Journal article · 2026 · Open access

Knowledge-Augmented Large Language Model for Multimodal Electronic Health Record–Based Risk Prediction: Development and Validation Study

Rituparna Datta, Jiaming Cui, Zihan Guan, Vishal Reddy, Joshua C. Eby, Gregory R. Madden, Rupesh Silwal, Anil Kumar S. Vullikanti

JMIR AI, 5, e88356 · Published 7 April 2026 · DOI 10.2196/88356

Open full textCite this paper

In brief

“Knowledge-Augmented Large Language Model for Multimodal Electronic Health Record–Based Risk Prediction: Development and Validation Study” is a 2026 journal article by Rituparna Datta and 7 co-authors, published in JMIR AI. OpenAlex counts 7 citations as of 19 November 2026, which puts it in the top 2% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at JMIR AI.

Citations
7
Most cited in
2026 (7)
Field-weighted impact
7.57
References
54
Authors
8

Abstract

Background Accurate clinical outcome prediction using electronic health records (EHRs) is crucial for patient care and resource allocation. EHRs include both structured data and rich, unstructured clinical notes. However, prior machine learning methods struggle with the multimodality, long context of notes, and severe class imbalance in clinical tasks. Objective This study aimed to introduce and evaluate KAMELEON (Knowledge-Augmented Multimodal EHR Learning for Outcome Prediction), a unified, 2-stage hybrid framework that integrates diverse EHR modalities and external biomedical knowledge to enhance clinical risk prediction. Methods This study used the publicly available, deidentified Medical Information Mart for Intensive Care-III dataset, which includes structured and unstructured data for over 40,000 intensive care unit patients. The 2 tasks studied were 30-day readmission (403/10,031, 4% positive rate) and in-hospital mortality prediction (2423/17,903, 13% positive rate). Train-test splits were patient-disjoint (80:20). Performance was evaluated against general and medical large language models (LLMs) and structured baselines. Key metrics included the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and macro F1-score. Results The KAMELEON framework consistently outperformed all existing baselines. 30-day readmission: the KAMELEON-balanced random forests model achieved an AUROC of 0.85 and a sensitivity (recall) of 0.79. Ablation analysis shows the critical role of the LLM-generated reasoning, with its removal causing the AUROC to drop from 0.85 to 0.7 and sensitivity to fall by over 80%. In-hospital mortality: the KAMELEON-extreme gradient boosting model achieved an AUROC of 0.92 and an AUPRC of 0.650. Unstructured-only models showed limited ability to discern mortality, with AUROC values near chance (around 0.51-0.53). Conclusions To our knowledge, KAMELEON represents one of the first systematic frameworks to enhance LLMs for health care prediction through graph-guided knowledge retrieval combined with structured machine learning. The framework demonstrates superior performance across both prediction tasks, highlighting the synergistic value of combining diverse data modalities and LLM reasoning for robust clinical risk estimation.

Cite this paper

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

APA 7

Datta, R., Cui, J., Guan, Z., Reddy, V., Eby, J. C., Madden, G. R., Silwal, R., & Vullikanti, A. K. S. (2026). Knowledge-Augmented Large Language Model for Multimodal Electronic Health Record–Based Risk Prediction: Development and Validation Study. JMIR AI, 5, e88356. https://doi.org/10.2196/88356

MLA 9

Datta, Rituparna, et al. “Knowledge-Augmented Large Language Model for Multimodal Electronic Health Record–Based Risk Prediction: Development and Validation Study.” JMIR AI, vol. 5, 2026, p. e88356. https://doi.org/10.2196/88356.

Chicago

Datta, Rituparna, Jiaming Cui, Zihan Guan, Vishal Reddy, Joshua C. Eby, Gregory R. Madden, Rupesh Silwal, and Anil Kumar S. Vullikanti. 2026. “Knowledge-Augmented Large Language Model for Multimodal Electronic Health Record–Based Risk Prediction: Development and Validation Study.” JMIR AI 5: e88356. https://doi.org/10.2196/88356.

Harvard

Datta, R. et al. (2026) ‘Knowledge-Augmented Large Language Model for Multimodal Electronic Health Record–Based Risk Prediction: Development and Validation Study’, JMIR AI, 5, p. e88356. doi:10.2196/88356.

IEEE

R. Datta et al., “Knowledge-Augmented Large Language Model for Multimodal Electronic Health Record–Based Risk Prediction: Development and Validation Study,” JMIR AI, vol. 5, p. e88356, 2026, doi: 10.2196/88356.

BibTeX

@article{datta2026knowledge,
  title     = {{Knowledge-Augmented Large Language Model for Multimodal Electronic Health Record–Based Risk Prediction: Development and Validation Study}},
  author    = {Datta, Rituparna and Cui, Jiaming and Guan, Zihan and Reddy, Vishal and Eby, Joshua C. and Madden, Gregory R. and Silwal, Rupesh and Vullikanti, Anil Kumar S.},
  journal   = {JMIR AI},
  year      = {2026},
  volume    = {5},
  pages     = {e88356},
  doi       = {10.2196/88356},
  url       = {https://doi.org/10.2196/88356}
}

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

  • clinical risk prediction
  • 30-day readmission prediction
  • in-hospital mortality prediction
  • intensive care unit patients
  • unstructured clinical notes
  • class imbalance
  • MIMIC-III

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?

Datta, R., Cui, J., Guan, Z., Reddy, V., Eby, J. C., Madden, G. R., Silwal, R., & Vullikanti, A. K. S. (2026). Knowledge-Augmented Large Language Model for Multimodal Electronic Health Record–Based Risk Prediction: Development and Validation Study. JMIR AI, 5, e88356. https://doi.org/10.2196/88356

How many times has this paper been cited?

7 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 at JMIR AI: sign in and open the full text from this page.

Who wrote this paper?

Rituparna Datta, Jiaming Cui, Zihan Guan, Vishal Reddy, Joshua C. Eby, Gregory R. Madden, Rupesh Silwal, Anil Kumar S. Vullikanti.

What is the DOI of this paper?

10.2196/88356, permanently at https://doi.org/10.2196/88356. 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.