Neuro-Symbolic AI for Alzheimer's Disease: Physics-Informed Biomarker Prediction and Verifiable Intervention Planning

David Scott Lewis, Enrique Zueco

Keywords: neuro-symbolic ai, alzheimer's disease, biomarker trajectories, at(n) framework, fourier neural operators, physics-informed learning, answer set programming, asp, temporal logic, smt solving, intervention planning, causal reasoning, precision medicine, formal verification, autoformalization, clinical decision support

TL;DR: Neuro-symbolic AI combines Fourier Neural Operators with ASP and SMT solvers to forecast AT(N) biomarker cascades and generate safety-verified treatment plans, enabling fast, explainable intervention planning in Alzheimer’s disease.

Abstract: Alzheimer's disease intervention planning requires both predictive modeling of biomarker trajectories and counterfactual reasoning about treatment timing. We propose a neuro-symbolic architecture that integrates Fourier Neural Operators (FNOs) for physics-informed biomarker prediction with Answer Set Programming (ASP) and SMT solving for verifiable intervention planning. Our approach adapts FNO methods to learn surrogate operators for AT(N) biomarker cascade dynamics, enabling fast multi-year trajectory forecasting while preserving cascade constraints. The symbolic layer formalizes clinical knowledge using first-order logic and temporal logic rules, allowing ASP/s(CASP) to generate candidate intervention strategies that are verified against safety properties using Z3 SMT solving. This combination provides both the predictive power of deep learning and the formal guarantees of symbolic reasoning, addressing critical translational challenges in precision medicine for Alzheimer's disease.

Submission Number: 92