Currently submitted to: Transfer Hub (manuscript eXchange)
Date Submitted: Nov 9, 2025
Open Peer Review Period: Nov 10, 2025 - Jan 5, 2026
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Network Modeling of Sleep Symptom Relations Assisted by Large Language Models: Collective Latent Space Network Analysis for a Proof-of-Concept Study
ABSTRACT
Background:
The analysis of symptom relationship is clinically essential in sleep medicine. Network modeling for sleep symptoms offers an interesting perspective to model and quantify symptom architecture. Notably, the perceived causal networks (PECAN) method represents a way to systematically collect how individuals themselves perceive the causal influence of their symptoms. However, its applicability remains limited by the difficulty of collecting data from a large number of subjects.
Objective:
Based on the “theorAIzer” framework, we developed a LLM-based PECAN using a pretrained large language model (LLM) to evaluate perceived causal relationships between sleep symptoms. We hypothesized that the causal structure derived from large corpora could support the systematic mapping of symptom interrelations within a collective latent space, by mobilizing this distributed memory through network analysis.
Methods:
Twenty-nine sleep symptoms were selected. Using the theorAIzer framework with prompt ensembling, a pretrained LLM (ChatGPT, July 2025 version; OpenAI) was queried to assess perceived causal relations by determining directionality, weight, and valence. Networks were visualized after regularization with graphical LASSO and model selection by eBIC; strength-type centrality was calculated, and robustness assessed with bootstrap resampling (N = 2,000).
Results:
The LLM-based PECAN comprised 29 nodes and 46 directed, weighted and valenced edges. Insomnia maintaining, insomnia initiating, and insomnia early were strongly linked to non-restorative sleep (respectively at w=0.77, 0.75, 0.68), which in turn had cascading effects on daytime sleepiness (w=0.70) and fatigue (w=0.72). Centrality analysis revealed hub-like symptoms such as non-restorative sleep (z=3.16), daytime sleepiness (z=1.96), fatigue (z=1.86), cognitive symptoms (z=1.84), and sleep inertia (z=1.32). Network robustness analysis indicated a stability coefficient of 0.55, supporting robustness of edges and centrality metrics.
Conclusions:
The resulting network reproduced well-established associations between sleep symptoms observed in clinical and epidemiological studies. In the future, the comparison between collective LLM-based and individualized PECAN networks could allow more precise modeling of a digital twin of a specific patient grounded in perceived causal networks of sleep symptoms. Clinical Trial: Not applicable
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.