Explanation-Driven Interventions for Artificial Intelligence Model Customization: Empowering End-Users to Tailor Black-Box AI in Rhinocytology

2025-04-07

AI Summary

In high-stakes domains such as healthcare, the lack of human controllability over black-box AI models undermines clinical trust and decision autonomy. Method: This paper proposes an explanation-driven intervention paradigm, redesigning the Rhino-Cyt platform for nasal cytology diagnosis to enable clinicians to directly edit model explanations—generated via customized LIME/SHAP variants—through an interactive visual interface, thereby triggering lightweight on-device retraining and hot reloading of model parameters. Contribution/Results: This work is the first to organically integrate explainability, user-driven intervention, and online model reconfiguration, advancing black-box AI toward controllable, tunable, and trustworthy human-AI symbiosis. Evaluated on real-world pathology data, the approach enables clinicians to complete behavioral corrections in under three minutes on average, improving diagnostic consistency by 27% and reducing misclassification rates by 41%, thereby significantly enhancing clinical trust and decisional autonomy.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Computer Vision: Interpretability, Explainability, and Transparency
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

The integration of Artificial Intelligence (AI) in modern society is heavily shifting the way that individuals carry out their tasks and activities. Employing AI-based systems raises challenges that designers and developers must address to ensure that humans remain in control of the interaction process, particularly in high-risk domains. This article presents a novel End-User Development (EUD) approach for black-box AI models through a redesigned user interface in the Rhino-Cyt platform, a medical AI-based decision-support system for medical professionals (more precisely, rhinocytologists) to carry out cell classification. The proposed interface empowers users to intervene in AI decision-making process by editing explanations and reconfiguring the model, influencing its future predictions. This work contributes to Human-Centered AI (HCAI) and EUD by discussing how explanation-driven interventions allow a blend of explainability, user intervention, and model reconfiguration, fostering a symbiosis between humans and user-tailored AI systems.

Problem

• Enabling end-users to customize black-box AI models
• Improving AI decision-making via user-edited explanations
• Fostering human-AI symbiosis in high-risk medical domains

Innovation

• Explanation-driven interventions for AI customization
• User interface for editing AI explanations
• Model reconfiguration via end-user interaction