Beyond Black-Box AI: Interpretable Hybrid Systems for Dementia Care

2025-07-01

AI Summary

Current AI—particularly large language models (LLMs)—exhibits limited clinical utility in dementia diagnosis and care, primarily due to opaque “black-box” decision-making, high hallucination risk, and weak causal reasoning, resulting in low clinician trust and no measurable improvement in diagnostic performance. To address this, we propose a human-in-the-loop neurosymbolic hybrid intelligence framework that integrates LLMs with clinical causal knowledge, rule-based reasoning engines, and explainable AI (XAI) techniques, thereby unifying predictive accuracy with decision transparency. Our key innovation lies in the deep synergistic alignment of statistical learning, symbolic inference, and domain-expert clinical workflows—enhancing both explanation consistency and operational adaptability. Empirical evaluation demonstrates significant improvements in clinicians’ comprehension of AI outputs, trust in recommendations, and rate of clinical adoption, validating a novel AI evaluation paradigm centered on clinical interpretability, workflow integration, and patient-centered outcomes.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability
• Machine Learning: Neuro-Symbolic Learning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

The recent boom of large language models (LLMs) has re-ignited the hope that artificial intelligence (AI) systems could aid medical diagnosis. Yet despite dazzling benchmark scores, LLM assistants have yet to deliver measurable improvements at the bedside. This scoping review aims to highlight the areas where AI is limited to make practical contributions in the clinical setting, specifically in dementia diagnosis and care. Standalone machine-learning models excel at pattern recognition but seldom provide actionable, interpretable guidance, eroding clinician trust. Adjacent use of LLMs by physicians did not result in better diagnostic accuracy or speed. Key limitations trace to the data-driven paradigm: black-box outputs which lack transparency, vulnerability to hallucinations, and weak causal reasoning. Hybrid approaches that combine statistical learning with expert rule-based knowledge, and involve clinicians throughout the process help bring back interpretability. They also fit better with existing clinical workflows, as seen in examples like PEIRS and ATHENA-CDS. Future decision-support should prioritise explanatory coherence by linking predictions to clinically meaningful causes. This can be done through neuro-symbolic or hybrid AI that combines the language ability of LLMs with human causal expertise. AI researchers have addressed this direction, with explainable AI and neuro-symbolic AI being the next logical steps in further advancement in AI. However, they are still based on data-driven knowledge integration instead of human-in-the-loop approaches. Future research should measure success not only by accuracy but by improvements in clinician understanding, workflow fit, and patient outcomes. A better understanding of what helps improve human-computer interactions is greatly needed for AI systems to become part of clinical practice.

Problem

• AI lacks transparency in dementia diagnosis and care
• Hybrid systems improve interpretability and clinical workflow
• Future AI should enhance clinician understanding and patient outcomes

Innovation

• Hybrid AI combining statistical and rule-based knowledge
• Neuro-symbolic AI integrating LLMs with human expertise
• Explainable AI prioritizing clinical interpretability