The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
Interpretable machine learning for early predicting the risk of ventilator-associated pneumonia in ischemic stroke patients in the intensive care unit
Open accessAbstract
Background: The incidence of ventilator-associated pneumonia (VAP) in ischemic stroke (IS) patients is linked to a variety of detrimental outcomes. Current approaches for the early identification of individuals at high risk for developing VAP are limited and often lack clinical interpretability. The goal of this study is to develop and validate an interpretable machine learning (ML) model for early predicting VAP risk in IS patients in the intensive care unit (ICU). Methods: Data on IS patients were extracted from versions 2.2 and 3.0 of the Medical Information Mart for Intensive Care-IV database, with version 2.2 being used for model training and internal validation and version 3.0 for external testing. The primary outcome was the incidence of VAP post-ICU admission. The Boruta algorithm was used to select features prior to developing 10 ML models. The Shapley Additive Explanation (SHAP) method was employed to assess the global and local interpretability of the model’s decision-making process. The final model and Streamlit were used for developing and launching an online web application. Results: A total of 419 IS patients were included, with 401 in the derivation and 118 in the test group. Following feature selection, seven clinical characteristics were incorporated in the ML model: systolic and diastolic blood pressure, international normalized ratio, length of stay before mechanical ventilation, dysphagia, antibiotic counts and suctioning counts. Among the 10 evaluated ML models, the Random Forest (RF) model outperformed the others, achieving an internal validation AUC of 0.776, accuracy of 0.704, sensitivity of 0.900, and specificity of 0.588. In external testing, performance dropped to an AUC of 0.644, accuracy of 0.610, sensitivity of 0.688, and specificity of 0.519, raising concerns about the model’s generalizability. Conclusion: The RF model is reliable in early identifying high-risk IS patients for VAP. The SHAP method offers clear and intuitive explanations for individual risk assessment. The web-based tool has the potential to improve clinical outcomes by promptly recognizing patients at increased VAP risk and facilitating early intervention, further multicenter prospective studies are required to validate its generalizability and practical utility.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures






Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Feature Selection with the Boruta Package
Kursa, M. B., & Rudnicki, W. R. (2010) · Journal of Statistical Software · doi:10.18637/jss.v036.i11 · Cited by 5,659 · cited 1×
“By iteratively eliminating features that do not outperform their shadow counterparts, the algorithm robustly identifies truly informative features (12).”
Collins, G. S., Moons, K. G. M., Dhiman, P., Riley, R. D., Beam, A. L., Van Calster, B., Ghassemi, M., Liu, X., Reitsma, J. B., van Smeden, M., et al. (2024) · BMJ · doi:10.1136/bmj-2023-078378 · Cited by 4,718
MIMIC-IV, a freely accessible electronic health record dataset
Johnson, A. E. W., Bulgarelli, L., Shen, L., Gayles, A., Shammout, A., Horng, S., Pollard, T. J., Hao, S., Moody, B., Gow, B., et al. (2023) · Scientific Data · doi:10.1038/s41597-022-01899-x · Cited by 3,401
World Stroke Organization (WSO): Global Stroke Fact Sheet 2022
Feigin, V. L., Brainin, M., Norrving, B., Martins, S., Sacco, R. L., Hacke, W., Fisher, M., Pandian, J., & Lindsay, P. (2022) · International Journal of Stroke · doi:10.1177/17474930211065917 · Cited by 2,979 · cited 1×
“According to World Stroke Organization statistics for 2022, stroke continues to be the second leading cause of mortality and the third leading cause of disability worldwide, thereby posing a significant threat to public health (1).”
Dysphagia After Stroke: Incidence, Diagnosis, and Pulmonary Complications
Martino, R., Foley, N., Bhogal, S., Diamant, N., Speechley, M., & Teasell, R. (2005) · Stroke · doi:10.1161/01.str.0000190056.76543.eb · Cited by 1,973 · cited 1×
“Recent studies have further confirmed that stroke-related dysphagia significantly increases the risk of pulmonary infection, underscoring the clinical importance of early dysphagia screening in stroke patients (22, 23).”
Torres, A., Niederman, M. S., Chastre, J., Ewig, S., Fernandez-Vandellos, P., Hanberger, H., Kollef, M., Li Bassi, G., Luna, C. M., Martin-Loeches, I., et al. (2017) · European Respiratory Journal · doi:10.1183/13993003.00582-2017 · Cited by 1,387 · cited 1×
“According to current guidelines on VAP treatment (32), prophylactic antibiotic use is generally not recommended to prevent VAP, due to the risk of long-term or unnecessary antibiotic use fostering resistant bacterial strains, increasing the burden of antibiotic resistance for both patients and…”
Ventilator-associated pneumonia in adults: a narrative review
Papazian, L., Klompas, M., & Luyt, C.-E. (2020) · Intensive Care Medicine · doi:10.1007/s00134-020-05980-0 · Cited by 1,010 · cited 1×
“Stroke patients undergoing MV are at increased risk for a serious pulmonary complication known as ventilator-associated pneumonia (VAP), which may have a devastating impact on their respiratory function and overall prognosis (3).”
Complications and Outcome After Acute Stroke: Does Dysphagia Matter?
Smithard, D. G., O'Neill, P. A., Park, C., Morris, J., Wyatt, R., England, R., & Martin, D. F. (1996) · Stroke · doi:10.1161/01.str.27.7.1200 · Cited by 734 · cited 1×
“Stroke patients often experience dysphagia, with incidence rates ranging from 30 to 50% (15, 16).”
Hilkens, N. A., Casolla, B., Leung, T. W., & de Leeuw, F.-E. (2024) · The Lancet · doi:10.1016/s0140-6736(24)00642-1 · Cited by 681 · cited 1×
“Ischemic stroke (IS) is the most prevalent type, accounting for 60%–70% of all instances (2).”
Johnson, A., Bulgarelli, L., Pollard, T., Gow, B., Moody, B., Horng, S., Celi, L. A., & Mark, R. (2024) · PhysioNet · doi:10.13026/07hj-2a80 · Cited by 524
Cited by
Cao, H., Gui, L., Wei, J., Zheng, M., Cheng, M., & Ning, C. (2025) · BMC Cardiovascular Disorders · doi:10.1186/s12872-025-05231-4 · Cited by 4
Self-citationZarantonello, F., De Cassai, A., Pettenuzzo, T., Sella, N., Mormando, G., Bolzon, A., Fulvio, G. A., Bertoncello, C. A., & Boscolo, A. (2026) · Korean journal of anesthesiology · doi:10.4097/kja.251142 · Cited by 3
“Although 41.1% of the studies reported EHR integration, only 10.7% achieved a combination of EHR connectivity and real-time deployment [14,18,21,29,50,52,54,58,76,78,86,108], confirming that data access alone does not ensure operational availability.”
InfluentialHajikarimloo, B., Mohammadzadeh, I., Tos, S. M., Hashemi, R., Khoshrou, A., Amjadzadeh, M., Dehghan, M., Aghajan, S., Goudarzi, E., Najari, D., et al. (2026) · Neurocritical Care · doi:10.1007/s12028-026-02450-1 · Cited by 3
Li, C., Zhang, T., Chen, H., Wang, S., Wang, L., Huan, Y., Liu, J., & Liu, L. (2026) · Frontiers in Neurology · doi:10.3389/fneur.2026.1848730 · Cited by 1
“The SHAP (Shapley Additive Explanations) method, grounded in cooperative game theory, was employed to interpret the optimal model (15).”
Zhang, Y., Lin, M., Zhou, Y.-X., Lin, X., Wei, Y., Li, B., Li, J., Luo, H., Deng, Y., Qin, Z., et al. (2026) · Frontiers in Neurology · doi:10.3389/fneur.2026.1666960
“Although existing tools (e.g., Bayesian networks or machine learning models) improve prediction performance, they lack interpretability, failing to clarify the mechanisms of key risk factors (e.g., inflammatory indices or respiratory function parameters) (20).”
Metadata
- Authors
- Cao, H., Wei, J., Hua, P., & Yang, S.
- Affiliations
- Sun Yat-sen University (CN)
- First Affiliated Hospital of Guangzhou University of Chinese Medicine (CN)
- Corresponding author
- Hua, Ping
- Yang, Songran
- Venue
- Frontiers in Neurology
- Publisher
- Frontiers Media SA
- Published
- 2025-05-07
- Volume
- 16
- Pages
- 1513732-1513732
- ISSN
- 1664-2295 (ISSN-L)
- PMC
- PMC12092222
- OpenAlex
- W4410184250
- Cited by
- 7
- References
- 34
- Citations by year
- 2026: 6 · 2025: 1
- FWCI
- 5.71
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Neurology (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (201704030032, 81771165)
- Topics
- Health Sciences › Medicine › Critical Care and Intensive Care Medicine › Nosocomial Infections in ICU
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- ventilator-associated pneumonia, ischemic stroke, risk prediction, intensive care unit, model interpretability, SHAP, random forest, MIMIC-IV, dysphagia, mechanical ventilation, antibiotic use, blood pressure, international normalized ratio
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Interpretable machine learning for early predicting the risk of ventilator-associated pneumonia in ischemic stroke patients in the intensive care unit. https://app.cochat.ai/papers/10.3389/fneur.2025.1513732
- The paper
- Cao, H., Wei, J., Hua, P., & Yang, S. (2025). Interpretable machine learning for early predicting the risk of ventilator-associated pneumonia in ischemic stroke patients in the intensive care unit. Frontiers in Neurology. https://doi.org/10.3389/fneur.2025.1513732
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.