Previously submitted to: JMIR Medical Informatics (no longer under consideration since Aug 07, 2026)
Date Submitted: Jul 28, 2026
Open Peer Review Period: Aug 7, 2026 - Aug 7, 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 Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).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Warning: This is an author submission that is not peer-reviewed or edited.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.
Development and external validation of a machine learning model for early prediction of malnutrition risk in elderly critically ill patients with heart failure: A Multicenter Study Using MIMIC-IV and eICU-CRD
ABSTRACT
Background:
Malnutrition is highly prevalent among elderly critically ill patients with heart failure (HF) and is associated with prolonged mechanical ventilation and elevated mortality. Early and accurate identification of malnutrition risk is essential for timely intervention and individualized treatment.
Objective:
This study aimed to develop and externally validate an interpretable machine learning (ML) model for the early prediction of malnutrition risk in elderly critically ill patients with HF.
Methods:
This retrospective study drew on two data sources: MIMIC-IV as the training cohort, randomly split into training and internal validation sets, and eICU-CRD as the external validation cohort. High malnutrition risk was defined as a modified Nutrition Risk in Critically Ill (mNUTRIC) score ≥ 5. A total of 41 clinical features collected within the first 24 hours of intensive care unit (ICU) admission were initially screened. After multicollinearity assessment and feature selection, 15 features were ultimately retained for model construction. The candidate feature list was frozen at this point. Ten ML algorithms were compared, and model performance was primarily evaluated by AUROC. SHapley Additive exPlanations (SHAP) were used to assess feature importance and model interpretability.
Results:
The training cohort included 6,833 patients, of whom 57.4% were at high malnutrition risk; the external validation cohort comprised 3,309 patients (41.5% high risk). Among all models, XGBoost demonstrated the best discriminative performance. The final 15-feature model achieved an AUROC of 0.934 (95% CI: 0.921-0.945) on internal validation and 0.917 (95% CI: 0.908-0.926) on external validation. A Streamlit-based web application was developed for clinical deployment.
Conclusions:
We developed and externally validated an interpretable XGBoost model that accurately predicted malnutrition risk in elderly critically ill patients with HF using routinely available features, and deployed a web-based tool enabling real-time risk stratification at the point of care.
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.