Category: Sector: Health

Hard Questions: Health

  • Call for Book Chapters: OUR AI PROBLEMS

    Call for Book Chapters: OUR AI PROBLEMS

    Call for Book Chapters: Our AI Problems (Edited Volume)

    We believe that there are no easy answers when it comes to artificial intelligence and society. Across jurisdictions and decision-making bodies, those who develop or enforce regulations are confronted with difficult questions. These challenges arise for many reasons: the issues are often embedded in complex sociotechnical systems, lack straightforward solutions, or involve tensions between competing values and needs.

    The editors hold that AI can be of great service for humanity. At the same time, current regulatory frameworks lag far behind what is needed to ensure just, safe, and equitable access and outcomes. 

    Policymakers and subject-matter specialists are increasingly converging on a shared set of especially challenging issues.  Society is learning to join in the conversations. Accordingly, the proposed volume is envisioned as addressing the following areas: Economics and Power; Democracy and Trust; Risks Large and Small; Building Bridges and Inclusion; Media and Art; Environment and Health; Justice, Security, and Defense.

    If you are interested in contributing, we would be delighted to hear from you. If you know colleagues or collaborators who might wish to participate, please feel free to share this call with them as well.

    Deadline for chapter abstracts (250–300 words): 15 January 2026
    Deadline for chapter draft submission (8000–10,000 words; US English; APA style): 31 March 2026
    Deadline for final revisions: 15 May 2026

    Edited by Tammy Mackenzie, Ashley Elizabeth Muller, and Branislav Radeljić

    For more info about the editors, please see: Fellows
    Submissions and questions: Contact Branislav Radeljić, Ph.D., Director of Research.

  • Three Fellow’s Works in Nature this Year

    Three Fellow’s Works in Nature this Year

    We are proud to announce that Fellows were published 3 times in Nature this year. So far! We are very proud to be connecting people to the conversation in these ways. Thanks for your work, Fellows Jake Okechukwu Effoduh and Peer Herholz!

    Here are the works in question:

    Nature: Opinion: The path for AI in poor nations does not need to be paved with billions

    Nature: Scientific Data: A labeled clinical-MRI dataset of Nigerian brains

    Nature: Communications: Trainees’ perspectives and recommendations for catalyzing the next generation of NeuroAI researchers

  • Tackling AI Transparency Concerns in Biomedical Research: Bringing a Communication-Participatory Approach to the Conversation

    Tackling AI Transparency Concerns in Biomedical Research: Bringing a Communication-Participatory Approach to the Conversation

    Announcement by Leslie Salgado: “Happy to announce that my book chapter “Tackling AI Transparency Concerns in Biomedical Research: Bringing a Communication-Participatory Approach to the Conversation” is now published as part of the book “Artificial Intelligence in Biobanking. Ethical, Legal and Societal Challenges.” In my chapter, I address questions concerning transparency, explainability and interpretability from a communication-participatory stance. ” Congratulations, Leslie, and thanks for your work!

    Read it at Routledge

  • PARADIM: A Platform to Support Research at the Interface of Data Science and Medical Imaging

    PARADIM: A Platform to Support Research at the Interface of Data Science and Medical Imaging

    This paper describes PARADIM, a digital infrastructure designed to support research at the interface of data science and medical imaging, with a focus on Research Data Management best practices. The platform is built from open-source components and rooted in the FAIR principles through strict compliance with the DICOM standard. It addresses key needs in data curation, governance, privacy, and scalable resource management. Supporting every stage of the data science discovery cycle, the platform offers robust functionalities for user identity and access management, data de-identification, storage, annotation, as well as model training and evaluation. Rich metadata are generated all along the research lifecycle to ensure the traceability and reproducibility of results. PARADIM hosts several medical image collections and allows the automation of large-scale, computationally intensive pipelines (e.g., automatic segmentation, dose calculations, AI model evaluation). The platform fills a gap at the interface of data science and medical imaging, where digital infrastructures are key in the development, evaluation, and deployment of innovative solutions in the real world.

    More Information

  • A labeled clinical-MRI dataset of Nigerian brains

    A labeled clinical-MRI dataset of Nigerian brains

    There is currently a paucity of neuroimaging data from the African continent, limiting the diversity of data from a significant proportion of the global population. This in turn diminishes global health research and innovation. To address this issue, we present and describe the first Magnetic Resonance Imaging (MRI) dataset from individuals in the African nation of Nigeria. This dataset contains pseudonymized structural MRI (T1w, T2w, FLAIR) data of clinical quality, with 35 images from healthy control subjects, 31 images from individuals diagnosed with age-related dementia, and 22 from individuals with Parkinson’s Disease. Given the potential for Africa to contribute to the global neuroscience community, this unique MRI dataset represents both an opportunity and benchmark for future studies to share data from the African continent.

    More Information

  • Trainees’ perspectives and recommendations for catalyzing the next generation of NeuroAI researchers

    Trainees’ perspectives and recommendations for catalyzing the next generation of NeuroAI researchers

    At this critical juncture in the development of NeuroAI, we outline challenges and training needs of junior researchers working across AI and neuroscience. We also provide advice and resources to help trainees plan their NeuroAI careers.

    More Information

  • From Crisis Management to the crisis of management: Accountability and Liberal Democracies in the Outbreak of the Covid-19 Pandemic

    From Crisis Management to the crisis of management: Accountability and Liberal Democracies in the Outbreak of the Covid-19 Pandemic

    The outbreak of the COVID-19 pandemic shocked societies around the world. In their efforts to tailor their responses to the crisis to their own conditions for survival, from the outset governments tended to resort to arguments that limited accountability before their populations. Liberal democracies were no exception to this approach. In this context, their leaders used the metaphor of war to describe their position as guarantors of the population’s survival in the face of the new threat. Caught between uncertainty and the need to predict the nature and evolution of the invisible enemy, their responses called into question the political, professional and personal responsibility of leaders. This article offers a reflection on the level of responsibility of governments in liberal democracies in managing the pandemic. During the crisis, decision-makers tended to be driven by the narratives that were most beneficial to them in order to escape their responsibilities, thereby underpinning their short-term political needs through the use of bellicose metaphors, the blame game, competition with other countries, and the dispersion of sources in the decision-making process. This reality now calls for reflection by social actors, including experts, intellectuals and the media, to transcend the prevailing rhetoric in management of the pandemic and the “new normal” that followed, so that the dynamics of constant alterations in the rules of the game and responsibilities can give way, in the future, to a scenario with less arbitrariness and more accountability.

    More Information

  • De la gestión de crisis a la crisis de gestión: Responsabilidad y democracias liberales en el estallido de la pandemia de la COVID-19

    De la gestión de crisis a la crisis de gestión: Responsabilidad y democracias liberales en el estallido de la pandemia de la COVID-19

    El estallido de la pandemia de la COVID-19 conmocionó a las sociedades de todo el mundo. En su esfuerzo por adaptar sus respuestas a la crisis a sus propias condiciones de supervivencia, los gobiernos tendieron desde el principio a recurrir a argumentos que limitaban la rendición de cuentas frente a la población. Las democracias liberales no fueron ajenas a esta forma de abordar el problema. En ese contexto, sus dirigentes esgrimieron la metáfora de la guerra para describir su posición como garantes de la supervivencia de la población frente a la nueva amenaza. Atenazados entre la incertidumbre y la necesidad de predecir la naturaleza y la evolución del enemigo invisible, sus respuestas pusieron en entredicho la responsabilidad política, profesional y personal de los dirigentes. En este artículo se ofrece una reflexión sobre el nivel de responsabilidad de los gobiernos de las democracias liberales en la gestión de la pandemia. Durante la crisis, los decisores tendieron a dejarse llevar por las narrativas que les resultaban más beneficiosas para escabullirse de sus responsabilidades, apuntalando así sus necesidades políticas a corto plazo a través del uso de metáforas belicistas, el juego de culpas, la competición con otros países y la dispersión de las fuentes en el proceso de toma de decisiones. Esta realidad supone hoy un llamado a la reflexión a los actores sociales, incluidos los expertos, intelectuales y medios de comunicación, para trascender la retórica predominante en la gestión de la pandemia y la “nueva normalidad” que le siguió, de manera que la dinámica de alteraciones constantes de las reglas del juego y las responsabilidades pueda dar paso, en el futuro, a un escenario con menos arbitrariedad y más rendición de cuentas.

    More Information

  • Parameter efficient fine tuning: A comprehensive analysis across applications

    Parameter efficient fine tuning: A comprehensive analysis across applications

    The rise of deep learning has marked significant progress in fields such as computer vision, natural language processing, and medical imaging, primarily through the adaptation of pre-trained models for specific tasks. Traditional fine-tuning methods, involving adjustments to all parameters, face challenges due to high computational and memory demands. This has led to the development of Parameter Efficient Fine-Tuning (PEFT) techniques, which selectively update parameters to balance computational efficiency with performance. This review examines PEFT approaches, offering a detailed comparison of various strategies highlighting applications across different domains, including text generation, medical imaging, protein modeling, and speech synthesis. By assessing the effectiveness of PEFT methods in reducing computational load, speeding up training, and lowering memory usage, this paper contributes to making deep learning more accessible and adaptable, facilitating its wider application and encouraging innovation in model optimization. Ultimately, the paper aims to contribute towards insights into PEFT’s evolving landscape, guiding researchers and practitioners in overcoming the limitations of conventional fine-tuning approaches.

    More Information

  • BrainStat: A toolbox for brain-wide statistics and multimodal feature associations

    BrainStat: A toolbox for brain-wide statistics and multimodal feature associations

    Analysis and interpretation of neuroimaging datasets has become a multidisciplinary endeavor, relying not only on statistical methods, but increasingly on associations with respect to other brain-derived features such as gene expression, histological data, and functional as well as cognitive architectures. Here, we introduce BrainStat – a toolbox for (i) univariate and multivariate linear models in volumetric and surface-based brain imaging datasets, and (ii) multidomain feature association of results with respect to spatial maps of post-mortem gene expression and histology, task-based fMRI meta-analysis, as well as resting-state fMRI motifs across several common surface templates. The combination of statistics and feature associations into a turnkey toolbox streamlines analytical processes and accelerates cross-modal research. The toolbox is implemented in both Python and MATLAB, two widely used programming languages in the neuroimaging and neuroinformatics communities. BrainStat is openly available and complemented by an expandable documentation.

    More Information

  • fMRIflows: A Consortium of Fully Automatic Univariate and Multivariate fMRI Processing Pipelines

    fMRIflows: A Consortium of Fully Automatic Univariate and Multivariate fMRI Processing Pipelines

    One of the most significant current discussions in the understanding of the human brain is the functional recruitment of some regions of the cortex for specific tasks, regardless of the sensory modality (e.g. visual, tactile or auditory) in which the stimuli is received. The ability to perceive motion, among other visual properties, is a fundamental faculty of the human brain. Brain lesions that impair the detection and processing of motion have a profound impact on daily activity. Consequently, visual motion processing is one of the most fundamental and well-studied systems in the human brain, canonically known to develop mainly for the purpose of visual perception. A great deal of study on the multisensory responses to motion processing in the human brain focused on the middle temporal complex and superior temporal sulcus. Several studies using both neurophysiological and neuroimaging techniques showed the multisensory properties of these areas, showing their recruitment during both tactile and auditory motion stimulation. Despite the large amount of study on the topic it is still unclear whether the recruitment of these areas directly mediates the perception of motion through the different sensory input or regulates responses within primary sensory areas involved in the task. This MSCA fellowship allowed me to lay the foundations on the neural substrate underlying multisensory motion perception. We discovered that hMT+, an area mainly involved in visual motion processing, encode motion via spatial features of the stimulation rather than its intrinsic speed and our preliminary results show that, together with other visual areas, is able to decode speed via auditory and tactile motion stimulation, proving its multisensory function.

    More Information

  • The missing voices at AI conferences

    The missing voices at AI conferences

    Policymaking should be a society-wide effort, including elected officials, government employees, academics, business leaders, civil society groups and individuals. In theory, each of us should be able to participate.

    More Information