Preprint · 2026 · Open access

GHI-LLM: A Generalizable Framework for Structured Multimodal Health Inference with Large Language Models (Preprint)

Rafael Trujillo, Christian Poellabauer

Published 19 February 2026 · DOI 10.2196/preprints.93827

Open full textCite this paper

In brief

“GHI-LLM: A Generalizable Framework for Structured Multimodal Health Inference with Large Language Models (Preprint)” is a 2026 preprint by Rafael Trujillo and Christian Poellabauer. OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read.

Citations
0
References
36
Authors
2

Abstract

BACKGROUND Traditional machine learning approaches for health prediction require fixed input schemas and predefined tasks, limiting their applicability across heterogeneous datasets with varying study populations, collection protocols, and survey instruments. These constraints are particularly problematic in clinical settings where electronic health records and patient histories exhibit substantial structural variability. OBJECTIVE To develop and evaluate the GHI-LLM (Generalizable Health Inference with Large Language Models) framework, a generalizable prompting framework that enables large language models to perform zero-shot inference over heterogeneous multimodal health data without task-specific fine-tuning or prompt redesign across multiple health constructs, datasets, and task formulations. METHODS The framework was evaluated across three datasets: NetHealth (n=193 post-filtering), breast cancer survivors (n=50), and chronic pain patients (n=24). Wearable-derived features included circadian rhythm metrics, aggregate hourly activity, and sleep metrics. Three health constructs were assessed: depressive symptoms (CES-D), sleep quality (PSQI), and perceived stress (PSS). Eight experimental tasks spanning three task groups were designed: within-cohort percentile classification, longitudinal direction-of-change prediction, and cross-dataset pairwise comparisons. Six large language models were evaluated (Gemini 2.5 Flash, Gemini 2.5 Flash-Lite, GPT-4o-Mini, GPT-5-Mini, LLaMA-3.3-70B, LLaMA-2-70B) using zero-shot prompting augmented with z-scores, leave-one-out correlations, and embedded interpretation guides. RESULTS Frontier models achieved above-chance performance across all task types. For CES-D direction-of-change prediction at the highest difficulty level (n=97), GPT-5-Mini achieved balanced accuracy of 0.69 (95% CI 0.59-0.79), improving to 0.84 (95% CI 0.73-0.95) at lower difficulty (n=38). Within-cohort CES-D percentile classification reached 0.81 (95% CI 0.75-0.86) for GPT-5-Mini at baseline (n=193), increasing to 0.95 (95% CI 0.91-0.99) with stricter filtering (n=51). Cross-dataset pairwise comparisons showed score-band-dependent performance: CES-D comparisons achieved 0.97 balanced accuracy (95% CI 0.95-0.99) for GPT-5-Mini at the widest score difference band (21-60 points, n=268) compared to 0.57 (95% CI 0.53-0.62) at narrow bands (1-5 points, n=494). Performance varied systematically by construct, with CES-D tasks consistently outperforming PSS and PSQI tasks. LLaMA models failed to exceed chance on percentile and pairwise tasks but achieved modest success on direction-of-change tasks. CONCLUSIONS GHI-LLM demonstrates that domain-agnostic, task-agnostic health inference is achievable through structured zero-shot prompting alone, enabling reasoning across heterogeneous datasets with partially overlapping inputs. Performance scaled consistently with task difficulty and varied meaningfully across health constructs, suggesting genuine structured reasoning rather than artifact exploitation. These findings support the potential of LLMs as flexible intermediaries for multimodal health data interpretation in research contexts, though careful empirical validation remains essential before deployment.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Trujillo, R., & Poellabauer, C. (2026). GHI-LLM: A Generalizable Framework for Structured Multimodal Health Inference with Large Language Models (Preprint). https://doi.org/10.2196/preprints.93827

MLA 9

Trujillo, Rafael, and Christian Poellabauer. “GHI-LLM: A Generalizable Framework for Structured Multimodal Health Inference with Large Language Models (Preprint).” 2026. https://doi.org/10.2196/preprints.93827.

Chicago

Trujillo, Rafael and Christian Poellabauer. 2026. “GHI-LLM: A Generalizable Framework for Structured Multimodal Health Inference with Large Language Models (Preprint).” https://doi.org/10.2196/preprints.93827.

Harvard

Trujillo, R. and Poellabauer, C. (2026) ‘GHI-LLM: A Generalizable Framework for Structured Multimodal Health Inference with Large Language Models (Preprint)’. doi:10.2196/preprints.93827.

IEEE

R. Trujillo and C. Poellabauer, “GHI-LLM: A Generalizable Framework for Structured Multimodal Health Inference with Large Language Models (Preprint),” 2026, doi: 10.2196/preprints.93827.

BibTeX

@misc{trujillo2026generalizable,
  title     = {{GHI-LLM: A Generalizable Framework for Structured Multimodal Health Inference with Large Language Models (Preprint)}},
  author    = {Trujillo, Rafael and Poellabauer, Christian},
  year      = {2026},
  doi       = {10.2196/preprints.93827},
  url       = {https://doi.org/10.2196/preprints.93827}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare

  • large language models
  • zero-shot prompting
  • circadian rhythm
  • sleep metrics
  • physical activity
  • depressive symptoms
  • sleep quality
  • perceived stress

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Trujillo, R., & Poellabauer, C. (2026). GHI-LLM: A Generalizable Framework for Structured Multimodal Health Inference with Large Language Models (Preprint). https://doi.org/10.2196/preprints.93827

How many times has this paper been cited?

0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: sign in and open the full text from this page.

Who wrote this paper?

Rafael Trujillo, Christian Poellabauer.

What is the DOI of this paper?

10.2196/preprints.93827, permanently at https://doi.org/10.2196/preprints.93827. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.