26 papers · ranked by Valyu relevance
Raymond Sheh, Isaac Monteath
Explainable Artificial Intelligence (XAI) has become popular in the last few years. The Artificial Intelligence (AI) community in general, and the Machine Learning (ML) community in particular, is coming to the realisation that in many applications, for AI to be trusted, it must not only demonstrate good performance in…
Giovanni Cinà, Tabea E. Röber, Rob Goedhart, Ş. İlker Birbil
The recent uptake in certified Artificial Intelligence (AI) tools for healthcare applications has renewed the debate around their adoption. Explainable AI, the sub-discipline promising to render AI devices more transparent and trustworthy, has also come under scrutiny as part of this discussion. Some experts in the…
Matteo Rizzo, Alberto Veneri, Matteo Marcuzzo, Alessandro Zangari + 4 more
Explainable Artificial Intelligence, or XAI, is a vibrant research topic in the artificial intelligence community. It is raising growing interest across methods and domains, especially those involving high-stakes decision-making, such as the biomedical sector. Much has been written about the subject, yet XAI still…
Oana Geman, Sara Sharghilavan, Hadi Abbasi, Roxana Toderean + 3 more
The main challenges in the life of a child with autism are difficulties in communication, behavior, and social interaction. Early diagnosis of this neurodevelopmental disorder improves patient outcomes by enabling more effective, personalized interventions. This diagnosis can sometimes be difficult, especially in very…
Miguel A. Lago, Ghada Zamzmi, Brandon Eich, Jana G. Delfino + 2 more
Explainability features are intended to provide insight into the internal mechanisms of an Artificial Intelligence (AI) device, but there is a lack of evaluation techniques for assessing the quality of provided explanations. We propose a framework to assess and report explainable AI features in medical images. Our…
Gourab K Patro, Himanshi Agrawal, Himanshu Gharat, Supriya Panigrahi + 3 more
Modern general-purpose AI systems made using large language and vision models, are capable of performing a range of tasks like writing text articles, generating and debugging codes, querying databases, and translating from one language to another, which has made them quite popular across industries. However, there are…
Fabio Morreale, Joan Serrà, Yuki Mistufuji
Explainable AI (XAI) is frequently positioned as a technical problem of revealing the inner workings of an AI model. This position is affected by unexamined onto-epistemological assumptions: meaning is treated as immanent to the model, the explainer is positioned outside the system, and a causal structure is presumed…
Catharina Margaretha van Leersum, George Demiris
In view of research on XAI, computer scientist Tim Miller argues that creating an AI system explaining itself and its decision-making process seems impossible. To underline this statement, ) uses a quote from AI researcher Geoff Hinton, who argues that people also cannot explain how they work because decisions are…
Niharika Mathur, Smit Desai
As AI systems become increasingly conversational, a gap emerges wherein explanations are studied as static artifacts, yet in practice, are experienced as dialogue. In this provocation, we argue that the conversational layer around an explanation is not incidental to its effectiveness, but a critical constituent.…
Mohamed Ebraheem, Jamie Toghranegar, Yael Bensoussan, John Michael Templeton + 1 more
Background Driven by recent advances in artificial intelligence (AI), particularly in medicine, audio-based voice and speech biomarkers are increasingly investigated for various medical applications as a complementary or even alternative modality to traditional medical devices. The adoption of deep learning techniques…
Michal Moshkovitz, Suraj Srinivas, Lesia Semenova, Nave Frost + 6 more
Despite the proliferation of Explainable AI (XAI) techniques -- from feature attributions to sparse autoencoders -- explanations rarely influence real-world workflows. In practice, they are often generated and discarded without guiding meaningful action. This gap reflects foundational shortcomings: research has not yet…
Daniil Lisik, Tai Dinh, Ding Zou
Rapid advancements in artificial intelligence (AI), in combination with increased availability of rich large-scale clinical data, has paved the way for promising implementations in both diagnosing/subtyping as well as managing of sleep disordered breathing (SDB). A central strength of AI in this regard is how it…
Nadeesha Hettikankanamage, Niusha Shafiabady, Fiona Chatteur, Robert M. X. Wu + 3 more
Artificial Intelligence (AI) has achieved immense progress in recent years across a wide array of application domains, with biomedical imaging and sensing emerging as particularly impactful areas. However, the integration of AI in safety-critical fields, particularly biomedical domains, continues to face a major…
David Martínez-Enguita, Thomas Hillerton, Julia Åkesson, Maria Lerm + 1 more
Genome-scale DNA methylation (DNAm) profiles capture organismal physiology, but most predictive models lack transparency and multi-level applicability. Here we develop an explainable framework that quantifies respiratory, cardiovascular, and metabolic status as bounded health scores (0–1) derived from sex-specific…
Eléonore Houdoyer, Solène Le Bars, Valérian Chambon
Automation has been shown to weaken the sense of agency (SoA), the experience of controlling one’s actions and their outcomes, by disrupting the predictive link between intention and effect. Explainable AI (XAI) has been proposed as a solution, yet the neurocognitive mechanisms through which explanations restore agency…
Jerzy Stefanowski
This paper addresses the limitations of Explainable Artificial Intelligence (XAI) with respect to insufficient evaluation. They are illustrated through the DetoxAI image recognition system for bias detection and concept unlearning. Then, an example of a human-grounded evaluation of methods for explaining image…
Khizra Maqsood, Duarte Polvora Brandao, Jareth Wolfe, Bhavana Kayyar + 9 more
Enhancers are non-coding regions of DNA that regulate gene transcription, yet the mechanisms underlying enhancer activity remain incompletely understood. Despite extensive experimental and computational efforts, we still lack accurate enhancer maps in many human cells, tissues and disease contexts. Here, we developed…
Authors not listed
Artificial intelligence (AI) is reshaping chemical engineering. Still, its role in safety-critical operations is limited because we rarely see tools that link physical models with data-driven methods. This study brings together three elements: physics-constrained neural networks, uncertainty quantification, and a…
Arno Leue, Akhila Bairy, Maike Schwammberger
Autonomous and software-intensive systems have been growing in occurrence, complexity, and assumed responsibility. Due to the high complexity of these systems, properties like transparency and explainability must be a focus of investigation. To date, no universally applicable definition and guide for the development of…
Authors not listed
Predicting drug-induced toxicity remains a central challenge in computational toxicology, particularly for organ-specific adverse effects that arise from diverse structural, biochemical, and mechanistic origins. Existing deep learning models excel at pattern recognition but often lack mechanistic interpretability…
Vedant Parikh, Brandon Foley, Will Gatlin, Max Ludwick + 2 more
Artificial intelligence (AI) has transformed prediction of protein structure and biomolecular interactions, yet modeling of allosteric regulation remains a persistent and unresolved challenge. We develop a dual explainable AI framework that systematically interrogates AI Co-Folding models AlphaFold3, Protenix, Boltz-2…
Wenbo Wang, Simran Swain, Jaeyong Lee, Zuwan Lin + 10 more
Reproducibility in biological research and manufacturing remains constrained by the complexity of multi-step protocols, fragmented data-analysis pipelines, and the intrinsic variability of experimental execution. Here, we present Agentic Lab, an agentic-physical AI platform that unifies large language model and vision…
Authors not listed
The value of generative artificial intelligence (AI) for teaching and learning is currently hotly debated. Concerns regarding the accuracy of information produced by generative AI as well as student over-reliance on this tool coexist with excitement about tailored opportunities that AI may provide for educational…
Authors not listed
Bayesian optimization (BO) has become increasingly important for experimental optimization across scientific domains, yet implementing BO pipelines requires significant programming expertise and familiarity with specialized frameworks. This creates a barrier for domain experts who could benefit from BO but lack the…
Authors not listed
As the utilization of artificial intelligence (AI) and generative AI (GenAI) is expanding in the educational field, presenting significant implications for STEM disciplines, it is bringing opportunities to enhance how chemistry and chemical engineering are taught and learned. This perspective critically explores the…
Authors not listed
This paper addresses the challenge of decarbonizing global energy systems by proposing the Shibah Integrated Bio-Electro-AI CCUS-H2 Framework, a multidisciplinary approach that combines hydrogen production, storage, and utilization with carbon capture, utilization, and storage (CCUS). The framework tackles high costs…