An official website of the United States government
Patients resuscitated from cardiac arrest who enter a coma are at high risk of death. Forecasting neurological outcomes of these patients (i.e., the task of neurological prognostication) could help with treatment decisions: which patients are likely to awaken from their coma and should be kept on life-sustaining therapies, and which are so ill that they would unlikely benefit from treatment? In this paper, we propose, to the best of our knowledge, the first dynamic framework for neurological prognostication of post-cardiac-arrest comatose patients using EEG data: our framework makes predictions for a patient over time as more EEG data become available, and different training patients’ available EEG time series could vary in length. Predictions themselves are phrased in terms of either time-to-event outcomes (time-to-awakening or time-to-death) or as the patient’s probability of awakening or of dying across multiple time horizons (e.g., within the next 24, 48, or 72 hours). Our framework is based on using any dynamic survival analysis model that supports competing risks in the form of estimating patient-level cumulative incidence functions. We consider three competing risks as to what happens first to a patient: awakening, being withdrawn from life-sustaining therapies (and thus deterministically dying), or dying (by other causes). For some patients, we do not know which of these happened first since they were still in a coma when data collection stopped (i.e., their outcome is censored). Competing risks models readily accommodate such patients. We demonstrate our framework by benchmarking three existing dynamic survival analysis models that support competing risks on a real dataset of 922 post-cardiac-arrest coma patients. Our main experimental findings are that: (1) the classical Fine and Gray model which only uses a patient’s static features and summary statistics from the patient’s latest hour’s worth of EEG data is highly competitive, achieving accuracy scores as high as the recently developed Dynamic-DeepHit model that uses substantially more of the patient’s EEG data; and (2) in an ablation study, we show that our choice of modeling three competing risks results in a model that is at least as accurate while learning more information than simpler models (using two competing risks or a standard survival analysis setup with no competing risks).
more »
« less
This content will become publicly available on December 20, 2025
Confronting risks of mirror life
All known life is homochiral. DNA and RNA are made from “righthanded” nucleotides, and proteins are made from “left-handed” amino acids. Driven by curiosity and plausible applications, some researchers had begun work toward creating lifeforms composed entirely of mirror-image biological molecules. Such mirror organisms would constitute a radical departure from known life, and their creation warrants careful consideration. The capability to create mirror life is likely at least a decade away and would require large investments and major technical advances; we thus have an opportunity to consider and preempt risks before they are realized. Here, we draw on an indepth analysis of current technical barriers, how they might be eroded by technological progress, and what we deem to be unprecedented and largely overlooked risks. We call for broader discussion among the global research community, policy-makers, research funders, industry, civil society, and the public to chart an appropriate path forward.
more »
« less
- PAR ID:
- 10591160
- Author(s) / Creator(s):
- ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; more »
- Publisher / Repository:
- Science
- Date Published:
- Journal Name:
- Science
- Volume:
- 386
- Issue:
- 6728
- ISSN:
- 0036-8075
- Page Range / eLocation ID:
- 1351 to 1353
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This research is motivated by the need for students’ early exposure to work readiness skills that promote effectiveness in dealing with complex open-ended technical problems as may be encountered in senior capstone projects or professional practice. This paper presents preliminary work in the use of building Rube Goldberg machines as student projects to foster some of these skills. Design of Rube Goldberg machines may be employed in a number of settings as a vehicle for teaching basic engineering skills. These designs require students to creatively consider a variety of unconventional approaches to solve simple problems. The Rube Goldberg paradigm allows students to communicate and to advance their ideas in a low-pressure environment where brainstorming is highly valued and where prior technical expertise affords no specific advantage. As such, projects based on Rube Goldberg machines are an effective way for freshmen and sophomore students, who may lack extensive technical skills, to acquire greater proficiency in some of the non-technical skills. This research gives results from a pilot study in project management using the Rube Goldberg model. The goal of this study is to determine the perceived efficacy of a proposed teaching vehicle for project management concepts that could strengthen the early stages of an existing series of Project Based Learning (PBL) oriented undergraduate engineering courses at the host institution, which currently make use of more closed-ended and single-solution design projects. In the study, a cohort of 27 engineering and engineering technology students participated in a sequence of extracurricular sessions in which they undertook progressively challenging open-ended project assignments. Each project introduced new constraints that required the students to address additional aspects of project management. Results from an end-of-year survey show that the participants had strongly positive impressions of their experiences related to these exercises. A majority of students felt that they had enhanced skills that would be valuable in professional life (96%), improved their leadership skills (92%), and had gained appreciation for the value of project planning (100%) and technical documentation (96%). It is anticipated that lessons learned from the project sequence will provide the framework for cross-disciplinary freshman and sophomore assignments in host institution’s PBL curriculum in the future.more » « less
-
Human-designed systems are increasingly leveraged by data-driven methods and artificial intelligence. This leads to an urgent need for responsible design and ethical use. The goal of this conceptual paper is two-fold. First, we will introduce the Framework for Design Reasoning in Data Life-cycle Ethical Management, which integrates three existing frameworks: 1) the design reasoning quadrants framework (representing engineering design research), and 2) the data life-cycle model (representing data management), and 3) the reflexive principles framework (representing ethical decision-making). The integration of three critical components of the framework (design reasoning, data reasoning, and ethical reasoning) is accomplished by centering on the conscientious negotiation of design risks and benefits. Second, we will present an example of a student design project report to demonstrate how this framework guides educators towards delineating and integrating data reasoning, ethical reasoning, and design reasoning in settings where ethical issues (e.g., AI solutions) are commonly experienced. The framework can be implemented to design courses through design review conversations that seamlessly integrate ethical reasoning into the technical and data decision-making processes.more » « less
-
Abstract Damage and disruption from flooding have rapidly escalated over recent decades. Knowing who and what is at risk, how these risks are changing, and what is driving these changes is of immense importance to flood management and policy. Accurate predictions of flood risk are also critical to public safety. However, many high‐profile research studies reporting risks at national and global scales rely upon a significant oversimplification of how floods behave—as a level pool—an approach known as bathtub modeling that is avoided in flood management practice due to known biases (e.g., >200% error in flood area) compared to physics‐based modeling. With publicity by news media, findings that would likely not be trusted by flood management professionals are thus widely communicated to policy makers and the public, scientific credibility is put at risk, and maladaptation becomes more likely. Here, we call upon researchers to abandon the practice of bathtub modeling in flood risk studies, and for those involved in the peer‐review process to ensure the conclusions of impact analyses are consistent with the limitations of the assumed flood physics. We document biases and uncertainties from bathtub modeling in both coastal and inland geographies, and we present examples of physics‐based modeling approaches suited to large‐scale applications. Reducing biases and uncertainties in flood hazard estimates will sharpen scientific understanding of changing risks, better serve the needs of policy makers, enable news media to more objectively report present and future risks to the public, and better inform adaptation planning.more » « less
-
In this paper, we extend the non-Abelian mirror proposal of two of the authors from two-dimensional gauge theories with connected gauge groups to the case of [Formula: see text] gauge groups with discrete theta angles. We check our proposed extension by counting and comparing vacua in mirrors to the known dual two-dimensional [Formula: see text] gauge theories. The mirrors in question are Landau–Ginzburg orbifolds, and for mirrors to [Formula: see text] gauge theories, the critical loci of the mirror superpotential often intersect fixed-point loci, so that to count vacua, one must take into account the twisted sector contributions. This is a technical novelty relative to the mirrors of gauge theories with connected gauge groups, for which critical loci do not intersect fixed-point loci and so no orbifold twisted sector contributions are pertinent. The vacuum computations turn out to be a rather intricate test of the proposed mirrors, in particular as untwisted sector states in the mirror to one theory are often exchanged with twisted sector states in the mirror to the dual. In cases with nontrivial IR limits, we also check that the central charges computed from the Landau–Ginzburg mirrors match those expected for the IR SCFTs.more » « less
