This volume set, LNCS 16875-16877, constitutes the refereed proceedings of the third International Conference on Artificial Intelligence in Healthcare, AIiH 2026, held in London, UK, during August 2628, 2026. The 101 full papers included in these proceedings were carefully reviewed and selected from 172 submissions. The papers were organized in topical sections as follows: Part I: Ethics of AI in healthcare; Patient data and privacy; Machine and deep learning approaches for health data; Predictive Analytics in Healthcare; AI driven early diagnosis and prevention; and AI driven proactive care and predictive intervention; Part II: Trustworthy AI for Healthcare in Resource-Constrained Settings; From Explainability to Accountability; Multimodal Generative AI in Healthcare; AI led personalised healthcare; AI in Pharmacology: drug discovery and drug development; Intelligent Systems & Robotics for Advanced Healthcare Solutions; Ambient Assisted Living Technology for Personalised Healthcare; and AI Innovations in Autism Diagnosis; Part III: Medical image analysis and processing; AI-aided medical imaging; AI in mental health; AI in proactive health management; Healthcare workflow optimisation and automation; and DoRa-PVS Challenge: The Domain Randomisation Challenge for Perivascular Space Segmentation.

Inhalt

.- Medical image analysis and processing

.- Benchmarking Foundation Models for Pulmonary Embolism Diagnosis and Prognosis to Reveal Demographic Disparities.
.- Phase-Guided Quality Regression in Apical Echocardiography via CNN-LSTM: A Systematic Backbone Benchmarking Study.
.- A Dual-Domain Grayscale-Wavelet Reparameterization Network for Upper-Limb Long-Bone Abnormality Detection on X-ray Images. .- GAZE: Grounded Agentic Zero-shot Evaluation with Viewer-Level Tools and Literature Retrieval on Rare Brain MRI. .- Workflow-Level ROI Restriction for Deep Learning-Based 3D Aortic Valve Segmentation in Non-Contrast Cardiac CT. .- General or Medical CLIP, Which one Shall We Choose?. .- Cross-View Attention Routing in Capsule Networks for Structured Interpretable Multi-View Mammogram Breast Cancer Classification. .- A Cascade YOLO-Based Approach for Robust Retinal Optic Disc and Optic Cup Segmentation. .- XSSR: Cross-Domain Self-Supervised Representative Selection for Efficient Annotation in Medical Image Segmentation. .- Regional Myocardial Strain Estimation with MyoTrackerChrono. .- Benchmarking deep learning and conventional methods for 2D and 3D lung tumour segmentation in CT images. .- Gumbel-Sigmoid Based Adaptive Sparse Hypergraph Learning for Brain Structural Connection Analysis. .- A Deep Learning Pipeline for Diabetic Foot Ulcer Detection and Stage Classification. .- Contrastive Learning for Acne Severity Grading with Small-Scale Datasets. .- Adversarial Attacks vs.Data Augmentation Strategies: A Comprehensive Comparative Study with Application to Diabetic Retinopathy Detection. .- Towards Fair Radiographic AI: Representation and Classification Bias Analysis. .- AI-aided medical imaging .- Evaluating the trustworthiness of the Fréchet Inception Distance with stochastic embedding representations. .- Multi-Expert Consensus as a Label-Free Quality Surrogate for Echocardiographic LV Segmentation. .- Transformer Architectures Improve Minority-Class Detection in Histopathological Classification of Colorectal Polyps. .- AI in mental health .- Empathic Structured Exploration Model (ESEM): A Conversational Framework for Mental Health Screening Chatbots. .- A Scalable LLM-Based System for Early Mental Health Intervention and Workforce Resilience Using Genkit. .- Performance Evaluation of LLMs for Psychological Assessment. .- AI in proactive health management .- When LLMs guide the Plate: Exploring Diet Recommendations for Mental Health Support. .- AIbased Approaches for Diabetes Management in Africa: Educational, Self-Management, and Adherence-Oriented Interventions. .- Healthcare workflow optimisation and automation .- Reducing Outpatient No-Shows with Adaptive Reminder Strategies: A Simulation Framework for Contextual Bandit Learning and Data Requirements. .- AI-Assisted Rare Metabolic Disease Screening from Targeted LC-HR-MS: A Human-in-the-Loop Pipeline with Synthetic Data Augmentation. .- Beyond Accuracy: A Decision-Theoretic Framework for Allocation-Aware Healthcare AI. .- DoRa-PVS Challenge: The Domain Randomisation Challenge for Perivascular Space Segmentation .- Assessing Generalisation of Perivascular Space Segmentation Across Heterogeneous MRI Cohorts: The DoRA-PVS Challenge 2026.