Clinically Meaningful Explainability for NeuroAI: An ethical, technical, and clinical perspective

• URL: http://arxiv.org/abs/2603.18028v1
• Date: Fri, 06 Mar 2026 10:16:31 GMT
• Title: Clinically Meaningful Explainability for NeuroAI: An ethical, technical, and clinical perspective
• Abstract summary: We argue that clinically meaningful explainability is essential for AI-enabled closed-loop medical neurotechnology.<n>Our aim is to inform stakeholders working in neurotechnology and regulatory framework development to ensure that explainability fulfills the right needs for the right stakeholders.
• Score: 4.679326716033649
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: While explainable AI (XAI) is often heralded as a means to enhance transparency and trustworthiness in closed-loop neurotechnology for psychiatric and neurological conditions, its real-world prevalence remains low. Moreover, empirical evidence suggests that the type of explanations provided by current XAI methods often fails to align with clinicians' end-user needs. In this viewpoint, we argue that clinically meaningful explainability (CME) is essential for AI-enabled closed-loop medical neurotechnology and must be addressed from an ethical, technical, and clinical perspective. Instead of exhaustive technical detail, clinicians prioritize clinically relevant, actionable explanations, such as clear representations of input-output relationships and feature importance. Full technical transparency, although theoretically desirable, often proves irrelevant or even overwhelming in practice, as it may lead to informational overload. Therefore, we advocate for CME in the neurotechnology domain: prioritizing actionable clarity over technical completeness and designing interface visualizations that intuitively map AI outputs and key features into clinically meaningful formats. To this end, we introduce a reference architecture called NeuroXplain, which translates CME into actionable technical design recommendations for any future neurostimulation device. Our aim is to inform stakeholders working in neurotechnology and regulatory framework development to ensure that explainability fulfills the right needs for the right stakeholders and ultimately leads to better patient treatment and care.

Related papers

• Human-AI Co-design for Clinical Prediction Models [8.099095493749868]
  We introduce HACHI, an iterative human-in-the-loop framework that uses AI agents to accelerate the development of fully interpretable clinical prediction models.<n>In two real-world prediction tasks, HACHI outperforms existing approaches, surfaces new clinically relevant concepts, and improves model generalizability across clinical sites and time periods.
  arXiv  Detail & Related papers  (2026-01-14T02:04:34Z)
• Before the Clinic: Transparent and Operable Design Principles for Healthcare AI [42.994619952353396]
  We propose two foundational design principles to operationalize pre-clinical technical requirements for healthcare AI.<n>We ground these principles in established XAI frameworks, map them to documented clinician needs, and demonstrate their alignment with emerging governance requirements.<n>This pre-clinical playbook provides actionable guidance for development teams, accelerates the path to clinical evaluation, and establishes a shared vocabulary bridging AI researchers, healthcare practitioners, and regulatory stakeholders.
  arXiv  Detail & Related papers  (2025-10-31T04:05:09Z)
• From Explainability to Action: A Generative Operational Framework for Integrating XAI in Clinical Mental Health Screening [0.3181700357675698]
  This paper argues that this gap is a translation problem and proposes the Generative Operational Framework.<n>This framework is designed to ingest the raw, technical outputs from diverse XAI tools and synthesize them with clinical guidelines.
  arXiv  Detail & Related papers  (2025-10-10T05:46:39Z)
• Interpretable Neuropsychiatric Diagnosis via Concept-Guided Graph Neural Networks [56.75602443936853]
  One in five adolescents currently live with a diagnosed mental or behavioral health condition, such as anxiety, depression, or conduct disorder.<n>While prior works use graph neural network (GNN) approaches for disorder prediction, they remain black-boxes, limiting their reliability and clinical translation.<n>In this work, we propose a concept-based diagnosis framework that that encodes interpretable functional connectivity concepts.<n>Our design ensures predictions through clinically meaningful connectivity patterns, enabling both interpretability and strong predictive performance.
  arXiv  Detail & Related papers  (2025-10-02T19:38:46Z)
• Interpretable Clinical Classification with Kolgomorov-Arnold Networks [70.72819760172744]
  Kolmogorov-Arnold Networks (KANs) offer intrinsic interpretability through transparent, symbolic representations.<n>KANs support built-in patient-level insights, intuitive visualizations, and nearest-patient retrieval.<n>These results position KANs as a promising step toward trustworthy AI that clinicians can understand, audit, and act upon.
  arXiv  Detail & Related papers  (2025-09-20T17:21:58Z)
• Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications [59.721265428780946]
  Large Language Models (LLMs) in medicine have enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning.<n>This paper provides the first systematic review of this emerging field.<n>We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies and test-time mechanisms.
  arXiv  Detail & Related papers  (2025-08-01T14:41:31Z)
• Doctor-in-the-Loop: An Explainable, Multi-View Deep Learning Framework for Predicting Pathological Response in Non-Small Cell Lung Cancer [0.6800826356148091]
  Non-small cell lung cancer (NSCLC) remains a major global health challenge.<n>We propose Doctor-in-the-Loop, a novel framework that integrates expert-driven domain knowledge with explainable artificial intelligence techniques.<n>Our approach employs a gradual multi-view strategy, progressively refining the model's focus from broad contextual features to finer, lesion-specific details.
  arXiv  Detail & Related papers  (2025-02-21T16:35:30Z)
• An Introduction to Natural Language Processing Techniques and Framework for Clinical Implementation in Radiation Oncology [1.2714439146420664]
  We present state-of-the-art NLP applications that employ large language models (LLMs) in radiation oncology research. LLMs are prone to many errors such as hallucinations, biases, and ethical violations, which necessitate rigorous evaluation and validation. Our article aims to provide guidance and insights for researchers and clinicians who are interested in developing and using NLP models in clinical radiation oncology.
  arXiv  Detail & Related papers  (2023-11-03T19:32:35Z)
• Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation [116.87918100031153]
  We propose a Cross-modal clinical Graph Transformer (CGT) for ophthalmic report generation (ORG) CGT injects clinical relation triples into the visual features as prior knowledge to drive the decoding procedure. Experiments on the large-scale FFA-IR benchmark demonstrate that the proposed CGT is able to outperform previous benchmark methods.
  arXiv  Detail & Related papers  (2022-06-04T13:16:30Z)
• Counterfactual Explanations as Interventions in Latent Space [62.997667081978825]
  Counterfactual explanations aim to provide to end users a set of features that need to be changed in order to achieve a desired outcome. Current approaches rarely take into account the feasibility of actions needed to achieve the proposed explanations. We present Counterfactual Explanations as Interventions in Latent Space (CEILS), a methodology to generate counterfactual explanations.
  arXiv  Detail & Related papers  (2021-06-14T20:48:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.