Using explainable machine learning to identify patients at risk of reattendance at discharge from emergency departments
Open accessAbstract
Short-term reattendances to emergency departments are a key quality of care indicator. Identifying patients at increased risk of early reattendance could help reduce the number of missed critical illnesses and could reduce avoidable utilization of emergency departments by enabling targeted post-discharge intervention. In this manuscript we present a retrospective, single-centre study where we created and evaluated an extreme gradient boosted decision tree model trained to identify patients at risk of reattendance within 72 hours of discharge from an emergency department (University Hospitals Southampton Foundation Trust, UK). Our model was trained using 35,447 attendances by 28,945 patients and evaluated on a hold-out test set featuring 8,847 attendances by 7,237 patients. The set of attendances from a given patient appeared exclusively in either the training or the test set. Our model was trained using both visit level variables (e.g., vital signs, arrival mode, and chief complaint) and a set of variables available in a patients electronic patient record, such as age and any recorded medical conditions. On the hold-out test set, our highest performing model obtained an AUROC of 0.747 (95% CI : 0.722-0.773) and an average precision of 0.233 (95% CI : 0.194-0.277). These results demonstrate that machine-learning models can be used to classify patients, with moderate performance, into low and high-risk groups for reattendance. We explained our models predictions using SHAP values, a concept developed from coalitional game theory, capable of explaining predictions at an attendance level. We demonstrated how clustering techniques can be used to investigate the different sub-groups of explanations present in our patient cohort.
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?
Number of comorbidities, arrival mode, and patient age latently encode patient frailty, which is closely related to higher long-term admission and re-admission risk.
“These are all factors that latently encode patient frailty, closely related to both higher long-term admission and re-admission risk30,31.”
From Using explainable machine learning to characterise data drift and detect emergent health risks for emergency department admissions during COVID-19 (2021) · cites this paper as [31]
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
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · see citing works
Advances in neural information processing systems 7
Cios, K. J., & Shields, M. E. (1997) · Neurocomputing · doi:10.1016/s0925-2312(97)90018-7 · Cited by 22,089 · see citing works
(1996) · Cited by 20,179 · see citing works
From local explanations to global understanding with explainable AI for trees
Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S.-I. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-019-0138-9 · Cited by 10,551 · see citing works
UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
McInnes, L., Healy, J., & Melville, J. (2018) · arXiv · doi:10.48550/arxiv.1802.03426 · Cited by 7,101 · see citing works
Practical Bayesian Optimization of Machine Learning Algorithms
Snoek, J., Larochelle, H., & Adams, R. P. (2012) · arXiv · doi:10.48550/arxiv.1206.2944 · Cited by 6,691 · see citing works
Dimensionality reduction for visualizing single-cell data using UMAP
Becht, E., McInnes, L., Healy, J., Dutertre, C.-A., Kwok, I. W. H., Ng, L. G., Ginhoux, F., & Newell, E. W. (2019) · Nature Biotechnology · doi:10.1038/nbt.4314 · Cited by 5,358 · see citing works
(2011) · Cited by 3,939 · see citing works
Artificial intelligence in healthcare
Yu, K.-H., Beam, A. L., & Kohane, I. S. (2018) · Nature Biomedical Engineering · doi:10.1038/s41551-018-0305-z · Cited by 2,817 · see citing works
Explainable machine-learning predictions for the prevention of hypoxaemia during surgery
Lundberg, S. M., Nair, B., Vavilala, M. S., Horibe, M., Eisses, M. J., Adams, T., Liston, D. E., Low, D. K.-W., Newman, S.-F., Kim, J., et al. (2018) · Nature Biomedical Engineering · doi:10.1038/s41551-018-0304-0 · Cited by 1,967 · see citing works
Bergstra, J., Yamins, D. L. K., & Cox, D. (2013) · Digital Access to Scholarship at Harvard (DASH) (Harvard University) · Cited by 1,817 · see citing works
The Effect of Emergency Department Crowding on Clinically Oriented Outcomes
Bernstein, S. L., Aronsky, D., Duseja, R., Epstein, S., Handel, D., Hwang, U., McCarthy, M., John McConnell, K., Pines, J. M., Rathlev, N., et al. (2009) · Academic Emergency Medicine · doi:10.1111/j.1553-2712.2008.00295.x · Cited by 1,147 · see citing works
Guttmann, A., Schull, M. J., Vermeulen, M. J., & Stukel, T. A. (2011) · BMJ · doi:10.1136/bmj.d2983 · Cited by 726 · see citing works
Frequent Users of Emergency Departments: The Myths, the Data, and the Policy Implications
LaCalle, E., & Rabin, E. (2010) · Annals of Emergency Medicine · doi:10.1016/j.annemergmed.2010.01.032 · Cited by 648 · see citing works
ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission
Huang, K., Altosaar, J., & Ranganath, R. (2019) · arXiv · doi:10.48550/arxiv.1904.05342 · Cited by 618 · see citing works
Moncada‐Torres, A., van Maaren, M. C., Hendriks, M. P., Siesling, S., & Geleijnse, G. (2021) · Scientific Reports · doi:10.1038/s41598-021-86327-7 · Cited by 340 · see citing works
Barreca, D. M. (2001) · ACM SIGKDD Explorations Newsletter · doi:10.1145/507533.507538 · Cited by 289 · see citing works
Association between frailty and 30-day outcomes after discharge from hospital
Kahlon, S., Pederson, J. L., Majumdar, S. R., Belga, S., Lau, D., Fradette, M., Boyko, D., Bakal, J. A., Johnston, C., Padwal, R. S., et al. (2015) · Canadian Medical Association Journal · doi:10.1503/cmaj.150100 · Cited by 234 · see citing works
UMAP reveals cryptic population structure and phenotype heterogeneity in large genomic cohorts
Diaz-Papkovich, A., Anderson-Trocmé, L., Ben-Eghan, C., & Gravel, S. (2019) · PLoS Genetics · doi:10.1371/journal.pgen.1008432 · Cited by 231 · see citing works
Berchet, C. (2015) · OECD health working papers · doi:10.1787/5jrts344crns-en · Cited by 136 · see citing works
Baier, N., Geißler, A., Bech, M., Bernstein, D., Cowling, T. E., Jackson, T. J., van Manen, J., Rudkjøbing, A., & Quentin, W. (2018) · Health Policy · doi:10.1016/j.healthpol.2018.11.001 · Cited by 136 · see citing works
Risk factors for 72-hour admission to the ED
Martin‐Gill, C., & Reiser, R. C. (2004) · The American Journal of Emergency Medicine · doi:10.1016/j.ajem.2004.07.023 · Cited by 117 · see citing works
Deschodt, M., Devriendt, E., Sabbe, M. B., Knockaert, D. C., Deboutte, P., Boonen, S., Flamaing, J., & Milisen, K. (2015) · BMC Geriatrics · doi:10.1186/s12877-015-0055-7 · Cited by 113 · see citing works
Sterling, N. W., Patzer, R. E., Di, M., & Schrager, J. D. (2019) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2019.06.008 · Cited by 112 · see citing works
Risk Prediction of Emergency Department Revisit 30 Days Post Discharge: A Prospective Study
Hao, S., Jin, B., Shin, A. Y., Zhao, Y., Zhu, C., Li, Z., Hu, Z., Fu, C., Ji, J., Wang, Y., et al. (2014) · PLoS ONE · doi:10.1371/journal.pone.0112944 · Cited by 89 · see citing works
Joseph, J. W., Leventhal, E. L., Grossestreuer, A. V., Wong, M. L., Joseph, L. J., Nathanson, L. A., Donnino, M. W., Elhadad, N., & Sanchez, L. D. (2020) · doi:10.1101/2020.05.02.20089052 · Cited by 57 · see citing works
Predicting 72-hour and 9-day return to the emergency department using machine learning
Hong, W. S., Haimovich, A. D., & Taylor, R. A. (2019) · JAMIA Open · doi:10.1093/jamiaopen/ooz019 · Cited by 42 · see citing works
Arendts, G., Fitzhardinge, S., Pronk, K., Hutton, M., Nagree, Y., & Donaldson, M. (2013) · Internal and Emergency Medicine · doi:10.1007/s11739-012-0895-5 · Cited by 25 · see citing works
Wijdenes, P., Haider, K., Gavrilovici, C., Gunning, B., Wolff, M. D., Lijnse, T. M., Armstrong, R., Teskey, G. C., Rho, J. M., Dalton, C., et al. (2021) · Scientific Reports · doi:10.1038/s41598-021-01528-4 · Cited by 20 · see citing works
Risk Factors for Emergency Department Short Time Readmission in Stratified Population
Besga, A., Ayerdi, B., Bezhold, G. A., Manzano, A., Lopetegui, P., Graña, M., & González-Pinto, A. M. (2015) · BioMed Research International · doi:10.1155/2015/685067 · Cited by 18 · see citing works
Li, Y., Chen, T., Chen, T., Li, X., Zeng, C., Liu, Z., & Xie, G. (2020) · PubMed Central · Cited by 12 · see citing works
Flagged first, then by citations
2 of the 34 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Loh, H. W., Ooi, C. P., Seoni, S., Barua, P. D., Molinari, F., & Acharya, U. R. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.107161 · Cited by 734 · see citing works
Explainable AI for clinical and remote health applications: A survey on tabular and time series data
Di Martino, F., & Delmastro, F. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10304-3 · Cited by 216 · see citing works
Duckworth, C., Chmiel, F. P., Burns, D. K., Zlatev, Z. D., White, N. M., Daniels, T. W. V., Kiuber, M., & Boniface, M. J. (2021) · Scientific Reports · doi:10.1038/s41598-021-02481-y · Cited by 109 · see citing works
Self-citationXAI-Based Clinical Decision Support Systems: A Systematic Review
Kim, S. Y., Kim, D. H., Kim, M., Ko, H.-J., & Jeong, O. (2024) · Applied Sciences · doi:10.3390/app14156638 · Cited by 84 · see citing works
Caterson, J., Lewin, A., & Williamson, E. (2024) · Digital Health · doi:10.1177/20552076241272657 · Cited by 40 · see citing works
Tanaka, M., Kohjitani, H., Yamamoto, E., Morimoto, T., Kato, T., Yaku, H., Inuzuka, Y., Tamaki, Y., Ozasa, N., Seko, Y., et al. (2024) · ESC Heart Failure · doi:10.1002/ehf2.14834 · Cited by 30 · see citing works
Lee, Y.-C., Ng, C., Hsu, C., Cheng, C.-W., & Chen, S.-Y. (2024) · BMC Emergency Medicine · doi:10.1186/s12873-024-00939-6 · Cited by 25 · see citing works
Diagnosing an overcrowded emergency department from its Electronic Health Records
Marzano, L., Darwich, A. S., Raghothama, J., Lethvall, S., Falk, N., Bodeby, P., & Meijer, S. (2024) · Scientific Reports · doi:10.1038/s41598-024-60888-9 · Cited by 15 · see citing works
He, B., & Qiu, Z. H. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1348907 · Cited by 16 · see citing works
Wang, J., Sourlos, N., Heuvelmans, M. A., Prokop, M., Vliegenthart, R., & van Ooijen, P. M. A. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107871 · Cited by 12 · see citing works
XAI-based Clinical Decision Support System: A Systematic Review
Kim, S., Kim, D., Kim, M., Ko, H., & Jeong, O. (2024) · doi:10.20944/preprints202406.0721.v1 · Cited by 72 · see citing works
Gadár, L., & Abonyi, J. (2024) · Scientific Reports · doi:10.1038/s41598-024-59690-4 · Cited by 10 · see citing works
Dambha‐Miller, H., Simpson, G., Akyea, R. K., Hounkpatin, H. O., Morrison, L. G., Gibson, J., Stokes, J., Islam, N., Chapman, A. P., Stuart, B. L., et al. (2022) · JMIR Research Protocols · doi:10.2196/34405 · Cited by 7 · see citing works
Self-citationArnaud, É., Moreno-Sánchez, P. A., Elbattah, M., Ammirati, C., van Gils, M., Dequen, G., & Ghazali, D. A. (2025) · Applied Sciences · doi:10.3390/app15158449 · Cited by 8 · see citing works
Oropeza-Valdez, J. J., Padrón-Manrique, C., Vázquez-Jiménez, A., Soberón, X., & Reséndis-Antonio, O. (2024) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2024.1429281 · Cited by 6 · see citing works
Desired clinical applications of artificial intelligence in emergency medicine: A Delphi study
Li, H., Hayward, J., Aguilar, L. S., & Franc, J. M. (2024) · The American Journal of Emergency Medicine · doi:10.1016/j.ajem.2024.02.031 · Cited by 5 · see citing works
Kuo, K.-M., Wu, W.-S., & Chang, C. S. (2025) · Journal of Medical Systems · doi:10.1007/s10916-025-02210-2 · Cited by 3 · see citing works
He, K., Wu, J., & Wang, C. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104773 · Cited by 2 · see citing works
Nwafor, O., Nwafor, C. N., Aboushady, A. A., & Solyman, A. (2024) · e-Prime - Advances in Electrical Engineering Electronics and Energy · doi:10.1016/j.prime.2024.100748 · Cited by 2 · see citing works
Santos, M. M., Peyroteo, M., & Lapão, L. V. (2024) · IEEE International Conference on Engineering, Technology and Innovation (ICE/ITMC) · doi:10.1109/ice/itmc61926.2024.10794414 · Cited by 2 · see citing works
Chang, T. L., Xia, H.-J., Mahajan, S., Mahajan, R., Maisog, J., Vattikuti, S., Chow, C., & Chang, J. C. (2022) · PLoS ONE · doi:10.1371/journal.pone.0302871 · Cited by 3 · see citing works
Autonomous Emergency Triage Support System
Ashaolu, O., Lyons, W., Stefanakos, I., Călinescu, R., Habli, I., Hodge, J., Picardi, C., Plant, K. L., & Townsend, B. (2023) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci62032.2023.00220 · Cited by 1 · see citing works
Sun, K. (2026) · JMIR Formative Research · doi:10.2196/87289 · Cited by 1 · see citing works
Machine Learning Approaches for Predicting Emergency Department Visits: A Scoping Review (Preprint)Preprint
Alaeddin, S., Jaye, K. M., Metri, N., Badge, H., Bendall, J., Brady, B., Chow, J. S. F., Dadich, A., Ditton, K., Gilmore, I., et al. (2025) · doi:10.2196/preprints.71903
Reid, F., Pravinkumar, S. J., Maguire, R., Main, A., McCartney, H., Winters, L., & Dong, F. (2025) · Digital Health · doi:10.1177/20552076251315293
Watanabe, Y., Kohjitani, H., Matsuoka, Y., Toyota, T., Sano, M., Azumi, Y., Hayashi, H., Murai, R., Ooka, J., Sasaki, Y., et al. (2025) · medRxiv · doi:10.1101/2025.10.07.25337539
Fan, L., Zuo, X., Tang, L., Xiong, H., You, Y., & Fan, C. (2025) · Frontiers in Public Health · doi:10.3389/fpubh.2025.1609206
SeqBoost: a sequential explainable model for predicting ED revisits within 72 hours
Vatiwutipong, P., & Noraset, T. (2026) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-026-03582-2
Peak-Aware Two-Stage LSTM Forecasting of Patient Arrivals in Welsh Emergency Departments
Morgan, M. L., Rahat, A. A.-A. M., Jenkins, G., & Zhang, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-35387-0_27
Schulte‐Althoff, M., Krappen, P., Bießmann, F., Jäger, S., Gubser, R., Hauß, A., Balzer, F., Kilgus, T., & Fürstenau, D. (2026) · npj Health Systems · doi:10.1038/s44401-026-00138-4
Novak, A., & Hruby, T. (2026) · Journal of Health Informatics and Digital Systems · doi:10.68159/h706285658
- Authors
- Chmiel, F. P., Burns, D. K., Azor, M., Borca, F., Boniface, M. J., Zlatev, Z. D., White, N. M., Daniels, T. W. V., & Kiuber, M.
- Affiliations
- University of Southampton (GB)
- University Hospital Southampton NHS Foundation Trust (GB)
- Southampton General Hospital (GB)
- Corresponding author
- Chmiel, F. P.
- ORCID
- Venue
- Scientific Reports
- Publisher
- openRxiv
- Published
- 2020-12-04
- Volume
- 11
- Issue
- 1
- Pages
- 21513-21513
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC8563762
- OpenAlex
- W3209507725
- Cited by
- 30
- References
- 34
- Citations by year
- 2026: 6 · 2025: 6 · 2024: 12 · 2023: 2 · 2022: 3 · 2021: 1
- FWCI
- 1.59
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- Scientific Reports (publishedVersion, cc-by)
- medRxiv (acceptedVersion)
- Europe PMC (PubMed Central) (publishedVersion, other-oa)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- ePrints Soton (University of Southampton) (acceptedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- ePrints Soton (University of Southampton) (submittedVersion)
- Funders
- Alan Turing Institute (EP/N510129/1., N510129, EPSRC Grant EP/N510129/1)
- National Institute for Health and Care Research (EP/N510129/1)
- Engineering and Physical Sciences Research Council (N510129, EP/N510129/, EP/N510129/1, EPSRC grant EP/N510129/1)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Medicine › Emergency Medicine › Emergency and Acute Care Studies
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- explainable machine learning, SHAP values, extreme gradient boosting, UMAP clustering, risk stratification, emergency department utilization, electronic health records
- MeSH terms
- Machine Learning, Adolescent, Adult, Aftercare, Aged, Algorithms, Emergency Service, Hospital, Female, Hospitalization, Humans, Male, Middle Aged, Patient Discharge, Patient Readmission, Retrospective Studies, Risk Factors, Triage, Critical Illness, Young Adult, Electronic Health Records
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
