JMIR Publications

ABSTRACT

Background:

Human digital twins have the potential to change the practice of personalizing cognitive health diagnosis because these systems can integrate multiple sources of health information and influences into a unified model. Cognitive health is multifaceted, yet researchers and clinical professionals struggle to align diverse sources of information into a single model.

Objective:

In this paper, we introduce a method called HDTwin, for unifying heterogeneous data using large language models. HDTwin is designed to predict cognitive diagnoses and offer explanations for its inferences.

Methods:

HDTwin integrates cognitive health data from multiple sources, including demographic, behavioral, EMA, n-back test, speech, and baseline experimenter interview markers. Data are converted into text prompts for a large language model. The system then combines these inputs with relevant external knowledge from the scientific literature to construct a predictive model. The model’s performance is validated using data from three studies involving n=124 participants, comparing its diagnostic accuracy with baseline machine learning classifiers.

Results:

HDTwin achieves an overall accuracy of 0.81, significantly outperforming baseline classifiers. The experiments also reveal that HDTwin yields superior predictive accuracy when information sources are fused compared to single sources. HDTwin’s chatbot interface provides interactive dialogues, aiding in diagnosis interpretation and allowing further exploration of patient data.

Conclusions:

HDTwin integrates diverse cognitive health data, enhancing the accuracy and explainability of cognitive diagnoses. This approach outperforms traditional models and provides an interactive interface for navigating patient information. The approach shows promise for improving early detection and intervention strategies in cognitive health. Clinical Trial: digital twin, smartwatch, digital behavior markers, large language models, text analysis, machine learning