An artificial intelligence tool to predict fluid requirement in the intensive care unit: a proof-of-concept study
Open accessAbstract
Introduction: The goal of personalised medicine in the intensive care unit (ICU) is to predict which diagnostic tests, monitoring interventions and treatments translate to improved outcomes given the variation between patients. Unfortunately, processes such as gene transcription and drug metabolism are dynamic in the critically ill; that is, information obtained during static non-diseased conditions may have limited applicability. We propose an alternative way of personalising medicine in the ICU on a real-time basis using information derived from the application of artificial intelligence on a high-resolution database. Calculation of maintenance fluid requirement at the height of systemic inflammatory response was selected to investigate the feasibility of this approach. Methods: The Multi-parameter Intelligent Monitoring for Intensive Care II (MIMIC II) is a database of patients admitted to the Beth Israel Deaconess Medical Center ICU in Boston. Patients who were on vasopressors for more than six hours during the first 24 hours of admission were identified from the database. Demographic and physiological variables that might affect fluid requirement or reflect the intravascular volume during the first 24 hours in the ICU were extracted from the database. The outcome to be predicted is the total amount of fluid given during the second 24 hours in the ICU, including all the fluid boluses administered. Results: We represented the variables by learning a Bayesian network from the underlying data. Using 10-fold cross-validation repeated 100 times, the accuracy of the model in predicting the outcome is 77.8%. The network generated has a threshold Bayes factor of seven representing the posterior probability of the model given the observed data. This Bayes factor translates into p < 0.05 assuming a Gaussian distribution of the variables. Conclusions: Based on the model, the probability that a patient would require a certain range of fluid on day two can be predicted. In the presence of a larger database, analysis may be limited to patients with identical clinical presentation, demographic factors, co-morbidities, current physiological data and those who did not develop complications as a result of fluid administration. By better predicting maintenance fluid requirements based on the previous day's physiological variables, one might be able to prevent hypotensive episodes requiring fluid boluses during the course of the following day.
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?
Celi et al. found that a Bayesian network model achieved a predictive accuracy of 77.8% in predicting fluid needs on ICU day two from early ICU data.
“The Bayesian network model achieved a predictive accuracy of 77.8%, demonstrating that AI-driven analysis of early ICU data can estimate subsequent fluid requirements, supporting its potential role in personalized, data-driven critical care decision-making.”
From Artificial Intelligence to Facilitate SEP-1 Measure Compliance and Fluid Management in Sepsis (2026) · cites this paper as [61]
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
Early goal-directed therapy in the treatment of severe sepsis and septic shock
Rivers, E., Nguyen, B., Havstad, S., Ressler, J., Muzzin, A., Knoblich, B., Peterson, E., & Tomlanovich, M. (2001) · New England Journal of Medicine · doi:10.1056/nejmoa010307 · Cited by 10,743 · see citing works
Statistical Decision Theory and Bayesian Analysis
Berger, J. O. (1985) · Springer Series in Statistics · doi:10.1007/978-1-4757-4286-2 · Cited by 7,722 · see citing works
Stastical Decision Theory and Bayesian Analysis.
Ghosh, M., & Berger, J. O. (1988) · Journal of the American Statistical Association · doi:10.2307/2288950 · Cited by 2,901 · see citing works
Toward Evidence-Based Medical Statistics. 2: The Bayes Factor
Goodman, S. N. (1999) · Annals of Internal Medicine · doi:10.7326/0003-4819-130-12-199906150-00019 · Cited by 913 · see citing works
Donati, A., Loggi, S., Preiser, J., Orsetti, G., Münch, C. M., Gabbanelli, V., Pelaia, P., & Pietropaoli, P. (2007) · CHEST Journal · doi:10.1378/chest.07-0621 · Cited by 316 · see citing works
Schurink, C. A. M., Lucas, P., Hoepelman, A. I. M., & Bonten, M. J. M. (2005) · The Lancet Infectious Diseases · doi:10.1016/s1473-3099(05)70115-8 · Cited by 100 · see citing works
Long-term outcomes from sepsis
Yende, S. P., & Angus, D. C. (2007) · Current Infectious Disease Reports · doi:10.1007/s11908-007-0059-3 · Cited by 86 · see citing works
Long-term outcome of patients who require renal replacement therapy after cardiac surgery
Landoni, G., Zangrillo, A., Franco, A., Aletti, G., Roberti, A., Calabró, M. G., Slaviero, G., Bignami, E. G., & Marino, G. (2006) · European Journal of Anaesthesiology · doi:10.1017/s0265021505001705 · Cited by 65 · see citing works
A Bayesian decision-support system for diagnosing ventilator-associated pneumonia
Schurink, C. A. M., Visscher, S., Lucas, P., van Leeuwen, H. J., Buskens, E., Hoff, R. G., Hoepelman, A. I. M., & Bonten, M. J. M. (2007) · Intensive Care Medicine · doi:10.1007/s00134-007-0728-6 · Cited by 41 · see citing works
Barbini, E., Cevenini, G., Scolletta, S., Biagioli, B., Giomarelli, P., & Barbini, P. (2007) · BMC Medical Informatics and Decision Making · doi:10.1186/1472-6947-7-35 · Cited by 31 · see citing works
Trampuž, A., Widmer, A. F., Flückiger, U. M., Haenggi, M., Frei, R., & Zimmerli, W. (2004) · Mayo Clinic Proceedings · doi:10.4065/79.5.604 · Cited by 23 · see citing works
Ho, K. M., & Knuiman, M. W. (2008) · Anaesthesia and Intensive Care · doi:10.1177/0310057x0803600107 · Cited by 20 · see citing works
Cevenini, G., Barbini, E., Scolletta, S., Biagioli, B., Giomarelli, P., & Barbini, P. (2007) · BMC Medical Informatics and Decision Making · doi:10.1186/1472-6947-7-36 · Cited by 17 · see citing works
Nikiforidis, G. C., & Sakellaropoulos, G. C. (1998) · Medical Informatics · doi:10.3109/14639239809001387 · Cited by 15 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Screening for diabetic retinopathy: new perspectives and challenges
Vujosevic, S., Aldington, S. J., Silva, P., Hernández, C., Scanlon, P., Peto, T., & Simó, R. (2020) · The Lancet Diabetes & Endocrinology · doi:10.1016/s2213-8587(19)30411-5 · Cited by 671 · see citing works
Application Scenarios for Artificial Intelligence in Nursing Care: Rapid Review
Seibert, K., Domhoff, D., Bruch, D., Schulte-Althoff, M., Fürstenau, D., Biessmann, F., & Wolf-Ostermann, K. (2021) · Journal of Medical Internet Research · doi:10.2196/26522 · Cited by 314 · see citing works
A Database-driven Decision Support System: Customized Mortality Prediction
Celi, L. A., Galvin, S., Davidzon, G., Lee, J., Scott, D., & Mark, R. G. (2012) · Journal of Personalized Medicine · doi:10.3390/jpm2040138 · Cited by 62 · see citing works
Self-citationAccessing the public MIMIC-II intensive care relational database for clinical research
Scott, D., Lee, J., Silva, I., Park, S., Moody, G. B., Celi, L. A., & Mark, R. G. (2013) · BMC Medical Informatics and Decision Making · doi:10.1186/1472-6947-13-9 · Cited by 61 · see citing works
Self-citationTemporal convolutional networks allow early prediction of events in critical care
Catling, F. J. R., & Wolff, A. (2019) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocz205 · Cited by 49 · see citing works
Artificial Intelligence in Critical Care
Mathur, P., & Burns, M. L. (2019) · International Anesthesiology Clinics · doi:10.1097/aia.0000000000000221 · Cited by 45 · see citing works
Kaieski, N., da Costa, C. A., Righi, R. D. R., Lora, P. S., & Eskofier, B. M. (2020) · Applied Soft Computing · doi:10.1016/j.asoc.2020.106612 · Cited by 45 · see citing works
Predictive combinations of monitor alarms preceding in-hospital code blue events
Hu, X., Sapo, M., Nenov, V., Barry, T., Kim, S., Do, D. H., Boyle, N., & Martin, N. A. (2012) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2012.03.001 · Cited by 43 · see citing works
Hypotension Risk Prediction via Sequential Contrast Patterns of ICU Blood Pressure
Ghosh, S., Feng, M., Nguyen, H. T., & Li, J. (2015) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2015.2453478 · Cited by 40 · see citing works
Exploring the Potential of Chatbots in Critical Care Nephrology
Suppadungsuk, S., Thongprayoon, C., Miao, J., Krisanapan, P., Qureshi, F., KASHANI, K. B., & Cheungpasitporn, W. (2023) · Medicines · doi:10.3390/medicines10100058 · Cited by 38 · see citing works
Errors, Omissions, and Outliers in Hourly Vital Signs Measurements in Intensive Care
Maslove, D. M., Dubin, J. A., Shrivats, A., & Lee, J. (2016) · Critical Care Medicine · doi:10.1097/ccm.0000000000001862 · Cited by 34 · see citing works
Sodium, volume and pressure control in haemodialysis patients for improved cardiovascular outcomes
Pinter, J., Chazot, C., Stuard, S., Moissl, U. M., & Canaud, B. (2020) · Nephrology Dialysis Transplantation · doi:10.1093/ndt/gfaa017 · Cited by 34 · see citing works
Dauvin, A., Donado, C., Bächtiger, P., Huang, K.-C., Sauer, C. M., Ramazzotti, D., Bonvini, M., Celi, L. A., & Douglas, M. J. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0192-z · Cited by 29 · see citing works
Self-citationComputerized decision support in adult and pediatric critical care
Williams, C. N., Bratton, S. L., & Hirshberg, E. L. (2013) · World Journal of Critical Care Medicine · doi:10.5492/wjccm.v2.i4.2 · Cited by 24 · see citing works
Cismondi, F., Horn, A. L., Fialho, A. S., Vieira, S. M., Reti, S. R., Sousa, J. M. C., & Finkelstein, S. N. (2012) · Expert Systems with Applications · doi:10.1016/j.eswa.2012.04.027 · Cited by 20 · see citing works
Recent approaches of artificial intelligence in intensive care unit: A review
Havelikar, U. A., Bembde, A., Patil, D., Shinde, A., Sharma, R. K., Patel, V. P., & Chaudhari, N. B. (2025) · Intelligent Hospital · doi:10.1016/j.inhs.2025.100030 · Cited by 12 · see citing works
Predictive data mining on monitoring data from the intensive care unit
Güiza, F., Eyck, J. V., & Meyfroidt, G. (2012) · Journal of Clinical Monitoring and Computing · doi:10.1007/s10877-012-9416-3 · Cited by 11 · see citing works
The use of data mining techniques to predict mortality and length of stay in an ICU
Navaz, A. N., Mohammed, E., Serhani, M. A., & Zaki, N. (2016) · International Conference on Innovations in Information Technology · doi:10.1109/innovations.2016.7880045 · Cited by 11 · see citing works
Chander, S., Kumari, R., Sadarat, F., & Luhana, S. (2023) · Current Problems in Cardiology · doi:10.1016/j.cpcardiol.2023.101805 · Cited by 11 · see citing works
The premise, promise, and perils of artificial intelligence in critical care cardiology
Huerta, N. H., Rao, S. J., Isath, A. M., Wang, Z., Glicksberg, B. S., & Krittanawong, C. (2024) · Progress in Cardiovascular Diseases · doi:10.1016/j.pcad.2024.06.006 · Cited by 10 · see citing works
Modeling for critically ill patients: An introduction for beginners
Lafont, E., Urien, S., Salem, J., Heming, N., & Faisy, C. (2015) · Journal of Critical Care · doi:10.1016/j.jcrc.2015.09.002 · Cited by 8 · see citing works
Dynamic prediction of life-threatening events for patients in intensive care unit
Hu, J., Kang, X., Xu, F.-F., Huang, K., Du, B., & Weng, L. (2022) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-022-02026-x · Cited by 8 · see citing works
Lapp, L., Bouamrane, M.-M., Roper, M., Kavanagh, K., & Schraag, S. (2022) · JMIR Perioperative Medicine · doi:10.2196/39907 · Cited by 7 · see citing works
Diabetic Retinopathy and Diabetic Macular Edema: Fighting the Emerging Global Burden
Bhattacharjee, H., Barman, M., & Garg, M. (2022) · Springer eBooks · doi:10.1007/978-981-19-7307-9_20 · Cited by 7 · see citing works
Pereira, M. A., Concheiro-Moscoso, P., López-Álvarez, A., Baños, G., Pazos, A., & Pereira, J. (2021) · Applied Sciences · doi:10.3390/app11062880 · Cited by 7 · see citing works
Pan, P., Wang, Y., Liu, C., Tu, Y., Cheng, H., Yang, Q., Xie, F., Li, Y., Xie, L., & Liu, Y. (2024) · Journal Of Big Data · doi:10.1186/s40537-024-00896-8 · Cited by 6 · see citing works
Collective Experience: A Database-Fuelled, Inter-Disciplinary Team-Led Learning System
Celi, L. A., Mark, R. G., Lee, J., Scott, D., & Panch, T. (2012) · Journal of Computing Science and Engineering · doi:10.5626/jcse.2012.6.1.51 · Cited by 6 · see citing works
Self-citationDias, C. C., Granja, C., Costa‐Pereira, A., da Gama, J. M. P., & Rodrigues, P. P. (2014) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms.2014.31 · Cited by 5 · see citing works
A novel neighbor selection approach for KNN
Kaveh-Yazdy, F., Zare-Mirakabad, M.-R., & Xia, F. (2012) · doi:10.1145/2346604.2346607 · Cited by 4 · see citing works
Tertiary Care - Medical, Psychosocial, and Environmental Aspects
Önal, A. E. (2023) · IntechOpen eBooks · doi:10.5772/intechopen.110957 · Cited by 4 · see citing works
Toward Unreasonable Effectiveness of Cardiac ICU Data
Chang, A. C., & Hunt, J. (2014) · Pediatric Critical Care Medicine · doi:10.1097/pcc.0000000000000176 · Cited by 4 · see citing works
Hemodynamic failure during sepsis: What clinicians and researchers must know
Léone, M., Russell, L., Cecconi, M., Khanna, A. K., Pirracchio, R., Bauer, M., & Rello, J. (2025) · Anaesthesia Critical Care & Pain Medicine · doi:10.1016/j.accpm.2025.101602 · Cited by 3 · see citing works
Using weak signals to predict spontaneous breathing trial success: a machine learning approach
Lombardi, R., Jozwiak, M., Dellamonica, J., & Pasquier, C. (2025) · Intensive Care Medicine Experimental · doi:10.1186/s40635-025-00724-0 · Cited by 2 · see citing works
Monitoring in the Healthcare Setting
Chesani, F., Enright, C. G., Montali, M., & Madden, M. G. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-28007-3_5 · Cited by 2 · see citing works
Artificial Intelligence in Neuroanesthesiology and Neurocritical Care
Rajagopalan, V., & Kulkarni, D. K. (2020) · Journal of Neuroanaesthesiology and Critical Care · doi:10.1055/s-0040-1701954 · Cited by 2 · see citing works
The assessment of drug safety for the fetus
Hecht, E. M. (2020) · International Journal of Clinical Pharmacy · doi:10.1007/s11096-020-01132-y · Cited by 2 · see citing works
Bayesian Networks for Evidence Based Clinical Decision Support.
Yet, B. (2013) · Cited by 2 · see citing works
Year in review 2007: Critical Care – cardiology
Camporota, L., Terblanche, M., & BENNETT, D. B. (2008) · Critical Care · doi:10.1186/cc7007 · Cited by 1 · see citing works
Applications of Artificial Intelligence in Ophthalmic Diseases
Long, M., & Ma, W. (2025) · Journal of Biosciences and Medicines · doi:10.4236/jbm.2025.132039 · Cited by 1 · see citing works
Polz, M., Bergmoser, K. M., Horn, M., Schörghuber, M., Šajić, J. L., Rienmüller, T. M., & Baumgärtner, C. (2023) · Frontiers in Physiology · doi:10.3389/fphys.2023.1101966 · Cited by 1 · see citing works
Lane, K., & Boyd, O. F. (2009) · Critical Care · doi:10.1186/cc7156 · Cited by 1 · see citing works
Artificial Intelligence to Facilitate SEP-1 Measure Compliance and Fluid Management in Sepsis
Nguyen, H. B., Krishtopaytis, E., Lopez, E., Farnoudi, N., Van, T., Kharalampova, V., & Coz Yataco, A. (2026) · Journal of Clinical Medicine · doi:10.3390/jcm15093477
“Celi et al. performed a proof-of-concept study aimed to evaluate the feasibility of using AI to predict individualized fluid requirements in ICU patients by analyzing data from the MIMIC II database at a single academic center, including 3014 patients on vasopressors [61].”
A Neural Approach for Controlling Vital Signs in the Intensive Care Unit Patients
Dadashi, A., Rowhanimanesh, A., & Choupankareh, S. (2015) · Medical Informatics
Year in review 2008: Critical Care - cardiology
Camporota, L., Terblanche, M., & BENNETT, D. B. (2009) · Critical Care · doi:10.1186/cc8025
Predicting neurosurgical clearance in the polytrauma patient with concomitant traumatic brain injury
Noureldine, M. H. A., Hartnett, S. M., Zavadskiy, G., Pressman, E., Kim, J. K., Davis, D., Ciesla, D. J., Bull, B., & Agazzi, S. (2021) · Journal of Clinical Neuroscience · doi:10.1016/j.jocn.2021.04.023
Hemphill, J. C., Sorani, M. D., Russell, S., & Manley, G. T. (2013) · Elsevier eBooks · doi:10.1016/b978-1-4377-0167-8.00045-5
Diabetic Macular Edema, Clinicopathologic and Keys for Management
Darwish, A. (2023) · IntechOpen eBooks · doi:10.5772/intechopen.112974
Future of fluid therapy for acute pancreatitis
Windsor, J. A., de‐Madaria, E., & Buxbaum, J. L. (2025) · Pancreatology · doi:10.1016/j.pan.2025.10.006
Hu, J., Kang, X.-H., Xu, F.-F., Huang, K.-Z., Du, B., & Weng, L. (2022) · Figshare · doi:10.6084/m9.figshare.21384442
Pan, P., Wang, Y., Liu, C., Tu, Y., Cheng, H., Yang, Q., Xie, F., Li, Y., Xie, L., & Liu, Y. (2024) · Figshare · doi:10.6084/m9.figshare.25649337
Hu, J., Kang, X.-H., Xu, F.-F., Huang, K.-Z., Du, B., & Weng, L. (2022) · Figshare · doi:10.6084/m9.figshare.21384445
- Authors
- Celi, L. A., Hinske Christian, L., Alterovitz, G., & Szolovits, P.
- Affiliations
- Massachusetts General Hospital (US)
- Boston Children's Hospital (US)
- Corresponding author
- Celi, Leo Anthony
- Venue
- Critical Care
- Published
- 2008-12-01
- Volume
- 12
- Issue
- 6
- Pages
- R151-R151
- ISSN
- 1364-8535 (ISSN-L)
- PMC
- PMC2646316
- OpenAlex
- W2167202211
- Cited by
- 52
- References
- 14
- Citations by year
- 2026: 1 · 2025: 5 · 2024: 2 · 2023: 6 · 2022: 6 · 2021: 3 · 2020: 5 · 2019: 3 · 2016: 2 · 2015: 4 · 2014: 2 · 2013: 4 · 2012: 6
- FWCI
- 1.59
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Critical Care (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- OPUS (Augsburg University) (submittedVersion, cc-by)
- Funders
- National Institute of Biomedical Imaging and Bioengineering (R01EB001659)
- U.S. National Library of Medicine (T15LM007092)
- National Center for Research Resources (P41RR013622)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Medicine › Surgery › Hemodynamic Monitoring and Therapy
- Health Sciences › Medicine › Epidemiology › Sepsis Diagnosis and Treatment
- Keywords
- intensive care unit, Bayesian networks, personalized medicine, vasopressor use, hypotension prevention, MIMIC II database, real-time prediction, critically ill patients
- MeSH terms
- Artificial Intelligence, Boston, Decision Making, Computer-Assisted, Female, Fluid Therapy, Humans, Intensive Care Units, Male, Vasoconstrictor Agents, Information Storage and Retrieval
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
