Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

Focus issue: Artificial intelligence in medical physics.

Advances in high-throughput technologies, digital phenotyping, and increased accessibility of publicly available datasets offer opportunities for big data to be applied in infectious disease surveillance, diagnosis, treatment, and outcome prediction. Artificial intelligence (AI) and machine learning (ML) have emerged as promising tools to analyze complex clinical and molecular data. However, it remains unclear which AI or ML models are most suitable for infectious disease management, as most existing studies use non-scoping literature reviews to recommend AI and ML models for data analysis. This scoping literature review thus examines the ML models and applications that are most relevant for infectious disease management, with a proposed actionable workflow for implementing ML models in clinical practice. We conducted a literature search on PubMed, Google Scholar, and ScienceDirect, including papers published in English between January 2020 and April 2024. Search keywords included AI, ML, public health, surveillance, diagnosis, prognosis, and infectious disease, to identify published studies using AI and ML in infectious disease management. Studies without public datasets or lacking descriptions of the ML models were excluded. This review included a total of 77 studies applied in surveillance, prognosis, and diagnosis. Different types of input data from infectious disease surveillance, clinical diagnosis, and prognosis required different ML and AI models to achieve the maximum performance in infectious disease management. Our findings highlight the potential of Explainable AI and ensemble learning models to be more broadly applicable in different aspects of infectious disease management, which can be integrated in clinical workflows to improve infectious disease surveillance, diagnosis, and prognosis. Explainable AI and ensemble learning models can be suitably used to achieve high accuracy in prediction. However, as most of the studies have not been validated in different cohorts, it remains unclear whether these ML models can be broadly applicable to different populations. Nonetheless, the findings encourage deploying ML and AI to complement clinicians and augment clinical decision-making.

Chapter Twelve - Human AI: Explainable and responsible models in computer vision

Artificial intelligence in interdisciplinary life science and drug discovery research.

The popularity of machine learning (ML), deep learning (DL) and artificial intelligence (AI) has risen sharply in recent years. Despite this spike in popularity, the inner workings of ML and DL algorithms are often perceived as opaque, and their relationship to classical data analysis tools remains debated. Although it is often assumed that ML and DL excel primarily at making predictions, ML and DL can also be used for analytical tasks traditionally addressed with statistical models. Moreover, most recent discussions and reviews on ML focus mainly on DL, failing to synthesise the wealth of ML algorithms with different advantages and general principles. Here, we provide a comprehensive overview of the field of ML and DL, starting by summarizing its historical developments, existing algorithm families, differences to traditional statistical tools, and universal ML principles. We then discuss why and when ML and DL models excel at prediction tasks and where they could offer alternatives to traditional statistical methods for inference, highlighting current and emerging applications for ecological problems. Finally, we summarize emerging trends such as scientific and causal ML, explainable AI, and responsible AI that may significantly impact ecological data analysis in the future. We conclude that ML and DL are powerful new tools for predictive modelling and data analysis. The superior performance of ML and DL algorithms compared to statistical models can be explained by their higher flexibility and automatic data‐dependent complexity optimization. However, their use for causal inference is still disputed as the focus of ML and DL methods on predictions creates challenges for the interpretation of these models. Nevertheless, we expect ML and DL to become an indispensable tool in ecology and evolution, comparable to other traditional statistical tools.

Technology based on artificial intelligence (AI) is a revolutionary force that is changing economies, civilizations, and industries all over the world. AI, which has its roots in computer science and cognitive psychology, is a wide range of tools and methods designed to make robots capable of doing activities that have historically required human intellect. This abstract examines the many facets of artificial intelligence (AI) technology, including its fundamentals, uses, difficulties, and ramifications. Artificial Intelligence (AI) technology comprises several subfields such as robotics, computer vision, natural language processing, machine learning, and expert systems. Particularly, machine learning techniques have propelled incredible progress by allowing computers to learn from data and make judgments or predictions without the need for explicit programming. Natural language processing allows machines to comprehend, interpret, and produce human language, hence facilitating human-computer interaction. Machines can now see, analyze, and interpret visual data from the real world thanks to computer vision technology. Applications of AI technology may be found in a wide range of industries, including manufacturing, healthcare, finance, transportation, agriculture, education, and entertainment. AI-powered solutions help in drug discovery, medical imaging analysis, diagnosis, and customized therapy in the healthcare industry. AI algorithms are used in finance to power automated trading, fraud detection, risk assessment, and customer support. AI makes it possible for transportation to include predictive maintenance, traffic management, and driverless cars. Artificial Intelligence enhances supply chain management, quality assurance, and production processes in manufacturing. AI technology has the potential to revolutionize many industries, but it also comes with dangers and problems. These include privacy concerns, security hazards, ethical dilemmas, issues with prejudice and fairness, and effects on society and employment. Responsible AI methods, legal frameworks, multidisciplinary cooperation, and ethical standards are all necessary to meet these issues. Future prospects for AI technology development include the ability to solve challenging issues, spur creativity, increase productivity, and improve quality of life. But to fully utilize AI, one must take a comprehensive strategy that strikes a balance between the advancement of technology and ethical issues, human values, and social well-being. In summary, artificial intelligence (AI) technology is at the vanguard of innovation, presenting never-before-seen possibilities to transform whole sectors, spur economic expansion, and tackle global issues. AI has the ability to usher in a future of greater human-machine collaboration, innovation, and wealth through the promotion of collaboration, transparency, and ethical stewardship. the Ranking of the Artificial Intelligence using the TOPSIS Method . Interpretable Models is got the first rank whereas is the Ethical AI is having the Lowest rank. Keywords: Explainable AI (XAI), Interpretable Models, Ethical AI ,Responsible AI, Robustness and Adversarial Defense, Continual Learning, Federated Learning, Human-Centric AI, AI Governance and Policy

Any opinions expressed in the chapters are those of the authors. Whilst Emerald makes every effort to ensure the quality and accuracy of its content, Emerald makes no representation implied or otherwise, as to the chapters' suitability and application and disclaims any warranties, express or implied, to their use.

Global agriculture is poised to benefit from the rapid advance and diffusion of artificial intelligence (AI) technologies. AI in agriculture could improve crop management and agricultural productivity through plant phenotyping, rapid diagnosis of plant disease, efficient application of agrochemicals and assistance for growers with location-relevant agronomic advice. However, the ramifications of machine learning (ML) models, expert systems and autonomous machines for farms, farmers and food security are poorly understood and under-appreciated. Here, we consider systemic risk factors of AI in agriculture. Namely, we review risks relating to interoperability, reliability and relevance of agricultural data, unintended socio-ecological consequences resulting from ML models optimized for yields, and safety and security concerns associated with deployment of ML platforms at scale. As a response, we suggest risk-mitigation measures, including inviting rural anthropologists and applied ecologists into the technology design process, applying frameworks for responsible and human-centred innovation, setting data cooperatives for improved data transparency and ownership rights, and initial deployment of agricultural AI in digital sandboxes.

Summary A meticulous interpretation of steady-state or unsteady-state relative permeability (Kr) experimental data is required to determine a complete set of Kr curves. In this work, different machine learning (ML) models were developed to assist in a faster estimation of these curves from steady-state drainage coreflooding experimental runs. These ML algorithms include gradient boosting (GB), random forest (RF), extreme gradient boosting (XGB), and deep neural network (DNN) with a main focus on and comparison of the two latter algorithms (XGB and DNN). Based on existing mathematical models, a leading-edge framework was developed where a large database of Kr and capillary pressure (Pc) curves were generated. This database was used to perform thousands of coreflood simulation runs representing oil-water drainage steady-state experiments. The results obtained from these simulation runs, mainly pressure drop along with other conventional core analysis data, were used to estimate analytical Kr curves based on Darcy’s law. These analytically estimated Kr curves along with the previously generated Pc curves were fed as features into the ML model. The entire data set was split into 80% for training and 20% for testing. The k-fold cross-validation technique was applied to increase the model’s accuracy by splitting 80% of the training data into 10 folds. In this manner, for each of the 10 experiments, nine folds were used for training and the remaining fold was used for model validation. Once the model was trained and validated, it was subjected to blind testing on the remaining 20% of the data set. The ML model learns to capture fluid flow behavior inside the core from the training data set. In terms of applicability of these ML models, two sets of experimental data were needed as input; the first was the analytically estimated Kr curves from the steady-state drainage coreflooding experiments, while the other was the Pc curves estimated from centrifuge or mercury injection capillary pressure (MICP) measurements. The trained/tested model was then able to estimate Kr curves based on the experimental results fed as input. Furthermore, to test the performance of the ML model when only one set of experimental data is available to an end user, a recurrent neural network (RNN) algorithm was trained/tested to predict Kr curves in the absence of Pc curves as an input. The performance of the three developed models (XGB, DNN, and RNN) was assessed using the values of the coefficient of determination (R2) along with the loss calculated during training/validation of the model. The respective crossplots along with comparisons of ground truth vs. artificial intelligence (AI)-predicted curves indicated that the model is capable of making accurate predictions with an error percentage between 0.2% and 0.6% on history-matching experimental data for all three tested ML techniques. This implies that the AI-based model exhibits better efficiency and reliability in determining Kr curves when compared to conventional methods. The developed ML models by no means replace the need to conduct drainage coreflooding or centrifuge experiments but act as an alternative to existing commercial platforms that are used to interpret experimental data to predict Kr curves. The two main advantages of the developed ML models are their capability of predicting Kr curves within a matter of a few minutes as well as with limited intervention from the end user. The results also include a comparison between classical ML approaches, shallow neural networks, and DNNs in terms of accuracy in predicting the final Kr curves. The research presented here is an extension of the state-of-the-art framework proposed by Mathew et al. (2021). However, the two main aspects of the current study are the application of deep learning for the prediction of Kr curves and the application of feature engineering. The latter not only reduces the training/testing time for the ML models but also enables the end user to obtain the final predictions with the least set of experimental data. The various models discussed in this research work currently focus on the prediction of Kr curves for drainage steady-state experiments; however, the work can be extended to capture the imbibition cycle as well.

Explainable artificial intelligence (XAI) is of paramount importance to various domains, including healthcare, fitness, skill assessment, and personal assistants, to understand and explain the decision-making process of the artificial intelligence (AI) model. Smart homes embedded with smart devices and sensors enabled many context-aware applications to recognize physical activities. This study presents XAI-HAR, a novel XAI-empowered human activity recognition (HAR) approach based on key features identified from the data collected from sensors located at different places in a smart home. XAI-HAR identifies a set of new features (i.e., the total number of sensors used in a specific activity), as physical key features selection (PKFS) based on weighting criteria. Next, it presents statistical key features selection (SKFS) (i.e., mean, standard deviation) to handle the outliers and higher class variance. The proposed XAI-HAR is evaluated using machine learning models, namely, random forest (RF), K-nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), naive Bayes (NB) and deep learning models such as deep neural network (DNN), convolution neural network (CNN), and CNN-based long short-term memory (CNN-LSTM). Experiments demonstrate the superior performance of XAI-HAR using RF classifier over all other machine learning and deep learning models. For explainability, XAI-HAR uses Local Interpretable Model Agnostic (LIME) with an RF classifier. XAI-HAR achieves 0.96% of F-score for health and dementia classification and 0.95 and 0.97% for activity recognition of dementia and healthy individuals, respectively.

In recent years, the field of Artificial Intelligence (AI) and Machine Learning (ML) has witnessed remarkable advancements, revolutionizing various industries and domains. The proliferation of data availability, computational power, and algorithmic innovations has propelled the development of highly sophisticated AI models, particularly in the realm of Deep Learning (DL). These DL models have demonstrated unprecedented levels of accuracy and performance across a wide range of tasks, including image recognition, natural language processing, and complex decision-making. However, amidst these impressive achievements, a critical challenge has emerged - the lack of interpretability.Highly accurate AI models, including DL models, are often referred to as black boxes because their internal workings and decision-making processes are not readily understandable to humans. While these models excel in generating accurate predictions or classifications, they do not provide clear explanations for their reasoning, leaving users and stakeholders in the dark about how and why specific decisions are made. This lack of interpretability raises concerns and limits the trust that humans can place in these models, particularly in safety-critical or high-stakes applications where accountability, transparency, and understanding are paramount.To address the challenge of interpretability, Explainable AI (xAI) has emerged as a multidisciplinary field that aims to bridge the gap in understanding between machines and humans. xAI encompasses a collection of methods and techniques designed to shed light on the decision-making processes of AI models, making their outputs more transparent, interpretable, and comprehensible to human users.The main objective of this paper is to enhance the explainability of AI-based systems that involve user interaction by employing various xAI methods. The proposed approach revolves around a comprehensive ML workflow, beginning with the utilization of real-world data to train a machine learning model that learns the behavior of a simulated driver. The training process encompasses a diverse range of real-world driving scenarios, ensuring that the model captures the intricacies and nuances of different driving situations. This training data serves as the foundation for the subsequent phases of the workflow, where the model's predictive performance is evaluated.Following the training and testing phases, the predictions generated by the ML model are subjected to explanation using different xAI methods, such as LIME (Local Interpretable Model-Agnostic Explanations) and SHAP (SHapley Additive exPlanations). These xAI methods operate at both the global and local levels, providing distinct perspectives on the model's decision-making process. Global explanations offer insights into the overall behavior of the ML model, enabling a broader understanding of the patterns, relationships, and features that the model deems significant across different instances. These global explanations contribute to a deeper comprehension of the decision-making process employed by the model, allowing users to gain insights into the underlying factors driving its predictions.In contrast, local explanations offer detailed insights into specific instances or predictions made by the model. By analyzing these local explanations, users can better understand why the model made a particular prediction in a given case. This granular analysis facilitates the identification of potential weaknesses, biases, or areas for improvement in the model's performance. By pinpointing the specific features or factors that contribute to the model's decision in individual instances, local explanations offer valuable insights for refining the model and enhancing its accuracy and reliability.In conclusion, the lack of explainability in AI models, particularly in the realm of DL, presents a significant challenge that hinders trust and understanding between machines and humans. Explainable AI (xAI) has emerged as a vital field of research and practice, aiming to address this challenge by providing methods and techniques to enhance the interpretability and transparency of AI models. This paper focuses on enhancing the explainability of AI-based systems involving user interaction by employing various xAI methods. The proposed ML workflow, coupled with global and local explanations, offers valuable insights into the decision-making processes of the model. By unraveling the scenario-based behavior of a self-learning function with user interaction, this paper aims to contribute to the understanding and interpretability of AI-based systems. The insights gained from this research can pave the way for enhanced user trust, improved model performance, and further advancements in the field of explainable AI.

Artificial intelligence (AI) based predictive models for early detection of cardiovascular disease (CVD) risk are increasingly being utilised. However, AI based risk prediction models that account for right-censored data have been overlooked. This systematic review (PROSPERO protocol CRD42023492655) includes 33 studies that utilised machine learning (ML) and deep learning (DL) models for survival outcome in CVD prediction. We provided details on the employed ML and DL models, eXplainable AI (XAI) techniques, and type of included variables, with a focus on social determinants of health (SDoH) and gender-stratification. Approximately half of the studies were published in 2023 with the majority from the United States. Random Survival Forest (RSF), Survival Gradient Boosting models, and Penalised Cox models were the most frequently employed ML models. DeepSurv was the most frequently employed DL model. DL models were better at predicting CVD outcomes than ML models. Permutation-based feature importance and Shapley values were the most utilised XAI methods for explaining AI models. Moreover, only one in five studies performed gender-stratification analysis and very few incorporate the wide range of SDoH factors in their prediction model. In conclusion, the evidence indicates that RSF and DeepSurv models are currently the optimal models for predicting CVD outcomes. This study also highlights the better predictive ability of DL survival models, compared to ML models. Future research should ensure the appropriate interpretation of AI models, accounting for SDoH, and gender stratification, as gender plays a significant role in CVD occurrence.

Artificial intelligence (AI) has, in the recent past, experienced a rebirth with the growth of generative AI systems such as ChatGPT and Bard. These systems are trained with billions of parameters and have enabled widespread accessibility and understanding of AI among different user groups. Widespread adoption of AI has led to the need for understanding how machine learning (ML) models operate to build trust in them. An understanding of how these models generate their results remains a huge challenge that explainable AI seeks to solve. Federated learning (FL) grew out of the need to have privacy-preserving AI by having ML models that are decentralized but still share model parameters with a global model. This study sought to examine the extent of development of the explainable AI field within the FL environment in relation to the main contributions made, the types of FL, the sectors it is applied to, the models used, the methods applied by each study, and the databases from which sources are obtained. A systematic search in 8 electronic databases, namely, Web of Science Core Collection, Scopus, PubMed, ACM Digital Library, IEEE Xplore, Mendeley, BASE, and Google Scholar, was undertaken. A review of 26 studies revealed that research on explainable FL is steadily growing despite being concentrated in Europe and Asia. The key determinants of FL use were data privacy and limited training data. Horizontal FL remains the preferred approach for federated ML, whereas post hoc explainability techniques were preferred. There is potential for development of novel approaches and improvement of existing approaches in the explainable FL field, especially for critical areas. OSF Registries 10.17605/OSF.IO/Y85WA; https://osf.io/y85wa.

Industry 4.0 has brought about a significant transformation in manufacturing by merging the digital and physical systems. It introduced innovations such as Internet of Things (IoT), Big Data, Artificial Intelligence (AI), and automation into industrial processes to promote the concept of smart manufacturing. Our current research focuses on creating methodologies for effectively using data in manufacturing through AI and Machine Learning (ML). Many US manufacturers, particularly Small to Medium Manufacturers (SMM), struggle to utilize ML due to financial constraints or a shortage of data science expertise. While Industry 4.0 emphasizes automation, Industry 5.0 introduces the idea of human-machine collaboration, where Industry 4.0 technology enhances human productivity using technologies like IoT and Big Data with an emphasis on trust as a key factor in their cooperation. This research concentrates on building trustworthy ML models that can be easily developed by SMM's for democratized AI, a central aspect of Industry 5.0. This involves developing interpretable ML models capable of explaining their decision-making processes by employing Explainable AI (XAI) concepts for interpretation. Subsequently, this work leverages the insights from XAI to improve ML performance through the domain manufacturing knowledge. By leveraging the aforementioned research thrusts, the final outcome of this research is a framework that establishes both trustworthy and generalizable ML models for SMMs.

Background: Questions surrounding the ethics of artificial intelligence (AI) have been debated for decades [1]. However, in recent years there have been multiple initiatives, scholarly reviews, and policy documents to identify and define ethical issues in play [2]. The efforts to bring high-level principles to applicable practice are complex and can be lost in translation [3]. Moreover, a call to be proactive, rather than reactive, stems from a deduction of intentions behind responsible innovation, value-centric design principles, education efforts, and representative data management techniques. Contemporary applications of AI are complex and difficult to explain, edit, and deal with once integrated in a natural system [4] [5]. Therefore, the analysis conducted within this systematic literature review (SLR) will clarify methods to promote and engage practice on the front end of ethical and responsible AI. As such, the research question is explored: How does each helix in the Quintuple Innovation model address responsible and ethical AI technology with anticipatory or proactive approaches? Methods: To conduct this ongoing research, an adaptation of the PRISMA framework and Hess & Fore's 2017 methodological approach guides the SLR [6] [7]. We included journal articles that were written in English and published between 2018-2023. The collected studies aim to examine how academic scholarship approaches to responsible AI within academia, government, industry, civil society, or the natural environment (the Quintuple Helix). The Web of Science, Google Scholar, and PhilPapers databases were used to identify a set of prominent publications in this field: AI & Society, Nature Machine Intelligence, Minds and Machines, IEEE Transactions on Technology and Society, AI and Ethics, Science and Engineering Ethics, and Communications of the ACM. A key limitation of this study is that it cannot gather the entirety of literature written about the topics of proactively promoting ethical AI due to the vast size and definitional complexity of the associated fields. These inclusion criteria allow the researchers to manage the data and draw meaningful insights from the most current thinking that is reflected in the rapid development of AI innovation we see today. Results and discussion: This poster will present preliminary results and the theoretical framework that guided the qualitative coding process. Additionally, this poster will serve as a forum to collect experts' opinions about what they would like to see from this SLR dataset, and how we can incorporate those elements into our coding. As a result, this data will be able to inform future work to investigate multiple gaps in the literature. For instance, U.S. Government work not protected by U.S. copyright this study will result in a theoretical framework that identifies proactive approaches to responsible and sustainable AI aligned with the five sectors for innovation. Inspired from [8], the effects of investments in education, and other sectors, will be mapped as a chain of responsible AI innovation across all innovation sectors. Finally, we can draw informed conclusions about the use and misuse of experts in AI, ethics, education, and policy. By working towards these objectives, we can see how the interdisciplinary field has made (or not made) a collective effort toward promoting responsible AI-filling a gap in the literature that highlights proactive approaches, rather than reactive. In conclusion, this data will inform experts across multiple domains about how to approach and organize a concerted effort to promote ethical and responsible AI in a pragmatic way.