Prediction model of in-hospital mortality in intensive care unit patients with heart failure: machine learning-based, retrospective analysis of the MIMIC-III database
Open accessThe DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Abstract
Objective: The predictors of in-hospital mortality for intensive care units (ICUs)-admitted heart failure (HF) patients remain poorly characterised. We aimed to develop and validate a prediction model for all-cause in-hospital mortality among ICU-admitted HF patients. Design: A retrospective cohort study. Setting and participants: Data were extracted from the Medical Information Mart for Intensive Care (MIMIC-III) database. Data on 1177 heart failure patients were analysed. Methods: Patients meeting the inclusion criteria were identified from the MIMIC-III database and randomly divided into derivation (n=825, 70%) and a validation (n=352, 30%) group. Independent risk factors for in-hospital mortality were screened using the extreme gradient boosting (XGBoost) and the least absolute shrinkage and selection operator (LASSO) regression models in the derivation sample. Multivariate logistic regression analysis was used to build prediction models in derivation group, and then validated in validation cohort. Discrimination, calibration and clinical usefulness of the predicting model were assessed using the C-index, calibration plot and decision curve analysis. After pairwise comparison, the best performing model was chosen to build a nomogram according to the regression coefficients. Results: Among the 1177 admissions, in-hospital mortality was 13.52%. In both groups, the XGBoost, LASSO regression and Get With the Guidelines-Heart Failure (GWTG-HF) risk score models showed acceptable discrimination. The XGBoost and LASSO regression models also showed good calibration. In pairwise comparison, the prediction effectiveness was higher with the XGBoost and LASSO regression models than with the GWTG-HF risk score model (p<0.05). The XGBoost model was chosen as our final model for its more concise and wider net benefit threshold probability range and was presented as the nomogram. Conclusions: Our nomogram enabled good prediction of in-hospital mortality in ICU-admitted HF patients, which may help clinical decision-making for such patients.
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
DeLong, E. R., DeLong, D. M., & Clarke-Pearson, D. L. (1988) · Biometrics · doi:10.2307/2531595 · Cited by 22,649
McDonagh, T. A., Metra, M., Adamo, M., Gardner, R. S., Baumbach, A., Böhm, M., Burri, H., Butler, J., Čelutkienė, J., Chioncel, O., et al. (2021) · European Heart Journal · doi:10.1093/eurheartj/ehab670 · Cited by 19,442
2016 ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure
Ponikowski, P., Voors, A. A., Anker, S. D., Bueno, H., Cleland, J. G. F., Coats, A. J. S., Falk, V., González-Juanatey, J. R., Harjola, V.-P., Jankowska, E. A., et al. (2016) · European Heart Journal · doi:10.1093/eurheartj/ehw128 · Cited by 11,429
MIMIC-III, a freely accessible critical care database
Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L.-W. H., Feng, M., Ghassemi, M., Moody, B., Szolovits, P., Anthony Celi, L., & Mark, R. G. (2016) · Scientific Data · doi:10.1038/sdata.2016.35 · Cited by 8,141
Decision curve analysis: a novel method for evaluating prediction models
Vickers, A. J., & Elkin, E. B. (2006) · Medical Decision Making · doi:10.1177/0272989x06295361 · Cited by 6,341
Adams, K. F., Fonarow, G. C., Emerman, C. L., LeJemtel, T. H., Costanzo, M. R., Abraham, W. T., Berkowitz, R. L., Galvao, M., & Horton, D. P. (2005) · American Heart Journal · doi:10.1016/j.ahj.2004.08.005 · Cited by 2,116
Fonarow, G. C. (2005) · JAMA · doi:10.1001/jama.293.5.572 · Cited by 1,611
Predicting survival in heart failure: a risk score based on 39 372 patients from 30 studies
Pocock, S. J., Ariti, C. A., McMurray, J. J. V., Maggioni, A., Køber, L., Squire, I. B., Swedberg, K., Dobson, J., Poppe, K. K., Whalley, G. A., et al. (2013) · European Heart Journal · doi:10.1093/eurheartj/ehs337 · Cited by 1,331 · cited 1×
“Involving a small number of routinely collected variables, this tool can be easily used at the bedside.”
MethodSauerbrei, W., Royston, P., & Binder, H. (2007) · Statistics in Medicine · doi:10.1002/sim.3148 · Cited by 1,171 · cited 1×
“Second, we used the least absolute shrinkage and selection operator (LASSO) method, 19 which involves regression analysis to perform both variable selection and regularisation.”
MethodPlagnol, V., Curtis, J., Epstein, M., Mok, K. Y., Stebbings, E., Grigoriadou, S., Wood, N. W., Hambleton, S., Burns, S. O., Thrasher, A. J., et al. (2012) · Bioinformatics · doi:10.1093/bioinformatics/bts526 · Cited by 743 · cited 1×
“First, we used extreme gradient boosting (XGBoost), 17 a supervised machine-learning and data-mining tool, which involves a meta-algorithm, to construct a strong ensemble learner from weak learners, such as regression trees.”
MethodCardiovascular Event Prediction by Machine Learning: The Multi-Ethnic Study of Atherosclerosis
Ambale-Venkatesh, B., Yang, X., Wu, C. O., Liu, K., Hundley, W. G., McClelland, R., Gomes, A. S., Folsom, A. R., Shea, S., Guallar, E., et al. (2017) · Circulation Research · doi:10.1161/circresaha.117.311312 · Cited by 639
Variation in critical care services across North America and Western Europe*
Wunsch, H., Angus, D. C., Harrison, D. A., Collange, O., Fowler, R., Hoste, E. A. J., de Keizer, N. F., Kersten, A., Linde-Zwirble, W. T., Sandiumenge, A., et al. (2008) · Critical Care Medicine · doi:10.1097/ccm.0b013e318186aec8 · Cited by 624
Predictors of In-Hospital Mortality in Patients Hospitalized for Heart Failure
Abraham, W. T., Fonarow, G. C., Albert, N. M., Stough, W. G., Gheorghiade, M., Greenberg, B. H., O'Connor, C. M., Sun, J. L., Yancy, C. W., & Young, J. B. (2008) · Journal of the American College of Cardiology · doi:10.1016/j.jacc.2008.04.028 · Cited by 597
Peterson, P. N., Rumsfeld, J. S., Liang, L., Albert, N. M., Hernandez, A. F., Peterson, E. D., Fonarow, G. C., & Masoudi, F. A. (2010) · Circulation: Cardiovascular Quality and Outcomes · doi:10.1161/circoutcomes.109.854877 · Cited by 568 · cited 2×
“34 Our study showed that hyper-calcaemia indicated an adverse outcome.”
BackgroundMethodMissing data imputation: focusing on single imputation.
Zhang, Z. (2016) · PubMed · doi:10.3978/j.issn.2305-5839.2015.12.38 · Cited by 410 · cited 1×
“16”
Obesity and the Obesity Paradox in Heart Failure
Horwich, T. B., Fonarow, G. C., & Clark, A. L. (2018) · Progress in Cardiovascular Diseases · doi:10.1016/j.pcad.2018.05.005 · Cited by 392 · cited 1×
“Involving a small number of routinely collected variables, this tool can be easily used at the bedside.”
MethodObesity and the Obesity Paradox in Heart Failure
Clark, A. L., Fonarow, G. C., & Horwich, T. B. (2014) · Progress in Cardiovascular Diseases · doi:10.1016/j.pcad.2013.10.004 · Cited by 350
Follath, F., Yilmaz, M. B., Delgado, J. F., Parissis, J. T., Porcher, R., Gayat, E., Burrows, N., Mclean, A., Vilas-Boas, F., & Mebazaa, A. (2011) · Intensive Care Medicine · doi:10.1007/s00134-010-2113-0 · Cited by 286 · cited 1×
“Some models believe that it affects prognosis strongly 8 10 and some models disagree.”
BackgroundVoors, A. A., Ouwerkerk, W., Zannad, F., van Veldhuisen, D. J., Samani, N. J., Ponikowski, P., Ng, L. L., Metra, M., ter Maaten, J. M., Lang, C. C., et al. (2017) · European Journal of Heart Failure · doi:10.1002/ejhf.785 · Cited by 256 · cited 1×
“Involving a small number of routinely collected variables, this tool can be easily used at the bedside.”
MethodSiirila-Waris, K., Lassus, J., Melin, J., Peuhkurinen, K., Nieminen, M. S., Harjola, V.-P., & for the FINN-AKVA study group (2006) · European Heart Journal · doi:10.1093/eurheartj/ehl407 · Cited by 226
Chang, P. P., Wruck, L. M., Shahar, E., Rossi, J. S., Loehr, L. R., Russell, S. D., Agarwal, S. K., Konety, S. H., Rodriguez, C. J., & Rosamond, W. D. (2018) · Circulation · doi:10.1161/circulationaha.117.027551 · Cited by 218
Hallmarks of ion channel gene expression in end‐stage heart failure
Borlak, J., & Thum, T. (2003) · The FASEB Journal · doi:10.1096/fj.02-0889com · Cited by 171
Lupón, J., de Antonio, M., Vila, J., Peñafiel, J., Galán, A., Zamora, E., Urrutia, A., & Bayes-Genis, A. (2014) · PLoS ONE · doi:10.1371/journal.pone.0085466 · Cited by 148 · cited 1×
“Involving a small number of routinely collected variables, this tool can be easily used at the bedside.”
MethodShiga, T., Suzuki, A., Haruta, S., Mori, F., Ota, Y., Yagi, M., Oka, T., Tanaka, H., Murasaki, S., Yamauchi, T., et al. (2019) · ESC Heart Failure · doi:10.1002/ehf2.12418 · Cited by 144
Safavi, K. C., Dharmarajan, K., Kim, N. V., Strait, K. M., Li, S., Chen, S. I., Lagu, T. C., & Krumholz, H. M. (2013) · Circulation · doi:10.1161/circulationaha.112.001088 · Cited by 134
Low diastolic blood pressure and adverse outcomes in heart failure with preserved ejection fraction
Tsujimoto, T., & Kajio, H. (2018) · International Journal of Cardiology · doi:10.1016/j.ijcard.2018.04.031 · Cited by 59 · cited 1×
“Involving a small number of routinely collected variables, this tool can be easily used at the bedside.”
MethodPark, J. J., Choi, D., Yoon, C., Oh, I., Lee, J. H., Ahn, S., Yoo, B., Kang, S., Kim, J., Baek, S. H., et al. (2015) · European Journal of Heart Failure · doi:10.1002/ejhf.276 · Cited by 55 · cited 1×
“Involving a small number of routinely collected variables, this tool can be easily used at the bedside.”
Methodvan Diepen, S., Bakal, J. A., Lin, M., Kaul, P., McAlister, F. A., & Ezekowitz, J. A. (2015) · Journal of the American Heart Association · doi:10.1161/jaha.114.001708 · Cited by 51
The Critical Care Obesity Paradox and Implications for Nutrition Support
Patel, J. J., Rosenthal, M. D., Miller, K. R., Codner, P. A., Kiraly, L. N., & Martindale, R. G. (2016) · Current Gastroenterology Reports · doi:10.1007/s11894-016-0519-8 · Cited by 51
Chioncel, O. D., Ambrosy, A. P., Filipescu, D. C., Bubenek, Ș., Vinereanu, D., Petriş, A. O., Collins, S. P., Macarie, C., & Gheorghiade, M. (2014) · Journal of Cardiovascular Medicine · doi:10.2459/jcm.0000000000000030 · Cited by 40 · cited 1×
“Some models believe that it affects prognosis strongly 8 10 and some models disagree.”
BackgroundJensen, A.-S. C., Polcwiartek, C., Søgaard, P., Mortensen, R. N., Davidsen, L., Aldahl, M., Eriksen, M. A., Kragholm, K. H., Torp-Pedersen, C. T., & Hansen, S. M. (2018) · The American Journal of Medicine · doi:10.1016/j.amjmed.2018.10.006 · Cited by 40
Chen, C., Yoshida, A., Asakura, M., Hasegawa, T., Takahama, H., Amaki, M., Funada, A., Asanuma, H., Yokoyama, H., Kim, J., et al. (2012) · Circulation Journal · doi:10.1253/circj.cj-12-0040 · Cited by 39 · cited 1×
“Involving a small number of routinely collected variables, this tool can be easily used at the bedside.”
MethodWajner, A., Zuchinali, P., Olsen, V. D. R., Polanczyk, C. A., & Rohde, L. E. P. (2017) · Arquivos Brasileiros de Cardiologia · doi:10.5935/abc.20170136 · Cited by 37
Núñez, J. E., Carrascosa-García, S., Núñez, E., Bonanad, C., Bodí, V., Miñana, G., Santas, E., Escribano, D., Bayés‐Genís, A., Pascual-Figal, D. A., et al. (2014) · European Heart Journal Acute Cardiovascular Care · doi:10.1177/2048872614540094 · Cited by 33 · cited 1×
“Involving a small number of routinely collected variables, this tool can be easily used at the bedside.”
MethodPredictors of Frequent Readmissions in Patients With Heart Failure
Wang, N., Gallagher, R. D., Sze, D., Hales, S., & Tofler, G. H. (2017) · Heart Lung and Circulation · doi:10.1016/j.hlc.2017.10.024 · Cited by 30
Singh, K. P., & Gupta, S. (2014) · Toxicology and Applied Pharmacology · doi:10.1016/j.taap.2014.01.006 · Cited by 29 · cited 1×
“18 The parameters of a regression tree consist of the tree structures and the weights of the leaf nodes.”
BackgroundJia, Q., Wang, Y., He, P., Huang, X., Yan, W., Mu, Y., He, K., & Tian, Y. (2017) · PubMed Central · doi:10.11909/j.issn.1671-5411.2017.11.002 · Cited by 20
Lagu, T. C., Pekow, P. S., Stefan, M. S., Shieh, M., Pack, Q. R., Kashef, M. A., Atreya, A. R., Valania, G. E., Slawsky, M., & Lindenauer, P. K. (2018) · Journal of the American Heart Association · doi:10.1161/jaha.116.005256 · Cited by 16
Yagyu, T., Kumada, M., & Nakagawa, T. (2017) · PLoS ONE · doi:10.1371/journal.pone.0187410 · Cited by 12 · cited 1×
“Involving a small number of routinely collected variables, this tool can be easily used at the bedside.”
MethodDvornik, Š., Jurjević, T. Z., Jurjević, N., Lekić, A., & Zaputović, L. (2017) · Acta Clinica Belgica · doi:10.1080/17843286.2017.1410599 · Cited by 10
In-Hospital Mortality Predictors of Heart Failure Patients in Rajavithi Hospital.
Pongsuthana, S., & Chopchai, K. (2017) · PubMed · Cited by 3
Cited by
Weiner, E. B., Dankwa-Mullan, I., Nelson, W. A., & Hassanpour, S. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0000810 · Cited by 218
Peng, S., Huang, J., Liu, X., Deng, J., Sun, C., Tang, J., Chen, H., Cao, W., Wang, W., Duan, X., et al. (2022) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2022.994359 · Cited by 88
Pang, K., Li, L., Ouyang, W., Liu, X., & Tang, Y. (2022) · Diagnostics · doi:10.3390/diagnostics12051068 · Cited by 84
“A study used admission and laboratory variables to construct an XGBoost model to predict in-hospital mortality among patients with heart failure and achieved a high AUC of 0.84 [16].”
MethodInfluentialKarpov, O. E., Николаевна, П. Е., Kurkin, S., Александрович, М. В., Gusev, A. V., Shusharina, N. N., & Hramov, A. E. (2023) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph20075335 · Cited by 72
Machine learning based readmission and mortality prediction in heart failure patients
Sabouri, M., Bitarafan‐Rajabi, A., Hajianfar, G., Gharibi, O., Mohebi, M., Avval, A. H., Naderi, N., & Shiri, I. (2023) · Scientific Reports · doi:10.1038/s41598-023-45925-3 · Cited by 51
“In other studies by Li et al. 23 and Kwon et al. 43 , renal functionality is assessed by measuring either means of creatinine or chronic renal insufficiency.”
BackgroundInfluential
Metadata
- Authors
- Li, F., Xin, H., Zhang, J., Fu, M., Zhou, J., & Lian, Z.
- Affiliations
- Fudan University (CN)
- Affiliated Hospital of Qingdao University (CN)
- Corresponding author
- Zhou, Jingmin
- Lian, Zhexun
- Venue
- BMJ Open
- Publisher
- BMJ
- Published
- 2021-07
- Volume
- 11
- Issue
- 7
- Pages
- e044779
- ISSN
- 2044-6055 (ISSN-L)
- PMC
- PMC8311359
- OpenAlex
- W3184022450
- Cited by
- 128
- References
- 41
- Citations by year
- 2026: 9 · 2025: 36 · 2024: 46 · 2023: 25 · 2022: 11 · 2021: 1
- FWCI
- 13.91
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- BMJ Open (publishedVersion, cc-by-nc)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Basic Research Program of China (973 350 Program, 2012CB518605)
- National Natural Science Foundation of China (81370199)
- the Program for the Outstanding Academic Leaders supported by Shanghai Science and Technology Commission (16XD1400700)
- Topics
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Heart Failure Treatment and Management
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Health Sciences › Medicine › Critical Care and Intensive Care Medicine › Sepsis Diagnosis and Treatment
- Keywords
- heart failure, in-hospital mortality, mortality prediction model, intensive care unit patients, nomogram, XGBoost, LASSO, risk factors, MIMIC-III
- MeSH terms
- Machine Learning, Critical Care, Heart Failure, Humans, Intensive Care Units, Retrospective Studies, Hospital Mortality
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
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.