Clinical Features and Physiological Signals Fusion Network for Mechanical Circulatory Support Need Prediction in Pediatric Cardiac Intensive Care Unit
Open accessAbstract
We link the hemodynamic response to inotropic agents with outcomes related to Mechanical Circulatory Support (MCS) by analyzing physiological time series and clinical features using a Machine Learning/Deep Learning ensemble approach for multi-modal waveforms in the pediatric cardiac intensive care setting of a quaternary-care hospital. Unlike existing studies that typically process a single feature type or focus on short-term diagnoses from physiological signals, our novel system processes minute-by-minute multi-sensor data to identify the need for MCS in patients admitted with acute decompensated heart failure. The data used includes tabular clinical features, time series from hemodynamic monitors, and raw waveforms from electrocardiogram and arterial blood pressure signals. Our predictions support an early identification of high-risk patients after just two days of Intensive Care Unit (ICU) admission, with classification and feature importance results confirming the predictive ability of the early hemodynamic response to inotropic agent administration, achieving an AUC of 0.88 in the prediction classification task. This is particularly significant in cases where clinical decisions are not straightforward, such as those in the cohort for this study.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Only a small number of studies connected multimodal predictions to clinical interventions.
“Only a small number of studies connected multimodal predictions to clinical interventions [36–39]”
From Multimodal Artificial Intelligence for Precision Critical Care: A Scoping Review (2026) · cites this paper as [39]
Late fusion combined outputs from modality-specific models without requiring explicit data-level alignment.
“whereas late fusion combined outputs from modality-specific models without requiring explicit data-level alignment [39,54–56].”
From Multimodal Artificial Intelligence for Precision Critical Care: A Scoping Review (2026) · cites this paper as [39]
Regarding missing values within individual modalities, 36 studies focused on structured data, with only one study each considering waveforms and video modality.
“Regarding missing values within individual modalities, 36 studies focused on structured data, with only one study each considering waveforms [39] and video modality [55].”
From Multimodal Artificial Intelligence for Precision Critical Care: A Scoping Review (2026) · cites this paper as [39]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569 · see citing works
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970 · see citing works
Heart Rate Variability: Standards of Measurement, Physiological Interpretation, and Clinical Use
Electrophysiology, T. F. O. T. E. S. O. C. T. N. A. (1996) · Circulation · doi:10.1161/01.cir.93.5.1043 · Cited by 17,159 · see citing works
Kuhn, M., & Johnson, K. (2013) · doi:10.1007/978-1-4614-6849-3 · Cited by 6,788 · see citing works
SGDR: Stochastic Gradient Descent with Warm Restarts
Loshchilov, I., & Hutter, F. (2016) · arXiv · doi:10.48550/arxiv.1608.03983 · Cited by 5,309 · see citing works
The Elements of Statistical Learning
Hastie, T. J., Tibshirani, R. J., & Friedman, J. H. (2009) · Springer series in statistics · doi:10.1007/b94608 · Cited by 4,111 · see citing works
Ensemble deep learning: A review
Ganaie, M. A., Hu, M., Malik, A. K., Tanveer, M., & Suganthan, P. N. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105151 · Cited by 2,282 · see citing works
Receiver operating characteristic curve: overview and practical use for clinicians
Nahm, F. S. (2022) · Korean Journal of Anesthesiology · doi:10.4097/kja.21209 · Cited by 1,569 · see citing works
Fleming, S., Thompson, M. J., Stevens, R., Heneghan, C. J., Plüddemann, A., Maconochie, I. K., Tarassenko, L., & Mant, D. (2011) · The Lancet · doi:10.1016/s0140-6736(10)62226-x · Cited by 1,287 · see citing works
Drew, B. J., Harris, P., Zègre-Hemsey, J. K., Mammone, T., Schindler, D., Salas-Boni, R., Bai, Y., Tinoco, A., Ding, Q., & Hu, X. (2014) · PLoS ONE · doi:10.1371/journal.pone.0110274 · Cited by 438 · see citing works
Review of noise removal techniques in ECG signals
Chatterjee, S., Thakur, R. S., Yadav, R. N., Gupta, L., & Raghuvanshi, D. K. (2020) · IET Signal Processing · doi:10.1049/iet-spr.2020.0104 · Cited by 335 · see citing works
Interpretable machine learning a guide for making black box models explainable
Molnar, C. (2022) · Cited by 313 · see citing works
Complications associated with mechanical circulatory support
Ali, J. M., & Abu-Omar, Y. (2020) · Annals of Translational Medicine · doi:10.21037/atm.2020.03.152 · Cited by 65 · see citing works
HyperImpute: Generalized Iterative Imputation with Automatic Model SelectionPreprint
Jarrett, D. P., Cebere, B., Liu, T., Curth, A., & van der Schaar, M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.07769 · Cited by 37 · see citing works
Early prediction of hemodynamic interventions in the intensive care unit using machine learning
Rahman, A., Chang, Y., Dong, J., Conroy, B., Natarajan, A., Kinoshita, T., Vicario, F., Frassica, J. J., & Xu-Wilson, M. (2021) · Critical Care · doi:10.1186/s13054-021-03808-x · Cited by 36 · see citing works
Clinical Presentation, Classification, and Outcomes of Cardiogenic Shock in Children
Puri, K., Jentzer, J. C., Spinner, J. A., Hope, K. D., Adachi, I., Tume, S. C., Tunuguntla, H. P., Choudhry, S., Cabrera, A. G., & Price, J. F. (2024) · Journal of the American College of Cardiology · doi:10.1016/j.jacc.2023.11.019 · Cited by 28 · see citing works
Self-citationCan machine learning improve patient selection for cardiac resynchronization therapy?
Hu, S.-Y., Santus, E., Forsyth, A. W., Malhotra, D., Haimson, J., Chatterjee, N. A., Kramer, D. B., Barzilay, R., Tulsky, J. A., & Lindvall, C. J. (2019) · PLoS ONE · doi:10.1371/journal.pone.0222397 · Cited by 28 · see citing works
Au-Yeung, W.-T. M., Sevakula, R. K., Sahani, A. K., Kassab, M. B., Boyer, R. B., Isselbacher, E. M., & Armoundas, A. A. (2021) · European Heart Journal - Digital Health · doi:10.1093/ehjdh/ztab058 · Cited by 24 · see citing works
Yao, H., Golbus, J. R., Gryak, J., Pagani, F. D., Aaronson, K. D., & Najarian, K. (2022) · The Journal of Heart and Lung Transplantation · doi:10.1016/j.healun.2022.08.028 · Cited by 10 · see citing works
Classification of Level of Consciousness in a Neurological ICU Using Physiological Data
Gomez, L., Shen, Q., Doyle, K. W., Vrosgou, A., Velazquez, A. G., Megjhani, M., Ghoshal, S., Roh, D. J., Agarwal, S., Park, S., et al. (2022) · Neurocritical Care · doi:10.1007/s12028-022-01586-0 · Cited by 7 · see citing works
Deep Learning System for Left Ventricular Assist Device Candidate Assessment from Electrocardiograms
Mendoza, A., Cavallaro, J. R., & Razavi, M. (2023) · Computing in cardiology · doi:10.22489/cinc.2023.180 · Cited by 2 · see citing works
Self-citationPredicting Readmission of Heart Failure Patients
Koscova, Z., Vargova, E., Pavlus, J., Smíšek, R., Viščor, I., Bulková, V., & Plešinger, F. (2023) · Computing in cardiology · doi:10.22489/cinc.2023.207 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Multimodal Artificial Intelligence for Precision Critical Care: A Scoping Review
Yang, M., Shi, N., Chen, H., Po, E. Y. P., Ng, P. Y., Lai, P. C. K., Wu, Y.-C., & Fong, D. Y. T. (2026) · Health Data Science · doi:10.34133/hds.0356 · Cited by 3 · see citing works
“…storage requirements and their primary relevance to specific clinical tasks, such as neurological outcome prediction with EEG [ 19 , 52 , 53 , 56 , 61 ] or MRI [ 19 , 52 ], pneumonia detection via chest x-ray [ 62 , 63 ], and forecasting mechanical circulatory support needs from ECG and ABP [ 39 ].”
InfluentialRucks, N., Korlakov, S., Scharf, S. A., Rommerskirchen, A., Haas, R. R., & Conrad, S. (2026) · Scientific Reports · doi:10.1038/s41598-026-57782-x · Cited by 1 · see citing works
Predicting adolescent depression: an interpretable machine learning model
Chen, X., Yang, B., Han, L., Li, X., Jin, W., Xie, Z., Tao, M., Chen, Y., Gu, Y., Solomon, O. M., et al. (2026) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-026-03482-5
Ji, Q., Wu, Y. J., Yang, M., Liu, J. L., Zhang, X., Lin, Y., & Hu, W. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2026.1874474
- Authors
- Mendoza, A., Tume, S., Puri, K., Acosta, S., & Cavallaro, J. R.
- Affiliations
- Rice University (US)
- Baylor College of Medicine (US)
- Venue
- IEEE Journal of Biomedical and Health Informatics
- Published
- 2025-02
- Volume
- 29
- Issue
- 2
- Pages
- 783-791
- ISSN
- 2168-2194 (ISSN-L)
- 2168-2208
- PMC
- PMC11970999
- OpenAlex
- W4404914602
- Cited by
- 4
- References
- 22
- Citations by year
- 2026: 4
- FWCI
- 0.59
- Type
- journal article
- Language
- en
- Open access
- green
- pmc.ncbi.nlm.nih.gov
- Licence
- Locations
- IEEE Journal of Biomedical and Health Informatics (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (publishedVersion)
- Europe PMC (PubMed Central) (acceptedVersion)
- Funders
- DOD (HT9425-23-1-0663)
- NIH (1R01HL166724-01A1)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Physical Sciences › Engineering › Biomedical Engineering › Mechanical Circulatory Support Devices
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- mechanical circulatory support, pediatric cardiac intensive care, acute decompensated heart failure, inotropic agents, hemodynamic response, electrocardiogram, arterial blood pressure, early risk detection, ensemble learning, feature importance
- MeSH terms
- Machine Learning, Deep Learning, Adolescent, Child, Child, Preschool, Electrocardiography, Female, Heart Failure, Heart-Assist Devices, Hemodynamics, Humans, Infant, Male, Signal Processing, Computer-Assisted, Intensive Care Units, Pediatric
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
