Utilizing Sequential Information of General Lab-test Results and Diagnoses History for Differential Diagnosis of Dementia

TL;DR

This paper introduces a novel method that leverages routine lab test sequences and advanced deep learning models to improve early and differential diagnosis of Alzheimer's Disease, addressing data variability and accessibility issues.

Contribution

It proposes modeling lab test histories as sequences and applying word embedding and deep time series models for better AD diagnosis, a novel approach in this context.

Findings

Enhanced diagnostic accuracy for AD.

Scalable and cost-effective screening method.

Effective modeling of temporal lab test patterns.

Abstract

Early diagnosis of Alzheimer's Disease (AD) faces multiple data-related challenges, including high variability in patient data, limited access to specialized diagnostic tests, and overreliance on single-type indicators. These challenges are exacerbated by the progressive nature of AD, where subtle pathophysiological changes often precede clinical symptoms by decades. To address these limitations, this study proposes a novel approach that takes advantage of routinely collected general laboratory test histories for the early detection and differential diagnosis of AD. By modeling lab test sequences as "sentences", we apply word embedding techniques to capture latent relationships between tests and employ deep time series models, including long-short-term memory (LSTM) and Transformer networks, to model temporal patterns in patient records. Experimental results demonstrate that our approach improves diagnostic accuracy and enables scalable and costeffective AD screening in diverse clinical settings.