Deep learning has demonstrated expert-level performance in melanoma classification, positioning it as a powerful tool in clinical dermatology. However, model opacity and the lack of interpretability remain critical barriers to clinical adoption, as clinicians often struggle to trust the decision-making processes of black-box models. To address this gap, we present a Cross-modal Explainable Framework for Melanoma (CEFM) that leverages contrastive learning as the core mechanism for achieving interpretability. Specifically, CEFM maps clinical criteria for melanoma diagnosis—namely Asymmetry, Border, and Color (ABC)—into the Vision Transformer embedding space using dual projection heads, thereby aligning clinical semantics with visual features. The aligned representations are subsequently translated into structured textual explanations via natural language generation, creating a transparent link between raw image data and clinical interpretation. Experiments on public datasets demonstrate 92.79% accuracy and an AUC of 0.961, along with significant improvements across multiple interpretability metrics. Qualitative analyses further show that the spatial arrangement of the learned embeddings aligns with clinicians’ application of the ABC rule, effectively bridging the gap between high-performance classification and clinical trust.

Artificial Intelligence (AI) has rapidly transformed the medical field, necessitating significant changes in medical education to prepare healthcare professionals for future work requirements. However, the integration of AI into medical curricula has been slow and lacks standardization. In this paper, we present our work in developing a year-long postgraduate-level AI in Medicine program offered by a medical school at a public university in Singapore. Our curriculum design follows Kern's six-step approach to medical curriculum development, organized into a four-session framework. These sessions involved collaboration with hospital and university administrators, educators, industry experts, and healthcare professionals. The program is structured around three core courses: Foundational Healthcare AI, Clinical Applications of Healthcare AI, and Governance and Ethics for Healthcare AI. Each course comprises multiple modules with associated projects, emphasizing hands-on learning. The program adopts a problem-based learning approach, supported by a blended learning environment to accommodate the schedules of working healthcare professionals. Evaluations by industry experts highlight the program's potential to address critical gaps in the healthcare sector. This study contributes to the integration of AI into medical training by providing a standardized approach that can be adapted globally.

Vital signs, such as heart rate and blood pressure, are critical indicators of patient health and are widely used in clinical monitoring and decision-making. While deep learning models have shown promise in forecasting these signals, their deployment in healthcare remains limited in part because clinicians must be able to trust and interpret model outputs. Without reliable uncertainty quantification - particularly calibrated prediction intervals (PIs) - it is unclear whether a forecasted abnormality constitutes a meaningful warning or merely reflects model noise, hindering clinical decision-making. To address this, we present two methods for deriving PIs from the Reconstruction Uncertainty Estimate (RUE), an uncertainty measure well-suited to vital-sign forecasting due to its sensitivity to data shifts and support for label-free calibration. Our parametric approach assumes that prediction errors and uncertainty estimates follow a Gaussian copula distribution, enabling closed-form PI computation. Our non-parametric approach, based on k-nearest neighbours (KNN), empirically estimates the conditional error distribution using similar validation instances. We evaluate these methods on two large public datasets with minute- and hour-level sampling, representing high- and low-frequency health signals. Experiments demonstrate that the Gaussian copula method consistently outperforms conformal prediction baselines on low-frequency data, while the KNN approach performs best on high-frequency data. These results underscore the clinical promise of RUE-derived PIs for delivering interpretable, uncertainty-aware vital sign forecasts.

Uncertainty is a fundamental challenge in medical practice, but current medical AI systems fail to explicitly quantify or communicate uncertainty in a way that aligns with clinical reasoning. Existing XAI works focus on interpreting model predictions but do not capture the confidence or reliability of these predictions. Conversely, uncertainty estimation (UE) techniques provide confidence measures but lack intuitive explanations. The disconnect between these two areas limits AI adoption in medicine. To address this gap, we propose Explainable Uncertainty Estimation (XUE) that integrates explainability with uncertainty quantification to enhance trust and usability in medical AI. We systematically map medical uncertainty to AI uncertainty concepts and identify key challenges in implementing XUE. We outline technical directions for advancing XUE, including multimodal uncertainty quantification, model-agnostic visualization techniques, and uncertainty-aware decision support systems. Lastly, we propose guiding principles to ensure effective XUE realisation. Our analysis highlights the need for AI systems that not only generate reliable predictions but also articulate confidence levels in a clinically meaningful way. This work contributes to the development of trustworthy medical AI by bridging explainability and uncertainty, paving the way for AI systems that are aligned with real-world clinical complexities.

Explaining machine learning (ML) predictions has become crucial as ML models are increasingly deployed in high-stakes domains such as healthcare. While SHapley Additive exPlanations (SHAP) is widely used for model interpretability, it fails to differentiate between causality and correlation, often misattributing feature importance when features are highly correlated. We propose Causal SHAP, a novel framework that integrates causal relationships into feature attribution while preserving many desirable properties of SHAP. By combining the Peter-Clark (PC) algorithm for causal discovery and the Intervention Calculus when the DAG is Absent (IDA) algorithm for causal strength quantification, our approach addresses the weakness of SHAP. Specifically, Causal SHAP reduces attribution scores for features that are merely correlated with the target, as validated through experiments on both synthetic and real-world datasets. This study contributes to the field of Explainable AI (XAI) by providing a practical framework for causal-aware model explanations. Our approach is particularly valuable in domains such as healthcare, where understanding true causal relationships is critical for informed decision-making.

In recent years, deep learning has gained traction in medical research, particularly in addressing challenges related to predicting outcomes from irregularly sampled time-series data. This irregularity, stemming from inconsistent follow-up appointments and vital sign recordings, poses significant hurdles for traditional machine learning techniques reliant on regularly sampled data. To overcome this, researchers have developed two main categories of methods: interpolation-based and non-interpolation-based models. Our study proposes STraTS-mTAND, a novel approach that integrates techniques from both categories to predict outcomes from irregularly sampled time-series data. By leveraging the strengths of STraTS, a non-interpolation model, and mTAND, an interpolation model, our approach aims to mitigate their respective limitations. Evaluation on datasets like the PhysioNet Challenge 2012 and MIMIC-III demonstrates superior performance compared to existing methods, showing improvements in both PR-AUC and ROC-AUC metrics. Notably, our approach exhibits robustness with less training data and performs effectively with sparser and more irregular time series—characteristics inherent in recorded medical data. Additionally, our analysis offers insights into optimizing predictive modelling in healthcare, potentially reducing costs associated with data extraction and management, shortening operational cycles for model development and deployment, and enhancing digital agility and sustainability within the healthcare sector.

Substantial progress has been made in developing deep-learning models for clinical diagnosis. While excelling in diagnostics, the broader clinical decision-making process also involves establishing optimal follow-up intervals (TCU), crucial for prognosis and timely treatment. To fully support clinical practice, it is imperative that deep learning models contribute to both initial diagnosis and TCU prediction. However, relying on separate monolithic models is computationally demanding and lacks interpretability, hindering clinician trust. Our proposed bilateral model, emphasizing ophthalmological cases, offers both initial diagnoses and follow-up predictions, enhancing interpretability and trust in clinical applications as clinicians are more likely to trust recommendations, knowing the diagnosis used is correct. Inspired by clinical practice, the model integrates hierarchical inference and self-supervised learning techniques to enhance predictive accuracy and interpretability. Consisting of a sparse autoencoder, diagnosis classifier, and TCU classifier, the model leverages insights from clinicians and observations of ophthalmological datasets to capture salient features and facilitate robust learning. By employing shared weights for encoding and diagnosing each organ, the model optimizes efficiency and doubles the effective dataset size. Experimental results on an ophthalmological dataset demonstrate superior performance compared to baseline models, with the hierarchical inference structure providing valuable insights into the model's decision-making process. The bilateral model not only enhances predictive modeling for conditions affecting bilaterally symmetrical organs but also empowers clinicians with interpretable outputs crucial for informed clinical decision-making, thereby advancing clinical practice and improving patient care.

Deep Neural Networks (DNNs) stand out as one of the most prominent approaches within the Machine Learning (ML) domain. The efficacy of DNNs has surged alongside recent increases in computational capacity, allowing these approaches to scale to significant complexities for addressing predictive challenges in big data. However, as the complexity of the DNN models increases, interpretability diminishes. In response to this challenge, explainable models such as Adversarial Gradient Integration (AGI) leverage path-based gradients provided by DNNs to elucidate their decisions. Yet, the performance of path-based explainers can be compromised when gradients exhibit irregularities during out-of-distribution path traversal. In this context, we introduce Quantified Uncertainty Counterfactual Explanations (QUCE), a method designed to mitigate out-of-distribution traversal by minimizing path uncertainty. QUCE not only quantifies uncertainty when presenting explanations but also generates more certain counterfactual examples. We showcase the performance of the QUCE method by comparing it with competing methods for both path-based explanations and generative counterfactual examples. The code repository for the QUCE method is available at: https://github.com/jamie-duell/QUCE_ICDM.

Analyzing patient health through irregular time series vital sign data demands innovative methods beyond conventional imputation techniques. This study introduces a novel approach diverging from prevailing attention-based models to explicitly capture temporal patient evolution. We adopt a paradigm where patients are viewed as dynamic systems evolving over time, with their vital signs encapsulating the system’s states. Our conceptual framework draws parallels to a Markov chain, exploring the transitions between states within a unit of time. To navigate the challenge of a vast state space, we employ a neural network to model expected transitions. Our method portrays the patient’s progression within one unit of time as the system evolves from one state to another, and forecasts states into the future. We outline the training process using irregular time series data and demonstrate its efficacy through analysis on two large vital sign data sets. Comparative analysis against attention-based models emphasizes the effectiveness and efficiency of our approach. This research heralds a promising avenue for patient vital sign analysis, providing insights into temporal patient evolution without relying on imputation methods, thereby enhancing predictive accuracy and interpretability of models.

The consideration of methods for causal inference, such as Average Treatment Effects in medical analytics, offers valuable insights into the effects of interventions. However, assessing causal effects through intervention has inherent limitations, as it is not feasible to evaluate a patient in two states simultaneously. To overcome this, A/B testing with control and experiment groups is often utilized to analyze the average effects of interventions. However, A/B testing is often limited to relatively small cohorts. Counterfactual explanations, an Explainable AI (XAI) technique, provide a way to determine how changes to an instance can impact associated predictions, thus evaluating an individual in hypothetical states using existing data without the need for physical intervention. In this context, this work introduces a new counterfactual explanation technique and proposes metrics and a theoretical analysis to evaluate its properties, helping to advance the understanding and application of counterfactual explanations in XAI.

eXplainable Artificial Intelligence (XAI) is at the forefront of Artificial Intelligence research. Little attention, however, has been paid to the development of XAI methods for temporal data. Current state-of-the-art methods treat instances as independent and do not utilise the time dimension. Critical fields such as Healthcare and Finance often take a temporal form, leaving a prominent gap in XAI research. To this end, we propose the utilisation and optimisation of path based methods to use the temporal nature of data for explanations. In this work we (1) Extrapolate on a new technique for explainability forming a formal introduction, based on Integrated Gradients, a technique not designed for temporal data, (2) introduce new properties for time-based explainers and give an overview of the state-of-the-art methods and their adherence to these properties, (3) provide a theoretical and empirical analysis of path based methods, (4) demonstrate explanations on real world case studies. From this, we identify the proposed method best adheres to both the proposed properties and existing properties. Similarly, we demonstrate how the introduced method outperforms state-of the-art methods in the demonstrated areas

Probabilistic rules are at the core of probabilistic structured argumentation. With a language L, probabilistic rules describe conditional probabilities Pr(σ0|σ1,…,σk) of deducing some sentences σ0∈L from others σ1,…,σk∈L by means of prescribing rules σ0←σ1,…,σk with head σ0 and body σ1,…,σk. In Probabilistic Assumption-based Argumentation (PABA), a few constraints are imposed on the form of probabilistic rules. Namely, (1) probabilistic rules in a PABA framework must be acyclic, and (2) if two rules have the same head, then the body of one rule must be the subset of the other. In this work, we show that both constraints can be relaxed by introducing the concept of Rule Probabilistic Satisfiability (Rule-PSAT) and solving the underlying joint probability distribution on all sentences in L. A linear programming approach is presented for solving Rule-PSAT and computing sentence probabilities from joint probability distributions.

Feature attribution XAI algorithms enable their users to gain insight into the underlying patterns of large datasets through their feature importance calculation. Existing feature attribution algorithms treat all features in a dataset homogeneously, which may lead to misinterpretation of consequences of changing feature values. In this work, we consider partitioning features into controllable and uncontrollable parts and propose the Controllable fActor Feature Attribution (CAFA) approach to compute the relative importance of controllable features. We carried out experiments applying CAFA to two existing datasets and our own COVID-19 non-pharmaceutical control measures dataset. Experimental results show that with CAFA, we are able to exclude influences from uncontrollable features in our explanation while keeping the full dataset for prediction.

Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) algorithms have been widely discussed by the Explainable AI (XAI) community but their application to wider domains are rare, potentially due to the lack of easy-to-use tools built around these methods. In this paper, we present ExMed, a tool that enables XAI data analytics for domain experts without requiring explicit programming skills. It supports data analytics with multiple feature attribution algorithms for explaining machine learning classifications and regressions. We illustrate its domain of applications on two real world medical case studies, with the first one analysing COVID-19 control measure effectiveness and the second one estimating lung cancer patient life expectancy from the artificial Simulacrum health dataset. We conclude that ExMed can provide researchers and domain experts with a tool that both concatenates flexibility and transferability of medical sub-domains and reveal deep insights from data.

Activity recognition is a key problem in multi-sensor systems. In this work, we introduce Computational Assumption-based Argumentation, an argumentation approach that seamlessly combines sensor data processing with high-level inference. Our method gives classification results comparable to machine learning based approaches with reduced training time while also giving explanations.

Identifying and rewarding truthful workers are key to the sustainability of crowdsourcing platforms. In this paper, we present a clustering based rewarding mechanism that rewards workers based on their truthfulness while accommodating the differences in workers' preferences. Experimental results show that the proposed approach can effectively discover subcrowds under various conditions, and truthful workers are better rewarded than less truthful ones.

Argumentation can be viewed as a process of generating explanations. However, existing argumentation semantics are developed for identifying acceptable arguments within a set, rather than giving concrete justifications for them. In this work, we propose a new argumentation semantics, related admissibility, designed for giving explanations to arguments in both Abstract Argumentation and Assumption-based Argumentation. We identify different types of explanations defined in terms of the new semantics. We also give a correct computational counterpart for explanations using dispute forests.

Argumentation can be viewed as a process of generating explanations. We propose a new argumentation semantics, related admissibility, for closely capturing explanations in Abstract Argumentation, and distinguish between compact and verbose explanations. We show that dispute forests, composed of dispute trees, can be used to correctly compute these explanations.

We present a method for (two) agents to resolve conflicts amongst themselves, when these conflicts arise from the agents suggesting different realizations of the same goal. The method uses generalpurpose dialogues to allow agents to exchange views. These are in the form of rules, assumptions and contraries of assumptions, in the format underlying Assumption-Based Argumentation (ABA). Thus, the dialogues amount to conducting an argumentation process in ABA. We define successful dialogues as those giving admissible sets of arguments and prove that these successful dialogues resolve conflicts. Thus, we provide a fully distributed, argumentation-based solution to conflict resolution while at the same time linking the computation of a well-known argumentation semantics and two-agent conflict resolution.

Recently we have seen a few development in argumentation-based dialogue systems, but there is less research in understanding agents' strategic behaviour in dialogues. We study agent strategies by linking a specific form of argumentation-based dialogues and mechanism design. Specifically, focusing on persuasion dialogues, we show how dialogues can be mapped to concepts in mechanism design. We prove that a “truthful” and “thorough” dialogue strategy is a dominant strategy under specific conditions. We also prove that a mechanism using this dialogue strategy implements a “persuasion social choice function” we define. These results show the validity of the proposed strategies for agents in persuasion and the feasibility of studying persuasion with mechanism design techniques.

Formal argumentation based dialogue models have attracted some research interests recently. Within this line of research, we propose a formal model for argumentation-based dialogues between agents, using assumption-based argumentation (ABA). Thus, the dialogues amount to conducting an argumentation process in ABA. The model is given in terms of ABA-specific utterances, debate trees and forests implicitly built during and drawn from dialogues, legal-move functions (amounting to protocols) and outcome functions. Moreover, we investigate the strategic behaviour of agents in dialogues, using strategy-move functions. We instantiate our dialogue model in a range of dialogue types studied in the literature, including information-seeking, inquiry, persuasion, conflict resolution, and discovery. Finally, we prove (1) a formal connection between dialogues and well-known argumentation semantics, and (2) soundness and completeness results for our dialogue models and dialogue strategies used in different dialogue types.

Conflicts exist in multi-agent systems. Agents have different interests and desires. Agents also hold different beliefs and may make different assumptions. To resolve conflicts, agents need to better convey information between each other and facilitate fair negotiations that yield jointly agreeable outcomes. In this paper, we present a two-agent conflict resolution scheme developed under Assumption-Based Argumentation (ABA). Agents represent their beliefs and desires in ABA. Conflicts are resolved by merging conflicting arguments. We also discuss the notion of fairness and the use of argumentation dialogue in conflict resolution.

Trajectory generation and control of large equipment in open field environments involves systematically and robustly operating in uncertain and dynamic terrain. This paper presents an integrated motion planning and control system for tracked vehicles. Flexible path-end adjustments and adaptive look-ahead are introduced to a state lattice planning approach with waypoint control. For a given processing horizon, this increases search coverage and reduces planning error. This tramming approach has been successfully fielded on a 98-ton autonomous blast hole drill rig used in iron ore mining in Western Australia. The system has undergone extensive testing and is now integrated into a production environment. This work is a key element in a larger program aimed at developing a fully autonomous, remotely operated mine.