Beyond Accuracy: Latent Perturbations for Cognitive-Aware Diagnosis

Abstract

Diagnosing rare diseases remains a persistent challenge, often hindered by *cognitive anchoring*: once clinicians settle on a common diagnosis, they often discount alternative explanations, including rare conditions. To address this, we propose a human-centered counterfactual reasoning framework using a Denoising Masked AutoEncoder (DMAE) to simulate *what-if* diagnostic scenarios that disrupt clinicians’ initial assumptions. Our model jointly learns (1) the true distribution of diseases and symptoms, and (2) human diagnostic behavior, revealing critical gaps between *medically possible* and *clinically considered* diagnoses. By strategically perturbing latent patient representations, it generates *contrastive counterfactuals* that highlight rare yet plausible diseases that cognitive bias often obscures. Unlike traditional decision-support tools, our system *proactively* suggests rare diseases not because they are statistically probable, but because they are *cognitively neglected*. Across four public and three private rare-disease datasets, our approach outperforms standard machine learning classifiers in detecting rare conditions while maintaining strong performance on common diagnoses. Beyond boosting accuracy, the counterfactual evidence encourages *hypothesis-driven reasoning* and supports clinical learning.