A Computational Ethical Framework for Financial Digital Phenotyping for Mental Health
2026-07-27 • Logic in Computer Science
Logic in Computer ScienceArtificial IntelligenceComputers and Society
AI summaryⓘ
The authors address the challenge of making sure AI systems, especially those analyzing personal behavior data (digital phenotyping), follow ethical rules not just on paper but in real-time. They created a system where ethical rules are written clearly using special logic and an 'ethical agent' watches over the AI to ensure it behaves correctly. They tested their idea using mental health and financial data and confirmed their system can detect and prevent ethical violations automatically. The authors note that while this is promising, real-world testing and human judgment remain important.
Digital PhenotypingEthical GovernanceDeontic Temporal LogicEthical AgentZ3 SMT SolverAI EthicsFormal VerificationMachine-verifiable EthicsContinuous Ethical Checking
Authors
Oluwadara Adedeji, Michael Mayowa Farayola, Jeff Brozena, Irina Tal, Regina Connolly, Mark Matthews
Abstract
Ethical governance of AI-driven systems is often expressed through high-level principles and static documentation, creating a gap between regulatory requirements and system-level verification. This challenge is particularly acute in digital phenotyping, where continuous behavioural data raises concerns around consent, privacy, and fairness. In this paper, we propose a computational ethical framework for AI-driven digital phenotyping system in which ethical requirements are formalised as deontic temporal logic constraints, alongside a conceptual ethical agent that oversees the system and ensures that any supervised system satisfies the specified constraints. Using a case study involving financial data and mental health, we model key ethical properties and verify them using the Z3 Satisfiability Modulo Theories (SMT) solver. Our evaluation shows that the framework is logically consistent and that violations of the specified ethical properties are ruled out within the formal model through counterexample-based verification. This presents early research enabling continuous, machine-verifiable ethical checking, moving beyond retrospective compliance based on static documentation. We discuss limitations, including the need for real-world verification with data, the challenge with subjectivity and contextual sensitivity, the need for human oversight, and outline how such approaches can support the development of digital phenotyping and AI systems with continuous and auditable ethical guarantees.