Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability

2026/08/03 by Abdullah Mamun, Shovito Barua Soumma, Hassan Ghasemzadeh
Computer Science · #cs.AI #cs.LG

paper · pdf · doi:10.1088/2516-1091/ae4e74

published as Progress in Biomedical Engineering, Volume 8, Number 2, Article 022007, 2026 · Preprint of the paper published in Progress in Biomedical Engineering. 26 pages, 5 figures

arxiv created 2026/08/03 · arxiv updated 2026/08/04

Abstract

Ensuring trust in AI systems is essential for the safe and ethical integration of machine learning systems into high-stakes domains such as digital health. Key dimensions, including robustness, explainability, fairness, accountability, and privacy, need to be addressed throughout the AI lifecycle, from problem formulation and data collection to model deployment and human interaction. While various contributions address different aspects of trustworthy AI, a focused synthesis on robustness and explainability, especially tailored to the healthcare context, remains limited. This review addresses that need by organizing recent advancements into an accessible framework, highlighting both technical and practical considerations. We present a structured overview of methods, challenges, and solutions, aiming to support researchers and practitioners in developing reliable and explainable AI solutions for digital health. This review article is organized into three main parts. First, we introduce the pillars of trustworthy AI and discuss the technical and ethical challenges, particularly in the context of digital health. Second, we explore application-specific trust considerations across domains such as intensive care, neonatal health, and metabolic health, highlighting how robustness and explainability support trust. Lastly, we present recent advancements in techniques aimed at improving robustness under data scarcity and distributional shifts, as well as explainable AI methods ranging from feature attribution to gradient-based interpretations and counterfactual explanations. This paper is further enriched with detailed discussions of the contributions toward robustness and explainability in digital health, the development of trustworthy AI systems in the era of LLMs, and various evaluation metrics for measuring trust and related parameters such as validity, fidelity, and diversity.

Citations

• Cross-Domain Conditional Diffusion Models for Time Series Imputation
• Llama-Nemotron: Efficient Reasoning Models
• GlyTwin: Digital Twin for Glucose Control in Type 1 Diabetes Through Optimal Behavioral Modifications Using Patient-Centric Counterfactuals
• Enhancing Metabolic Syndrome Prediction with Hybrid Data Balancing and Counterfactuals
• AIMI: Leveraging Future Knowledge and Personalization in Sparse Event Forecasting for Treatment Adherence
• MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
• LLM-Powered Prediction of Hyperglycemia and Discovery of Behavioral Treatment Pathways from Wearables and Diet
• AttenGluco: Multimodal Transformer-Based Blood Glucose Forecasting on AI-READI Dataset
• Freezing of Gait Detection Using Gramian Angular Fields and Federated Learning from Wearable Sensors
• Establishing and Evaluating Trustworthy AI: Overview and Research Challenges
• Use of What-if Scenarios to Help Explain Artificial Intelligence Models for Neonatal Health
• Multimodal Physical Activity Forecasting in Free-Living Clinical Settings: Hunting Opportunities for Just-in-Time Interventions
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification
• HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
• The Llama 3 Herd of Models
• DrHouse: An LLM-empowered Diagnostic Reasoning System through Harnessing Outcomes from Sensor Data and Expert Knowledge
• RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs
• A comprehensive study on fidelity metrics for XAI
• LLMs for Relational Reasoning: How Far are We?
• Explainable AI is Responsible AI: How Explainability Creates Trustworthy and Socially Responsible Artificial Intelligence
• A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
• Designing User-Centric Behavioral Interventions to Prevent Dysglycemia with Novel Counterfactual Explanations
• Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
• A model-agnostic and data-independent tabu search algorithm to generate counterfactuals for tabular, image, and text data
• Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations
• Explaining black box text modules in natural language with language models
• Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations
• YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
• Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey
• From attribution maps to human-understandable explanations through Concept Relevance Propagation
• Large Language Models are Zero-Shot Reasoners
• BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence
• Trustworthy Artificial Intelligence: A Review
• Show Your Work: Scratchpads for Intermediate Computation with Language Models
• Masked Autoencoders Are Scalable Vision Learners
• Trustworthy AI: From Principles to Practices
• Trustworthy AI: From Principles to Practices
• CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial Learning
• From Known to Unknown: Knowledge-guided Transformer for Time-Series Sales Forecasting in Alibaba
• Robust Counterfactual Explanations on Graph Neural Networks
• Inter-Beat Interval Estimation with Tiramisu Model: A Novel Approach with Reduced Error
• NICE: An Algorithm for Nearest Instance Counterfactual Explanations
• End-To-End Bias Mitigation: Removing Gender Bias in Deep Learning
• Role of Orthogonality Constraints in Improving Properties of Deep Networks for Image Classification
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• ActiLabel: A Combinatorial Transfer Learning Framework for Activity Recognition
• Trustworthy AI in the Age of Pervasive Computing and Big Data
• UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation
• Modeling Tabular data using Conditional GAN
• What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use
• Quantifying Interpretability and Trust in Machine Learning Systems
• e-SNLI: Natural Language Inference with Natural Language Explanations
• A Review of Challenges and Opportunities in Machine Learning for Health
• Addressing Conceptual Gaps in Big Data Research Ethics: An Application of Contextual Integrity
• Multimodal Explanations: Justifying Decisions and Pointing to the Evidence
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• A Unified Approach to Interpreting Model Predictions
• Axiomatic Attribution for Deep Networks
• Towards A Rigorous Science of Interpretable Machine Learning
• Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
• The Mythos of Model Interpretability
• Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers
• "Why Should I Trust You?": Explaining the Predictions of Any Classifier
• Personal Data: Thinking Inside the Box
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• Visualizing and Understanding Convolutional Networks
• Multimodal Deep Learning
• Bias in computer systems
• OpenAI o1 System Card