Field Of Artificial Intelligence Research Articles

Algorithm-Based Clinical Decision Support: Evolving Regulatory Landscape and Best Practices for Local Oversight

The potential of algorithm-based clinical decision support (CDS) in healthcare continues to increase with the growing field of artificial intelligence (AI)-enabled CDS. The use of these technologies to support clinicians, patients, and health systems is still quite new, and to date, implementors and regulators are still identifying the best processes and practices to ensure the effective, safe, and equitable use of these technology solutions. To assist individuals and organizations interested in implementation of algorithm-based CDS and AI-enabled CDS in healthcare, this article reviews the important regulatory decisions that form the landscape within which algorithm-based CDS has emerged, modern governance frameworks used to oversee these CDS systems, nuances in evaluation and monitoring throughout the CDS life cycle, best practices for real-world implementation, safety and equity considerations, and avenues for future collaboration and innovation.

Educating the Next Generation of Ethical AI Practitioners

Artificial intelligence (AI) technologies are rapidly advancing, increasing concerns about data privacy harms in AI models. We discuss how ethical AI can be incorporated into computer science curricula. This paper describes the design process for the first ‘AI Privacy Engineering’ course, to the best of our knowledge, taught in the United States. The course is designed for both undergraduate and graduate students at Georgia Tech. Throughout this course, students examine ethical implications of AI system design, development, deployment, and utilization, using the ACM’s General Ethical Principles as an ethical framework. Recognizing that data privacy represents only one possible form of harm, the course blends theoretical and conceptual lectures with hands-on projects that require students to address ethical issues, including bias, fairness, and accountability in AI systems. Herein, we discuss the course design process, including selecting the appropriate body of knowledge, establishing learning objectives, creating assignments, and considering pedagogical methodologies we employed. We explain the empirical methods used to inform our design, including a systematic review of courses teaching AI development at over 40 universities. Our structured curriculum can be used to effectively teach ethical and safe AI, and we propose how these topics may be incorporated more broadly into computer science courses. Finally, we discuss early successes and the challenges faced while teaching the course, particularly in maintaining relevance despite fast-paced changes in the field of AI, an evolving legislative landscape, accessing computational systems to run AI models, and varying levels of student preparedness.

An Overview of Artificial Intelligence in Gynaecological Pathology Diagnostics

Background: The advent of artificial intelligence (AI) has revolutionised many fields in healthcare. More recently, it has garnered interest in terms of its potential applications in histopathology, where algorithms are increasingly being explored as adjunct technologies that can support pathologists in diagnosis, molecular typing and prognostication. While many research endeavours have focused on solid tumours, gynaecological malignancies have nevertheless been relatively overlooked. The aim of this review was therefore to provide a summary of the status quo in the field of AI in gynaecological pathology by encompassing malignancies throughout the entirety of the female reproductive tract rather than focusing on individual cancers. Methods: This narrative/scoping review explores the potential application of AI in whole slide image analysis in gynaecological histopathology, drawing on both findings from the research setting (where such technologies largely remain confined), and highlights any findings and/or applications identified and developed in other cancers that could be translated to this arena. Results: A particular focus is given to ovarian, endometrial, cervical and vulval/vaginal tumours. This review discusses different algorithms, their performance and potential applications. Conclusions: The effective application of AI tools is only possible through multidisciplinary co-operation and training.

HiTrace: Hierarchical Class Tracing Approach for Open-Set Recognition on Skin Lesions.

In the constantly evolving field of artificial intelligence (AI), identifying unknown or novel classes, known as Open-set Recognition (OSR), is critical for ensuring the reliability of AI models in various applications, especially in the vital field of medical diagnostics. This study introduces a novel approach to advance OSR through the proposed hierarchical class tracing approach, HiTrace, for skin lesion classification. HiTrace incorporates three key components that tackle the complex challenges in OSR: the Hierarchy-Aware Prototype (HAP) learning for an efficient training strategy, the Distribution Enhancement (DE) module for optimized post-processing feature adjustment, and the Potential Class Tracing Algorithm (PCTA) for a hierarchical classification decision-making process. HiTrace leverages a hierarchical taxonomy to simplify the identification of new skin conditions, reducing the need for extensive manual annotation and addressing the limitations of existing methods. This study also introduces two novel evaluation metrics, the Hierarchical Open-set Classification Score (HOC-Score) and Major-Type Accuracy for Open-set samples (MTACC-O), which provide robust criteria for assessing a model's performance in classifying closed-set, in-taxonomy, and out-of-taxonomy results. Notably, the experimental results demonstrate significant advancements in the PAD-UFES-20 and ISIC 2019 datasets, with relative improvements of 15.3% and 21.1% in HOC-Score and 12.3% and 5.8% in MTACC-O, respectively, without compromising on competitive closed-set performance. To the best of our knowledge, this is the first study to present a three-stage analysis (i.e., closed-set, in-taxonomy, and out-of-taxonomy classification results) of OSR applied to a practical medical field. This comprehensive approach represents an influential stride in enhancing patient care through the early detection and treatment of skin diseases, paving the way for future research and development in medical diagnostics and beyond.

Quantum dot-based memristors for information processing and artificial intelligence applications.

Traditional computing systems struggle to keep pace with the development of artificial intelligence, as well as the development of the economy and continuous innovation in science and technology. Therefore, there is an urgent need for a new generation of powerful yet low-power computing technologies to replace them. Quantum dots have been incorporated into memristors due to their unique electrical properties, and the development of quantum dot memristors is expected to solve the problems faced by traditional memristors, including cycle stability, high energy consumption, and conductivity uniformity. This article reviews the research progress of quantum dot memristors and their simulation applications in artificial synapses. It summarizes some of the current challenges faced in the development of quantum dot memristors and discusses the potential future applications of these memristors in the field of artificial intelligence.

Rectified Lagrangian for Out-of-Distribution Detection in Modern Hopfield Networks

Modern Hopfield networks (MHNs) have recently gained significant attention in the field of artificial intelligence because they can store and retrieve a large set of patterns with an exponentially large memory capacity. A MHN is generally a dynamical system defined with Lagrangians of memory and feature neurons,where memories associated with in-distribution (ID) samples are represented by attractors in the feature space. One major problem in existing MHNs lies in managing out-of-distribution (OOD) samples because it was originally assumed that all samples are ID samples. To address this, we propose the rectified Lagrangian (RegLag), a new Lagrangian for memory neurons that explicitly incorporates an attractor for OOD samples in the dynamical system of MHNs. RecLag creates a trivial point attractor for any interaction matrix, enabling OOD detection by identifying samples that fall into this attractor as OOD. The interaction matrix is optimized so that the probability densities can be estimated to identify ID/OOD. We demonstrate the effectiveness of RecLag-based MHNs compared to energy-based OOD detection methods, including those using state-of-the-art Hopfield energies, across nine image datasets.

M²N: A Progressive Macro-to-Micro 3D Modeling Scheme for Unveiling Drug-Target Affinity

Accurate drug-target affinity (DTA) prediction holds significant potential in the field of artificial intelligence (AI)-based drug discovery. However, existing methods primarily operate at a single scale, specifically at the macro (residue) scale for target proteins and the micro (atom) scale for drugs, which limits their ability to provide information at micro (atom) scale for targets and macro (functional group, FG) scale for drugs. This limitation hinders a comprehensive understanding of the binding patterns and properties of drug-target pairs. In this paper, we propose a progressive Macro-to-Micro 3D Modeling Network (M²N) that enables macro (residue/FG) to micro (atom) scale unified modeling, termed cross-scale, to predict DTA. Specifically, M²N operates drugs by learning their chemical properties and structural characteristics from a 3D FG graph to a 3D atom graph. Correspondingly, M²N encodes proteins from a 3D residue graph to a 3D atom graph to exploit their sequence, evolutionary, and geometric representations. Such cross-scale 3D modeling scheme allows for coarse-to-fine embedding optimization, followed by an adaptive fusion module to dynamically integrate the refined features by end-to-end learning. Extensive experiments on two datasets indicate that M²N not only outperforms state-of-the-art methods under various conditions, but also provides a new paradigm for target and drug unified modeling.

A Syntactic Approach to Computing Complete and Sound Abstraction in the Situation Calculus

Abstraction is an important and useful concept in the field of artificial intelligence. To the best of our knowledge, there is no syntactic method to compute a sound and complete abstraction from a given low-level basic action theory and a refinement mapping. This paper aims to address this issue. To this end, we first present a variant of situation calculus, namely linear integer situation calculus, which serves as the formalization of high-level basic action theory. We then migrate Banihashemi, De Giacomo, and Lesperance’s abstraction framework to one from linear integer situation calculus to extended situation calculus. Furthermore, we identify a class of Golog programs, namely guarded actions, so as to restrict low-level Golog programs, and impose some restrictions on refinement mappings. Finally, we design a syntactic approach to computing a sound and complete abstraction from a low-level basic action theory and a restricted refinement mapping.

A Survey of Reasoning with Foundation Models: Concepts, Methodologies, and Outlook

Reasoning, a crucial ability for complex problem-solving, plays a pivotal role in various real-world settings such as negotiation, medical diagnosis, and criminal investigation. It serves as a fundamental methodology in the field of Artificial General Intelligence (AGI). With the ongoing development of foundation models, there is a growing interest in exploring their abilities in reasoning tasks. In this paper, we introduce seminal foundation models proposed or adaptable for reasoning, highlighting the latest advancements in various reasoning tasks, methods, and benchmarks. We then delve into the potential future directions behind the emergence of reasoning abilities within foundation models. We also discuss the relevance of multimodal learning, autonomous agents, and super alignment in the context of reasoning. By discussing these future research directions, we hope to inspire researchers in their exploration of this field, stimulate further advancements in reasoning with foundation models, e.g. Large Language Models (LLMs), and contribute to the development of AGI.

REPEAT: Improving Uncertainty Estimation in Representation Learning Explainability

Incorporating uncertainty is crucial to provide trustworthy explanations of deep learning models. Recent works have demonstrated how uncertainty modeling can be particularly important in the unsupervised field of representation learning explainable artificial intelligence (R-XAI). Current R-XAI methods provide uncertainty by measuring variability in the importance score. However, they fail to provide meaningful estimates of whether a pixel is certainly important or not. In this work, we propose a new R-XAI method called REPEAT that addresses the key question of whether or not a pixel is certainly important. REPEAT leverages the stochasticity of current R-XAI methods to produce multiple estimates of importance, thus considering each pixel in an image as a Bernoulli random variable that is either important or unimportant. From these Bernoulli random variables we can directly estimate the importance of a pixel and its associated certainty, thus enabling users to determine certainty in pixel importance. Our extensive evaluation shows that REPEAT gives certainty estimates that are more intuitive, better at detecting out-of-distribution data, and more concise.

ReactGPT: Understanding of Chemical Reactions via In-Context Tuning

The interdisciplinary field of chemistry and artificial intelligence (AI) is an active area of research aimed at accelerating scientific discovery. Large language Models (LLMs) have shown significant promise in biochemical tasks, especially the molecule caption translation, which aims to align between molecules and natural language texts. However, existing works mainly focus on single molecules, while alignment between chemical reactions and natural language text remains largely unexplored. Additionally, the description of reactions is an essential part in biochemical patents and literature, and research on this aspect not only can help better understand chemical reactions but also promote research on automating chemical synthesis and retrosynthesis. In this work, we propose \textbf{ReactGPT}, a framework aiming to bridge the gap between chemical reaction and text. ReactGPT allows a new task: reaction captioning, by adapting LLMs to learn reaction-text alignment from context examples via In-Context Tuning. Specifically, ReactGPT jointly leverages a Fingerprints-based Reaction Retrieval module, a Domain-Specific Prompt Design module, and a two-stage In-Context Tuning module. We evaluate the effectiveness of ReactGPT on reaction captioning and experimental procedure prediction, both of these tasks can reflect the understanding of chemical reactions. Experimental results show that compared to previous models, ReactGPT exhibits competitive capabilities in resolving chemical reactions and generating high-quality text with correct structure.

The Hard Problems of AI

There is currently an enlivened debate regarding the possibility of AI consciousness and/or sentience, as well as arguably more partial capabilities we associate with consciousness such as intelligence or creativity. The debate itself can be traced back to the inception of computing, but its current revitalisation is powered by recent advancements in the field of artificial intelligence that saw a swift increase in its capabilities to act in seemingly human-like ways. I argue that the debate is methodologically flawed, as it approaches the question of AI consciousness, intelligence, etc. as a decidable question dealing with matters of fact. Those engaged in the debate are driven by a desire to find a suitable definition of e.g. consciousness that would allow them to definitively settle the question of whether a particular AI system is conscious. However, drawing on Ludwig Wittgenstein’s later philosophy, I argue that no such definition exists, because the predicates in question are inherently vague (meaning that any verdicts they yield are bound to be vague, too). Moreover, the impression that we might be dealing with directly unobservable matters of fact is itself a flawed generalisation of the practice of observation reports to the practice of sensation reports[1]. In reality, third-person consciousness (sentience, agency, etc.) attributions are independent of a stipulated internal process happening inside those persons (or systems, in the case of AI). Therefore, the only sense in which the question of e.g. AI consciousness can be meaningfully asked is a pragmatic sense: what is it best to _think of such systems as? _But this question is subject to sociological and psychological factors, not conceptual ones. Therefore, it cannot be decided by the aforementioned strategies.

ARTIFICIAL INTELLIGENCE IN ENHANCING BIODEGRADATION PROCESSES: A DATA-DRIVEN APPROACH TO ENVIRONMENTAL SUSTAINABILITY

Objective: The purpose of this study is therefore to assess how AI can be used to advance biodegradation processes and thus support environmental sustainability by increasing the biodegradation rate, decreasing the likelihood of human mistakes, and anticipating the right conditions. Methodology: A quantitative research method was used and 250 professionals from different sectors including environmental scientists, molecular biologists, bio-technologists, and professionals in the field of Artificial Intelligence were included in the sample. The research applied a structured questionnaire that left a great impression on the participant’s opinions on the efficiency of AI in biodegradation, which was a blend of Likert-scale and multiple-choice questions. Using descriptive statistics, Cronbach’s Alpha for reliability, and principal component analysis (PCA) for dimensionality the data were analyzed. Results: Based on the results, it emerged that AI is considered to be useful in increasing biodegradation efficiency and estimating the best conditions. However, some questions were made about the effectiveness of using AI in determining the original human errors. Cronbach’s Alpha yielded a negative value of -0. 397 hence pointing out the low internal consistency of the data gathered The PCA result also indicated that perceiving AI was influenced by more than a single dimension, and the first two principal components accounted for 17 percent only. 5% and 17. 0% of the variance. Conclusion: Although there are various benefits to using AI in biodegradation there are also some limitations, especially on the reliability and consistency of the process. It was also observed from the results of the study that refinement of the AI tools and research focusing on the aims of AI to the actual biodegradation requirements are required. Filling these gaps will be critical to realizing AI’s potential for supporting environmental sustainability.

An Efficient Explainability of Deep Models on Medical Images

Nowadays, Artificial Intelligence (AI) has revolutionized many fields and the medical field is no exception. Thanks to technological advancements and the emergence of Deep Learning (DL) techniques AI has brought new possibilities and significant improvements to medical practice. Despite the excellent results of DL models in terms of accuracy and performance, they remain black boxes as they do not provide meaningful insights into their internal functioning. This is where the field of Explainable AI (XAI) comes in, aiming to provide insights into the underlying workings of these black box models. In this present paper the visual explainability of deep models on chest radiography images are addressed. This research uses two datasets, the first on COVID-19, viral pneumonia, normality (healthy patients) and the second on pulmonary opacities. Initially the pretrained CNN models (VGG16, VGG19, ResNet50, MobileNetV2, Mixnet and EfficientNetB7) are used to classify chest radiography images. Then, the visual explainability methods (GradCAM, LIME, Vanilla Gradient, Gradient Integrated Gradient and SmoothGrad) are performed to understand and explain the decisions made by these models. The obtained results show that MobileNetV2 and VGG16 are the best models for the first and second datasets, respectively. As for the explainability methods, the results were subjected to doctors and were validated by calculating the mean opinion score. The doctors deemed GradCAM, LIME and Vanilla Gradient as the most effective methods, providing understandable and accurate explanations.

Alignment of auditory artificial networks with massive individual fMRI brain data leads to generalisable improvements in brain encoding and downstream tasks

Abstract Artificial neural networks trained in the field of artificial intelligence (AI) have emerged as key tools to model brain processes, sparking the idea of aligning network representations with brain dynamics to enhance performance on AI tasks. While this concept has gained support in the visual domain, we investigate here the feasibility of creating auditory artificial neural models directly aligned with individual brain activity. This objective raises major computational challenges, as models have to be trained directly with brain data, which is typically collected at a much smaller scale than data used to train AI models. We aimed to answer two key questions: (1) Can brain alignment of auditory models lead to improved brain encoding for novel, previously unseen stimuli? (2) Can brain alignment lead to generalisable representations of auditory signals that are useful for solving a variety of complex auditory tasks? To answer these questions, we relied on two massive datasets: a deep phenotyping dataset from the Courtois neuronal modelling project, where six subjects watched four seasons (36 h) of the Friends TV series in functional magnetic resonance imaging and the HEAR benchmark, a large battery of downstream auditory tasks. We fine-tuned SoundNet, a small pretrained convolutional neural network with ~2.5 M parameters. Aligning SoundNet with brain data from three seasons of Friends led to substantial improvement in brain encoding in the fourth season, extending beyond auditory and visual cortices. We also observed consistent performance gains on the HEAR benchmark, particularly for tasks with limited training data, where brain-aligned models performed comparably with the best-performing models regardless of size. We finally compared individual and group models, finding that individual models often matched or outperformed group models in both brain encoding and downstream task performance, highlighting the data efficiency of fine-tuning with individual brain data. Our results demonstrate the feasibility of aligning artificial neural network representations with individual brain activity during auditory processing, and suggest that this alignment is particularly beneficial for tasks with limited training data. Future research is needed to establish whether larger models can achieve even better performance and whether the observed gains extend to other tasks, particularly in the context of few-shot learning.

Leveraging Large Language Models for Clinical Trial Eligibility Criteria Classification

The advent of transformer technology and large language models (LLMs) has further broadened the already extensive application field of artificial intelligence (AI). A large portion of medical records is stored in text format, such as clinical trial texts. Part of these texts is information regarding eligibility criteria. We aimed to harness the immense capabilities of an LLM by fine-tuning an open-source LLM (Llama-2) to develop a classifier from the clinical trial data. We were interested in investigating whether a fine-tuned LLM could better decide the eligibility criteria from the clinical trial text and compare the results with a more traditional method. Such an investigation can help us determine the extent to which we can rely on text-based applications developed from large language models and possibly open new avenues of application in the medical domain. Our results are comparable to the best-performing methods for this task. Since we used state-of-the-art technology, this research has the potential to open new avenues in the field of LLM application in the healthcare sector.

Explainable Ai In Customer Experience Management: Personalization Algorithms in Crm Systems

The article examines the features of integrating artificial intelligence algorithms (Explainable AI, XAI) into CRM systems aimed at enhancing customer experience (Customer Experience, CX). Based on an analysis of recent publications, the study explores the principles of personalization as well as approaches to the explainability of machine learning algorithms, including chatbots and recommendation systems. It demonstrates that transparency and interpretability of model outputs positively influence customer trust and loyalty while simultaneously improving the efficiency of internal business processes. The article analyzes the implementation experience of XAI in the banking sector, insurance call centers, and online retail, which has led to improvements in retention, conversion, and satisfaction metrics. The information presented in the article is intended for researchers and professionals in the field of artificial intelligence focused on developing interpretable machine learning algorithms, as well as for analysts seeking to optimize CRM systems to enhance customer experience management. In addition, the material is useful for professionals in corporate governance and marketing who aim to integrate advanced Explainable AI methods into personalization strategies and decision-making processes, ensuring the transparency and adaptability of services under dynamic market conditions.

The Analysis of Recommendation Algorithms in Different Domains and Future Development Trends

Recommendation algorithms are a crucial research direction in the fields of artificial intelligence and data science, with widespread applications in e-commerce, streaming media, education, healthcare, and social networks. The demand for accurate and personalized information has driven the development of recommendation systems. However, different application scenarios place varying emphases on recommendation algorithms. For instance, e-commerce focuses on conversion rates, social platforms emphasize user relationship expansion, and the healthcare sector prioritizes accuracy and privacy protection. Consequently, optimizing recommendation algorithms based on industry-specific characteristics has become a key research focus. This paper summarizes the core technologies of recommendation algorithms and their applications across different domains. It also analyzes current challenges such as data sparsity, the cold start problem, and privacy protection, along with corresponding countermeasures. To address these issues, researchers have proposed optimization methods that integrate deep learning and reinforcement learning, as well as improvements such as cross-domain data fusion and user intent modeling. Furthermore, future trends in recommendation systems include cross-domain recommendations, enhanced privacy protection techniques, improved interpretability, and the adoption of federated learning to ensure user data security while enhancing recommendation quality. With the continuous advancement of artificial intelligence, recommendation systems will become more intelligent, personalized, and secure, providing users with more accurate and efficient recommendation services.

Analysis of the Limitations and Future Trends of Loss Aversion

Existing research has shown that loss aversion has a certain influence on human decision-making, but many influencing factors have not been taken into account. Based on the existing theoretical studies, this paper summarizes and analyses the limitations of the current loss aversion theory from the perspectives of both experimental design and practical application. At the same time, in view of these existing limitations, this paper summarizes and analyses the innovations of the loss aversion theory research in the fields of neurology, social science, artificial intelligence and other fields in recent years, and makes a reasonable extension based on this, to provide a possible way to overcome the limitations of the current loss aversion theory. Through interdisciplinary development, research technology development, and experimental process improvement, future researchers can obtain more accurate and realistic theories related to loss aversion. The application fields of these theories will also be extended from the original fields of finance and politics to other fields with far-reaching effects.

Feature Processing Methods: Recent Advances and Future Trends

This paper reviews recent advances and future trends in feature processing methods within the field of artificial intelligence. With the rapid development of deep learning and big data technologies, feature processing has become essential for enhancing AI model performance. We begin by revisiting traditional feature processing methods, then focus on deep learning-based feature extraction techniques, automated feature engineering, and the application of feature processing in specific domains. The article also analyzes the current research challenges and outlines future development directions, offering structured insights for both researchers and practitioners across disciplines