practical endeavor—are easily overlooked when the predictions turn out true. Thus we note that self-fulfilling prophecies prompt no error signals; truth shrouds their mistakes from humans and machines alike. Consequently, self-fulfilling prophecies create several obstacles to accountability for the outcomes they produce. We conclude our critique by showing how failures of accountability, and the associated failures to make corrections, explain the connection between self-fulfilling prophecies and feedback loops. By analyzing the complex relationships between accuracy and other evaluatively significant features of predictions, this article sheds light both on the special case of self-fulfilling prophecies and on the ethics of prediction more generally.

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 dierences 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.

Although the concept of Responsible Innovation (RI) has been applied to different types of innovations, three common assumptions have remained the same. First, emerging technologies require assessment because of their radical novelty and unpredictability. Second, early assessment is necessary to impact the innovation trajectory. Third, anticipation of unknowns is needed to prepare for the unpredictable. I argue that these assumptions do not hold for liminal innovation practices in clinical settings, which are defined by continuous transition on both sides of the threshold between experiment and implementation, and between research and care. First of all, technologies at the center of liminal innovation practices have different characteristics than those typically attributed to emerging technologies. Additionally, the innovation trajectory is significantly different allowing continuous assessment and shaping long after implementation. Finally, these differences demand a reorientation in RI approaches for these cases, away from anticipation of the unknown and uncertain, and returning to observation of the known and predictable.

A self-fulfilling prophecy 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 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.

When information on a coma patient’s expected outcome is uncertain, a moral dilemma arises in clinical practice: if life-sustaining treatment is continued, the patient may survive with unacceptably poor neurological prospects, but if withdrawn a patient who could have recovered may die. Continuous electroencephalogram-monitoring is expected to substantially improve neuroprognostication for patients in coma after cardiac arrest. This raises expectations that decisions whether or not to withdraw will become easier. This paper investigates that expectation, exploring cEEG’s impacts when it becomes part of a socio-technical network in an Intensive Care Unit. Based on observations in two ICUs in the Netherlands and one in the USA that had cEEG implemented for research, we interviewed 25 family members, healthcare professionals, and surviving patients. The analysis focuses on the way patient outcomes are constructed, the kind of decision support these outcomes provide, and how cEEG affects communication between professionals and relatives. We argue that cEEG can take away or decrease the intensity of the dilemma in some cases, while increasing uncertainty for others. It also raises new concerns. Since its actual impacts furthermore hinge on how cEEG is designed and implemented, we end with recommendations for ensuring responsible development and implementation.

This master thesis analyzes specific challenges concerning 'truth-telling' war reporters face when reporting on international conflict. For this purpose truth is examined in accordance with journalistic principles outlined in codes of ethics, with a focus on objectivity and fairness. The aim is to discover ways to improve the application of principles, in order to battle epistemic errors and the effects they entail: polarization, reductionism, and superficiality. The study concludes that providing context and nuance is crucial, but that codes - although essential - are insufficient in helping journalists decide what is relevant and what is not. An approach in virtue ethics is recommended where phronesis (or practical wisdom) can inspire responsible journalists to comply with the spirit, rather than the letter of the principles.