Neuro-Oracle: A Trajectory-Aware Agentic RAG Framework for Interpretable Epilepsy Surgical Prognosis

TL;DR

Neuro-Oracle introduces a trajectory-aware framework combining MRI change analysis, retrieval of similar cases, and natural-language prognosis synthesis to improve epilepsy surgical outcome predictions.

Contribution

It presents a novel three-stage architecture integrating MRI trajectory encoding, case retrieval, and language-based prognosis generation for the first time.

Findings

Trajectory-based classifiers achieved AUCs between 0.834 and 0.905.

Neuro-Oracle's agent matched the AUC of discriminative classifiers at 0.867.

A Siamese ensemble attained an AUC of 0.905 without language model overhead.

Abstract

Predicting post-surgical seizure outcomes in pharmacoresistant epilepsy is a clinical challenge. Conventional deep-learning approaches operate on static, single-timepoint pre-operative scans, omitting longitudinal morphological changes. We propose \emph{Neuro-Oracle}, a three-stage framework that: (i) distils pre-to-post-operative MRI changes into a compact 512-dimensional trajectory vector using a 3D Siamese contrastive encoder; (ii) retrieves historically similar surgical trajectories from a population archive via nearest-neighbour search; and (iii) synthesises a natural-language prognosis grounded in the retrieved evidence using a quantized Llama-3-8B reasoning agent. Evaluations are conducted on the public EPISURG dataset ($N{=}268$ longitudinally paired cases) using five-fold stratified cross-validation. Since ground-truth seizure-freedom scores are unavailable, we utilize a clinical proxy label based on the resection type. We acknowledge that the network representations may potentially learn the anatomical features of the resection cavities (i.e., temporal versus non-temporal locations) rather than true prognostic morphometry. Our current evaluation thus serves mainly as a proof-of-concept for the trajectory-aware retrieval architecture. Trajectory-based classifiers achieve AUC values between 0.834 and 0.905, compared with 0.793 for a single-timepoint ResNet-50 baseline. The Neuro-Oracle agent (M5) matches the AUC of purely discriminative trajectory classifiers (0.867) while producing structured justifications with zero observed hallucinations under our audit protocol. A Siamese Diversity Ensemble (M6) of trajectory-space classifiers attains an AUC of 0.905 without language-model overhead.