The DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.
An automated machine learning-based model predicts postoperative mortality using readily-extractable preoperative electronic health record data
Open accessPublished version of a preprint
Abstract
Background Rapid, preoperative identification of patients with the highest risk for medical complications is necessary to ensure that limited infrastructure and human resources are directed towards those most likely to benefit. Existing risk scores either lack specificity at the patient level or utilise the American Society of Anesthesiologists (ASA) physical status classification, which requires a clinician to review the chart.Methods We report on the use of machine learning algorithms, specifically random forests, to create a fully automated score that predicts postoperative in-hospital mortality based solely on structured data available at the time of surgery. Electronic health record data from 53 097 surgical patients (2.01% mortality rate) who underwent general anaesthesia between April 1, 2013 and December 10, 2018 in a large US academic medical centre were used to extract 58 preoperative features.Results Using a random forest classifier we found that automatically obtained preoperative features (area under the curve [AUC] of 0.932, 95% confidence interval [CI] 0.910-0.951) outperforms Preoperative Score to Predict Postoperative Mortality (POSPOM) scores (AUC of 0.660, 95% CI 0.598-0.722), Charlson comorbidity scores (AUC of 0.742, 95% CI 0.658-0.812), and ASA physical status (AUC of 0.866, 95% CI 0.829-0.897). Including the ASA physical status with the preoperative features achieves an AUC of 0.936 (95% CI 0.917-0.955).Conclusions This automated score outperforms the ASA physical status score, the Charlson comorbidity score, and the POSPOM score for predicting in-hospital mortality. Additionally, we integrate this score with a previously published postoperative score to demonstrate the extent to which patient risk changes during the perioperative period.
Overview
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
Verification
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?
The use of ML in medicine promises to facilitate an understanding of what features drive outcomes.
“Another advantage is the promise that the use of ML in medicine will facilitate an understanding of what features drive outcomes (26).”
From Accessing Artificial Intelligence for Clinical Decision-Making (2021) · cites this paper as [26]
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
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
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
SMOTE synthetic minority over-sampling technique
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.953 · Cited by 32,865
Regularization and Variable Selection Via the Elastic Net
Zou, H., & Hastie, T. (2005) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.1467-9868.2005.00503.x · Cited by 20,957
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · arXiv · doi:10.48550/arxiv.1603.02754 · Cited by 7,104
Validation of a combined comorbidity index
Charlson, M., Szatrowski, T. P., Peterson, J., & Gold, J. (1994) · Journal of Clinical Epidemiology · doi:10.1016/0895-4356(94)90129-5 · Cited by 6,587
Quan, H., Li, B., Couris, C. M., Fushimi, K., Graham, P. J., Hider, P., Januel, J., & Sundararajan, V. (2011) · American Journal of Epidemiology · doi:10.1093/aje/kwq433 · Cited by 5,967
Moher, D., Schulz, K. F., & Altman, D. G. (2001) · The Lancet · doi:10.1016/s0140-6736(00)04337-3 · Cited by 5,373
Saito, T., & Rehmsmeier, M. (2015) · PLOS ONE · doi:10.1371/journal.pone.0118432 · Cited by 5,309
Moher, D., Schulz, K. F., & Altman, D. G. (2001) · BMC Medical Research Methodology · doi:10.1186/1471-2288-1-2 · Cited by 2,755
Scalable and accurate deep learning with electronic health records
Rajkomar, A., Oren, E., Chen, K., Dai, A. M., Hajaj, N., Hardt, M., Liu, P. J., Liu, X., Marcus, J., Sun, M., et al. (2018) · npj Digital Medicine · doi:10.1038/s41746-018-0029-1 · Cited by 2,648
Scalable and accurate deep learning with electronic health records.
Rajkomar, A., Oren, E., Chen, K., Dai, A. M., Hajaj, N., Hardt, M., Liu, P. J., Liu, X., Marcus, J., Sun, M., et al. (2018) · eScholarship (California Digital Library) · Cited by 2,242
Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine LearningPreprint
Lemaître, G., Nogueira, F., & Aridas, C. K. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.06570 · Cited by 1,923
Bilimoria, K., Liu, Y., Paruch, J., Zhou, L., Kmiecik, T. E., Ko, C. Y., & Cohen, M. E. (2013) · Journal of the American College of Surgeons · doi:10.1016/j.jamcollsurg.2013.07.385 · Cited by 1,854
ASA classification and perioperative variables as predictors of postoperative outcome
Wolters, U., Wolf, T., Stützer, H., & Schröder, T. (1996) · British Journal of Anaesthesia · doi:10.1093/bja/77.2.217 · Cited by 1,072
Spectral Regularization Algorithms for Learning Large Incomplete Matrices.
Mazumder, R., Hastie, T. J., & Tibshirani, R. J. (2010) · PubMed · Cited by 1,058
American Society of Anaesthesiologists physical status classification
Daabiss, M. A. (2011) · Indian Journal of Anaesthesia · doi:10.4103/0019-5049.79879 · Cited by 919
Early Surgery versus Conventional Treatment for Infective Endocarditis
Kang, D.-H., Kim, Y.-J., Kim, S.-H., Sun, B. J., Kim, D.-H., Yun, S.-C., Song, J.-M., Choo, S. J., Chung, C.-H., Song, J.-K., et al. (2012) · New England Journal of Medicine · doi:10.1056/nejmoa1112843 · Cited by 902
Spectral Regularization Algorithms for Learning Large Incomplete Matrices
MazumderRahul, HastieTrevor, & TibshiraniRobert (2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1859931 · Cited by 671
Identification and characterisation of the high-risk surgical population in the United Kingdom
Pearse, R. M., Harrison, D. A., James, P., Watson, D. I., Hinds, C., Rhodes, A., Grounds, R. M., & Bennett, E. (2006) · Critical Care · doi:10.1186/cc4928 · Cited by 669
Hackett, N., Oliveira, G. S. D., Jain, U. K., & Kim, J. Y. S. (2015) · International Journal of Surgery · doi:10.1016/j.ijsu.2015.04.079 · Cited by 653
Reliability of the American Society of Anesthesiologists physical status scale in clinical practice
Sankar, A., Johnson, S. R., Beattie, W. S., Tait, G., & Wijeysundera, D. N. (2014) · British Journal of Anaesthesia · doi:10.1093/bja/aeu100 · Cited by 555
Artificial intelligence powers digital medicine
Fogel, A. L., & Kvedar, J. C. (2018) · npj Digital Medicine · doi:10.1038/s41746-017-0012-2 · Cited by 473
Vacanti, C. J., VanHOUTEN, R. J., & HILL, R. C. (1970) · Anesthesia & Analgesia · doi:10.1213/00000539-197007000-00010 · Cited by 390
The ASA classification and peri-operative risk
Fitz-Henry, J. (2011) · Annals of The Royal College of Surgeons of England · doi:10.1308/rcsann.2011.93.3.185a · Cited by 373
for the CONSORT Group*, Moher, D., Schulz, K. F., & Altman, D. G. (2003) · Clinical Oral Investigations · doi:10.1007/s00784-002-0188-x · Cited by 259
Preoperative Score to Predict Postoperative Mortality (POSPOM)
Manach, Y. L., Collins, P. G. S., Rodseth, R. N., Bihan-Benjamin, C. L., Biccard, B. M., Riou, B., Devereaux, P. J., & Landais, P. (2015) · Anesthesiology · doi:10.1097/aln.0000000000000972 · Cited by 199
Lee, C. K., Hofer, I., Gabel, E., Baldi, P., & Cannesson, M. (2018) · Anesthesiology · doi:10.1097/aln.0000000000002186 · Cited by 185
Self-citationSessler, D. I., Sigl, J. C., Manberg, P. J., Kelley, S. D., Schubert, A., & Chamoun, N. G. (2010) · Anesthesiology · doi:10.1097/aln.0b013e3181f79a8d · Cited by 105
Dalton, J. E., Kurz, A. M., Turan, A., Mascha, E. J., Sessler, D. I., & Saager, L. (2011) · Anesthesiology · doi:10.1097/aln.0b013e318219d5f9 · Cited by 94
A Systematic Approach to Creation of a Perioperative Data Warehouse
Hofer, I. S., Gabel, E., Pfeffer, M. A., Mahbouba, M., & Mahajan, A. (2016) · Anesthesia & Analgesia · doi:10.1213/ane.0000000000001201 · Cited by 75
Self-citationLeeds, I. L., Truta, B., Parian, A. M., Chen, S. Y., Efron, J. E., Gearhart, S. L., Safar, B. A., & Fang, S. H. (2017) · Journal of Gastrointestinal Surgery · doi:10.1007/s11605-017-3538-3 · Cited by 56
The Validity of Discharge Billing Codes Reflecting Severe Maternal Morbidity
Sigakis, M. J. G., Leffert, L. R., Mirzakhani, H., Sharawi, N., Rajala, B., Callaghan, W. M., Kuklina, E. V., Creanga, A. A., Mhyre, J. M., & Bateman, B. T. (2016) · Anesthesia & Analgesia · doi:10.1213/ane.0000000000001436 · Cited by 47
Impact of Present-on-admission Indicators on Risk-adjusted Hospital Mortality Measurement
Dalton, J. E., Glance, L. G., Mascha, E. J., Ehrlinger, J., Chamoun, N. G., & Sessler, D. I. (2013) · Anesthesiology · doi:10.1097/aln.0b013e31828e12b3 · Cited by 39
Rubinsteyn, A., Feldman, S., O’Donnell, T., & Beaulieu‐Jones, B. K. (2016) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.594235 · Cited by 15
Machine Learning Tool for Automatic ASA Detection
Lazouni, M. E. A., Daho, M. E. H., Settouti, N., Chikh, M. A., & Mahmoudi, S. (2013) · Studies in computational intelligence · doi:10.1007/978-3-319-00560-7_5 · Cited by 7
Data-Driven System for Perioperative Acuity Prediction.
Zhang, L., Fabbri, D., & Wanderer, J. P. (2016) · AMIA · Cited by 2
The Validity of Discharge Billing Codes Reflecting Severe Maternal Morbidity
Sigakis, M. J. G., Leffert, L. R., Mirzakhani, H., Sharawi, N., Rajala, B., Callaghan, W. M., Kuklina, E. V., Creanga, A. A., Mhyre, J. M., & Bateman, B. T. (2017) · Obstetric Anesthesia Digest · doi:10.1097/01.aoa.0000512008.03839.93 · Cited by 1
Final report on research gaps of space-based Arctic monitoring
Gabarró, C., Bertino, L., Bracher, A. U., Diehl, T., Dierking, W., Gambau, V. G., Hughes, N., Lavergne, T., Malnes, E., Scholze, M., et al. (2020) · DIGITAL.CSIC (Spanish National Research Council (CSIC)) · doi:10.13039/501100000780
Scalable and accurate deep learning for electronic health records
Rajkomar, A., Oren, E., Chen, K., Dai, A. M., Hajaj, N., Liu, P. J., Liu, X., Sun, M., Sundberg, P., Yee, H., et al. (2018) · arXiv · doi:10.48550/arxiv.1801.07860
Flagged first, then by citations
Cited by
Sorted by citations
Accessing Artificial Intelligence for Clinical Decision-Making
Giordano, C., Brennan, M., Mohamed, B., Rashidi, P., Modave, F., & Tighe, P. (2021) · Frontiers in Digital Health · doi:10.3389/fdgth.2021.645232 · Cited by 326
“Another advantage is the promise that the use of ML in medicine will facilitate an understanding of what features drive outcomes (26).”
BackgroundMachine Learning and Surgical Outcomes Prediction: A Systematic Review
Elfanagely, O., Toyoda, Y., Othman, S., Mellia, J. A., Basta, M. N., Liu, T., Kording, K. P., Ungar, L., & Fischer, J. P. (2021) · Journal of Surgical Research · doi:10.1016/j.jss.2021.02.045 · Cited by 126
Large Language Model Capabilities in Perioperative Risk Prediction and Prognostication
Chung, P., Fong, C. T., Walters, A. M., Aghaeepour, N., Yetişgen, M., & O’Reilly-Shah, V. N. (2024) · JAMA Surgery · doi:10.1001/jamasurg.2024.1621 · Cited by 134
Klug, M., Barash, Y., Bechler, S., Resheff, Y. S., Tron, T., Ironi, A., Soffer, S., Zimlichman, E., & Klang, E. (2019) · Journal of General Internal Medicine · doi:10.1007/s11606-019-05512-7 · Cited by 120
Bishara, A. M., Chiu, C., Whitlock, E. L., Douglas, V. C., Lee, S., Butte, A. J., Leung, J. M., & Donovan, A. L. (2022) · BMC Anesthesiology · doi:10.1186/s12871-021-01543-y · Cited by 118
“…prediction models have been developed to predict delirium in hospitalized patients [17], postoperative delirium in focused patient populations [18], non-delirium-related intraoperative complications [19, 20], and postoperative mortality [21], in addition to applications in many other contexts [22].”
BackgroundMachine learning in perioperative medicine: a systematic review
Bellini, V., Valente, M., Bertorelli, G., Pifferi, B., Craca, M., Mordonini, M., Lombardo, G., Bottani, E., RIO, P. D., & Bignami, E. G. (2022) · Journal of Anesthesia Analgesia and Critical Care · doi:10.1186/s44158-022-00033-y · Cited by 120
“Moreover, a few studies compared automatically obtained algorithms to conventional scores, revealing the outperformance of ML models [25].”
ResultArina, P., Kaczorek, M. R., Hofmaenner, D. A., Pisciotta, W., Refinetti, P., Singer, M., Mazomenos, E. B., & Whittle, J. (2024) · Anesthesiology · doi:10.1097/aln.0000000000004764 · Cited by 81
“The potential for early, accurate diagnosis of organ dysfunction or other complications leading to timely or even pre-emptive treatment is an intriguing prospect but must be approached with rigorous validation and proper scrutiny to ensure improved outcomes and resource efficiency.”
Anesthesiologists’ Role in Value-based Perioperative Care and Healthcare Transformation
Mahajan, A., Esper, S. A., Cole, D. J., & Fleisher, L. A. (2021) · Anesthesiology · doi:10.1097/aln.0000000000003717 · Cited by 67
“Several anesthesiology and perioperative care groups have developed adaptive models through “deep learning” to predict 30-day mortality.(62,63) However, few have reported the results from implementation of these models in changing care delivery or clinical practice at the current time.”
BackgroundSelf-citationLee, C. K., Samad, M., Hofer, I. S., Cannesson, M. P., & Baldi, P. (2021) · npj Digital Medicine · doi:10.1038/s41746-020-00377-1 · Cited by 64
Self-citationThompson, M., Hill, B. L., Rakocz, N., Chiang, J. N., Geschwind, D. H., Sankararaman, S., Hofer, I. S., Cannesson, M. P., Zaitlen, N., & Halperin, E. (2022) · npj Genomic Medicine · doi:10.1038/s41525-022-00320-1 · Cited by 59
Self-citationArtificial intelligence and telemedicine in anesthesia: potential and problems
Bellini, V., Valente, M., Gaddi, A. V., Pelosi, P. P., & Bignami, E. G. (2022) · Minerva Anestesiologica · doi:10.23736/s0375-9393.21.16241-8 · Cited by 58
Artificial intelligence in perioperative medicine: a narrative review
Yoon, H., Yang, H.-L., Jung, C.-W., & Lee, H. (2022) · Korean Journal of Anesthesiology · doi:10.4097/kja.22157 · Cited by 70
“Hill et al. [30] developed a fully automated score to predict postoperative in-hospital mortality using RF from the EHRs of 53,097 surgical patients.”
BackgroundMethodInfluentialMachine Learning, Deep Learning, and Closed Loop Devices—Anesthesia Delivery
Wingert, T., Lee, C., & Cannesson, M. P. (2021) · Anesthesiology Clinics · doi:10.1016/j.anclin.2021.03.012 · Cited by 61
Self-citationPredictive analysis using machine learning: Review of trends and methods
Bokonda, P. L., Ouazzani-Touhami, K., & Souissi, N. (2020) · International Symposium on Advanced Electrical and Communication Technologies (ISAECT) · doi:10.1109/isaect50560.2020.9523703 · Cited by 50
Lee, S. W., Lee, H., Suh, J., Lee, K. H., Lee, H., Seo, S., Kim, T. K., Lee, S.-W., & Kim, Y. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00625-6 · Cited by 55
Samad, M., Angel, M., Rinehart, J. B., Kanomata, Y., Baldi, P., & Cannesson, M. P. (2023) · JAMIA Open · doi:10.1093/jamiaopen/ooad084 · Cited by 57
Self-citationWongtangman, K., Aasman, B., Garg, S., Witt, A. S., Harandi, A. A., Azimaraghi, O., Mirhaji, P., Soby, S., Anand, P., Himes, C. P., et al. (2023) · Journal of Clinical Anesthesia · doi:10.1016/j.jclinane.2023.111103 · Cited by 42
The automaton as a surgeon: the future of artificial intelligence in emergency and general surgery
Rimmer, L. J., Howard, C., Picca, L., & Bashir, M. (2020) · European Journal of Trauma and Emergency Surgery · doi:10.1007/s00068-020-01444-8 · Cited by 33
“Orthopaedic studies have published utilising AI in diagnosing fractures of both common orthopaedic injuries of the extremities, as well as in serious injuries to the vertebral column [23, 24].”
BackgroundFritz, B. A., King, C. R., Abdelhack, M., Chen, Y., Kronzer, A., Abraham, J., Tripathi, S., Abdallah, A. B., Kannampallil, T., Budelier, T. P., et al. (2024) · British Journal of Anaesthesia · doi:10.1016/j.bja.2024.08.004 · Cited by 33
Xu, D., Sheng, J. Q., Hu, P. J., Huang, T., & Hsu, C. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3033323 · Cited by 36
Henn, J., Buneß, A., Schmid, M. C., Kalff, J. C., & Matthaei, H. (2021) · Langenbeck s Archives of Surgery · doi:10.1007/s00423-021-02348-w · Cited by 31
“, ML) might replace human doctors and the accompanying human relationship between patient and physician [50].”
BackgroundReilly, J. R., Gabbe, B. J., Brown, W. A., Hodgson, C. L., & Myles, P. S. (2020) · ANZ Journal of Surgery · doi:10.1111/ans.16255 · Cited by 34
“Discrimination refers to the ability of a model to distinguish between patients who do and do not experience the endpoint, in this case, between patients who survive and those who die.(10) It is commonly measured by the c-statistic, which for a binary outcome is identical to the AUROC curve.”
MethodInfluentialPata, G., Bianchetti, L., Rota, M., Marengoni, A., Chiesa, D., Cassinotti, E., Palmisano, S., Colombi, M., Zotto, G. D., Romanelli, G., et al. (2020) · Journal of Surgical Oncology · doi:10.1002/jso.26314 · Cited by 29
“Thus, despite the widespread adoption of these scores, their ability to predict complications appears low among elderly CRC patients scheduled for surgery.(8) The comprehensive geriatric assessment (CGA) is the “evidence‐ based” reference tool to assess the overall health of elderly patients.”
BackgroundGreenwald, S. D., Chamoun, G. F., Chamoun, N. G., Clain, D., Hong, Z., Jordan, R., Manberg, P. J., Maheshwari, K. K., & Sessler, D. I. (2022) · Anesthesiology · doi:10.1097/aln.0000000000004380 · Cited by 29
Lin, W.-C., Chen, A., Song, X. B., Weiskopf, N. G., Chiang, M. F., & Hribar, M. R. (2023) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocad213 · Cited by 27
Chen, P., Chen, L., Lin, Y.-K., Li, G.-H., Lai, F., Lü, C.-W., Yang, C.-Y., Chen, K., & Lin, T. (2022) · JMIR Medical Informatics · doi:10.2196/38241 · Cited by 28
“Although these classification systems consider the patient’s general condition and surgery category, preoperative vital signs and laboratory data—which are critical in predicting postoperative mortality—are not typically included [6].”
BackgroundMethodResultInfluentialKermansaravi, M., Chiappetta, S., Shahmiri, S. S., Varas, J., Parmar, C. D., Lee, Y., Dang, J. T., Shabbir, A., Hashimoto, D. A., Jazi, A. H. D., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-94335-0 · Cited by 27
“For example, studies have demonstrated that preoperative factors such as age, BMI, duration of obesity, and specific biomarkers can be used to predict the likelihood of remission of type 2 diabetes after MBS 45–47 .”
Impact of Intraoperative Data on Risk Prediction for Mortality After Intra-Abdominal Surgery
Yan, X., Goldsmith, J., Mohan, S., Turnbull, Z. A., Freundlich, R. E., Billings, F. T., Kiran, R. P., Li, G., & Kim, M. (2021) · Anesthesia & Analgesia · doi:10.1213/ane.0000000000005694 · Cited by 22
Peng, X., Zhu, T., Wang, T., Wang, F., Li, K., & Hao, X. (2022) · BMC Anesthesiology · doi:10.1186/s12871-022-01827-x · Cited by 17
“In addition, multiple correlated features introduce noise in the process of model development using logistic regression, which may reduce predictive accuracy [24].”
BackgroundYoon, H., Kim, H. J., Kim, Y., Lee, H., Kim, B. R., Oh, H., Park, H., & Lee, H. (2024) · British Journal of Anaesthesia · doi:10.1016/j.bja.2024.01.030 · Cited by 16
Ke, J. X. C., DhakshinaMurthy, A., George, R. B., & Branco, P. (2024) · Discover Artificial Intelligence · doi:10.1007/s44163-024-00199-0 · Cited by 15
Opal: an implementation science tool for machine learning clinical decision support in anesthesia
Bishara, A. M., Wong, A. H., Wang, L., Chopra, M., Fan, W., Lin, A. J., Fong, N., Palacharla, A., Spinner, J., Armstrong, R., et al. (2021) · Journal of Clinical Monitoring and Computing · doi:10.1007/s10877-021-00774-1 · Cited by 14
“Within clinical anesthesia, ML models have been trained to predict numerous clinical outcomes including intraoperative hypotension [3], post-operative length to discharge [4], and post-operative mortality [5, 6].”
MethodTan, J. M., Cannesson, M. P., Feldman, J. M., Allan F. Simpao, M., McGrath, S. P., Khanna, A. K., Beard, J. W., McGaffigan, P., & Cole, D. J. (2025) · Anesthesia & Analgesia · doi:10.1213/ane.0000000000007540 · Cited by 13
Self-citationOdat, R. M., Marsool, M. D. M., Nguyen, D. H., Idrees, M., Hussein, A. M., Ghabally, M., Yasin, J. A., Hanifa, H., Sabet, C. J., Định, N. H., et al. (2024) · International Journal of Surgery · doi:10.1097/js9.0000000000002003 · Cited by 14
Ahmed, M. M., Othman, Z. K., Adebayo, U. O., Kasimieh, O., Okesanya, O. J., Musa, S. S., Branda, F., Cañezo, V. C., Cue, E. G., & Lucero‐Prisno, D. E. (2025) · Patient Safety in Surgery · doi:10.1186/s13037-025-00458-8 · Cited by 11
Dibiasi, C., Agibetov, A., Kapral, L., Zeiner, S., & Kimberger, O. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm12134434 · Cited by 12
AI-delirium guard: Predictive modeling of postoperative delirium in elderly surgical patients
Boppana, S. H., Tyagi, D., Komati, S. S. K., Boppana, S. L., Raj, R., & Mintz, C. D. (2025) · PLoS ONE · doi:10.1371/journal.pone.0322032 · Cited by 10
Risk factor stratification for postoperative delirium: A retrospective database study
Vacas, S., Grogan, T., Cheng, D., & Hofer, I. S. (2022) · Medicine · doi:10.1097/md.0000000000031176 · Cited by 9
Self-citationMaurer, M. M., Pfitzner, B., van de Water, R. P., Faraj, L., Riepe, C., Zuluaga, D., Krenzien, F., Raschzok, N., Siegel, R., Schineis, C., et al. (2025) · International Journal of Surgery · doi:10.1097/js9.0000000000003084 · Cited by 9
“[ 8–10 ] However, several challenges impede the effective development of artificial intelligence (AI) models in surgery to date.”
Perioperative Risk Stratification and Modification
Matthews, L., Levett, D. Z. H., & Grocott, M. P. W. (2022) · Anesthesiology Clinics · doi:10.1016/j.anclin.2022.03.001 · Cited by 9
Langlois, P. L., Imrie, F., Geraldo, M.-A., Wingert, T., Lahrichi, N., van der Schaar, M., & Cannesson, M. P. (2023) · Anesthesia & Analgesia · doi:10.1213/ane.0000000000006753 · Cited by 8
Self-citationWang, J.-W. D. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0000529 · Cited by 8
Automated Machine Learning in medical research: A systematic literature mapping study
Castro, G. A., Barioto, L. G., Cao, Y. H., Silva, R. M., Caseli, H. D. M., Machado‐Neto, J. A., Cerri, R., Villavicencio, A., & Almeida, T. A. (2025) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2025.103302 · Cited by 8
Boie, S. D., Giesa, N., Sekutowicz, M., Zhumagambetov, R., Haufe, S., Grünewald, E., & Balzer, F. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2026.1746867 · Cited by 9
Data Science Methods for Nursing-Relevant Patient Outcomes and Clinical Processes
Schultz, M. A., Walden, R. L., Cato, K., Coviak, C. P., Cruz, C., D’Agostino, F., Douthit, B. J., Forbes, T. H., Gao, G., Lee, M. A., et al. (2021) · CIN Computers Informatics Nursing · doi:10.1097/cin.0000000000000705 · Cited by 10
Stolze, A., van de Garde, E. M. W., Posthuma, L. M., Hollmann, M. W., Boer, D. D. K., Smit-Fun, V. M., Bühre, W., Boer, C., Noordzij, P. G., on behalf of the TRACE Study investigators, et al. (2022) · BMC Anesthesiology · doi:10.1186/s12871-022-01564-1 · Cited by 8
Value-Based Care and Anesthesiology in the USA
Ahmed, F., Chithrala, B., Barve, K., Biladeau, S. K., & Clifford, S. P. (2023) · Cureus · doi:10.7759/cureus.44410 · Cited by 7
“Opportunities lie in leveraging technology, such as electronic health records and data analytics, to facilitate data-driven decision-making, optimize care coordination, and measure performance [15].”
BackgroundWingert, T., Williams, T., Syed, B., Hill, B., Grogan, T., Young, A., Antongiorgi, Z. D., Salari, V., Joosten, A., Hofer, I. S., et al. (2026) · British Journal of Anaesthesia · doi:10.1016/j.bja.2025.11.042 · Cited by 7
“9 This model was based on readily-extractable features and performed better than ASA physical status, Charleson Comorbidity Index, and other preoperative scores on most measures of model performance.”
Self-citationLin, E., Lin, C.-H., & Lane, H. (2023) · Asian Journal of Psychiatry · doi:10.1016/j.ajp.2023.103866 · Cited by 7
Kowadlo, G., Mittelberg, Y., Ghomlaghi, M., Stiglitz, D. K., Kishore, K., Guha, R., Nazareth, J. M., & Weinberg, L. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02463-w · Cited by 7
“It is often di ffi cult for clinicians to find the data and calculate the score manually; therefore, they are rarely used [14].”
BackgroundMethodInfluentialOpportunities of AI-powered applications in anesthesiology to enhance patient safety
Kovacheva, V., & Nagle, B. (2024) · International Anesthesiology Clinics · doi:10.1097/aia.0000000000000437 · Cited by 7
Artificial intelligence in anesthesiology – a review
Bogoń, A., Górska, M., Ostojska, M., Kałuża, I., Dziuba, G., & Dobosz, M. (2024) · Journal of Pre-Clinical and Clinical Research · doi:10.26444/jpccr/191550 · Cited by 6
“Advanced analytical models can serve as early warning systems, alerting clinicians to sudden risk changes and aiding in the timely deployment of rapid response teams, thus improving patient monitoring in the hospital [23].”
BackgroundNamavarian, A., Gabinet‐Equihua, A., Deng, Y., Khalid, S., Ziai, H., Deutsch, K. M., Huang, J., Gilbert, R. W., Goldstein, D. P., Yao, C. M. K. L., et al. (2024) · The Laryngoscope · doi:10.1002/lary.31443 · Cited by 6
Artificial intelligence in obstetric anaesthesiology – the future of patient care?
Kong, A. Y. H., Liu, N., Tan, H. S., Sia, A. T. H., & Sng, B. L. (2024) · International Journal of Obstetric Anesthesia · doi:10.1016/j.ijoa.2024.104288 · Cited by 6
Riepe, C., van de Water, R. P., Winter, A., Pfitzner, B., Faraj, L., Ahlborn, R., Schulze, M., Zuluaga, D., Schineis, C., Beyer, K., et al. (2025) · International Journal of Surgery · doi:10.1097/js9.0000000000002372 · Cited by 6
“Furthermore, two studies investigating IHM with cohorts exceeding 50 000 cases also achieved AUROC results over 0.9 [ 18 , 25 ] .”
InfluentialSuh, J., & Lee, S.-W. (2022) · Scientific Reports · doi:10.1038/s41598-022-16144-z · Cited by 6
Zabolotskikh, I. B., Владимирович, Т. Н., Магомедов, М. А., Краснов, В. Г., Chernienko, L. Y., Shevyrev, S. N., Popov, A. S., Tyutyunova, E. V., Ватутин, С. Н., Malyshev, Y. P., et al. (2022) · Annals of critical care · doi:10.21320/1818-474x-2022-3-27-44 · Cited by 6
Hofer, I. S., & Wax, D. B. (2024) · Journal of Medical Systems · doi:10.1007/s10916-024-02106-7 · Cited by 5
“Since the first paper in the anesthesiology literature by Lee et al. in 2018 [1] dozens of papers have been published leveraging electronic health record data to predict a variety of perioperative outcomes such as mortality [2, 3], acute kidney injury (AKI) [2, 4–6], readmission [7–9] and others.”
Self-citationTe, R., Zhu, B., Ma, H., Zhang, X., Chen, S., Huang, Y., & Qi, G. (2024) · BMC Anesthesiology · doi:10.1186/s12871-024-02523-8 · Cited by 4
“Recently, various models have been developed to predict postoperative mortality [6, 7], postoperative pain [8], surgical acceptance [9], hypotension during anesthesia [10–12], surgery time [13, 14], intraoperative bradycardia [15], postoperative delirium [16, 17] and other risk outcomes [18–20].”
BackgroundMethodNonoperating room anesthesia: strategies to improve performance
Anwar, A., Heller, K. O., Esper, S. A., & Ferreira, R. G. (2021) · International Anesthesiology Clinics · doi:10.1097/aia.0000000000000339 · Cited by 4
Lv, S., Li, S., Yu, Z., Wang, K., Qiao, X. J., Gong, D., & Wu, C. (2021) · Journal of Healthcare Engineering · doi:10.1155/2021/4757668 · Cited by 4
“Since the beginning of the twenty-first century, under the guidance of the concept of precision medicine, supported by functional liver anatomy, pathological anatomy, new imaging technologies, new methods of liver function evaluation, and new technologies of liver parenchyma separation, precision liver resection has b…”
BackgroundRetractedHofer, I. S., Kupina, M., Laddaran, L., & Halperin, E. (2022) · Scientific Reports · doi:10.1038/s41598-022-13879-7 · Cited by 4
“The features used in the baseline model were based on previous work by our group predicting postoperative mortality both before and after surgery 3–5 .”
MethodSelf-citationTrends in Clinical Information Systems Research in 2019
Hackl, W. O., Hoerbst, A., & Systems, S. E. F. T. I. Y. S. O. C. I. (2020) · Yearbook of Medical Informatics · doi:10.1055/s-0040-1702018 · Cited by 4
“In this meeting, three papers [6–8] were finally selected as best papers for the CIS section (Table 2).”
BackgroundMachine Learning for Surgical Risk Assessment Decision Systems
Russell, M., Russell, D. M., Corizzo, R., & Japkowicz, N. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892752 · Cited by 3
“The AUC is a valuable metric to gauge model performance [24].”
BackgroundMethodInfluentialChu, L. F., & Kurup, V. (2025) · Current anesthesiology reports · doi:10.1007/s40140-024-00674-5 · Cited by 3
“Hill et al. (2019) successfully demonstrated that a ML-based model, trained on preoperative electronic health record (EHR) data, could predict postoperative mortality more accurately than traditional risk assessment tools [30].”
The role of artificial intelligence in preoperative medicine
Kendale, S. (2021) · International Anesthesiology Clinics · doi:10.1097/aia.0000000000000344 · Cited by 3
Anaesthesiologists as translational scientists
Castellanos, J. G., Perez, A. R., & Perez, R. K. (2020) · British Journal of Anaesthesia · doi:10.1016/j.bja.2019.12.035 · Cited by 3
Kong, S., Ning, X., Sun, J., Ding, K., Hu, J. R., Zhou, X., Ge, Y., Liu, X., Yang, F., Zhang, Z., et al. (2025) · International Journal of Surgery · doi:10.1097/js9.0000000000004536 · Cited by 2
“This granular, longitudinal analytical approach is consistent with the evolving landscape of perioperative medicine, which increasingly employs advanced machine learning to refine complication prediction and guide patient-specific interventions [ 41 , 42 ] .”
Anesthesia for cesarean delivery in the era of artificial intelligence: a narrative review
Frassanito, L., Filetici, N., Raimondo, P., Malvası, A., Gaudiano, A., Peragine, A., Lombardi, F., Vassalli, F., Pasta, G., & Bignami, E. G. (2026) · Journal of Anesthesia Analgesia and Critical Care · doi:10.1186/s44158-025-00326-y · Cited by 2
“In another study, Hill et al. were able to create a fully automated preoperative risk prediction score that forecasted in-hospital mortality better than ASA score, POSPOM score, and Charlson comorbidity score [34].”
InfluentialRetracted on April 24, 2025: Multi-Label Classification for Postoperative Complication Prediction
Luo, X. (2023) · International Conference on Networks, Communications and Information Technology (CNCIT) · doi:10.1145/3605801.3605833 · Cited by 2
RetractedHofer, I. S., Lee, A. C., Grogan, T., Lucero, J. M., & Cannesson, M. P. (2022) · Anesthesia & Analgesia · doi:10.1213/ane.0000000000006229 · Cited by 2
“Finally, in this study, we evaluated many laboratory tests (25) across a range of individuals (2 sexes and 6 ethnicities) resulting in over 300 different measurements.”
MethodSelf-citationSuh, J., Lee, G., Kim, J. W., Shin, J., Kim, Y., Lee, S.-W., & Kim, S. (2024) · JMIR Medical Informatics · doi:10.2196/56893 · Cited by 2
MOVER: Medical Informatics Operating Room Vitals and Events RepositoryPreprint
Samad, M., Rinehart, J. B., Angel, M., Kanomata, Y., Baldi, P., & Cannesson, M. P. (2023) · medRxiv · doi:10.1101/2023.03.03.23286777 · Cited by 2
Self-citationThe Current Use of Artificial Intelligence in Anesthesiology
Feldheim, T. V., Brennan, M. M., & Tighe, P. J. (2025) · Advances in Anesthesia · doi:10.1016/j.aan.2025.07.006 · Cited by 1
Bedeutung von künstlicher Intelligenz für die Risikoerkennung vor chirurgischen Eingriffen
Rosenberg, G. S., & Egloff, C. (2024) · Arthroskopie · doi:10.1007/s00142-024-00673-y · Cited by 1
Machine learning models in anaesthesiology: bridging the gap from model training to implementation
King, C. R., & Fritz, B. A. (2026) · British Journal of Anaesthesia · doi:10.1016/j.bja.2026.03.022 · Cited by 1
Perspectives on AI in Anaesthesiology
Kovacheva, V. (2023) · AI in Clinical Medicine · doi:10.1002/9781119790686.ch23
Retracted: Predictive Analysis Techniques of Disease using Machine Learning
Naaz, R., & Karunakaran, V. (2022) · International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT) · doi:10.1109/icerect56837.2022.10060049
“This puts forth the theory that doctors can diagnose diseases more effectively by using supervised learning as a potent tool [1].”
BackgroundRetractedAnalytical Approach of Machine Learning for Prediction Models
Kumar, M., & Dubey, S. K. (2023) · International Conference on Contemporary Computing and Informatics (IC3I) · doi:10.1109/ic3i59117.2023.10397812
Kricfalusi, M., Rice, R. C., Cabrera, A., Dasari, P., Chung, D., Case, T. R., Ruckle, D., Liu, J. N., Cheng, W. K., & Danisa, O. (2024) · International Journal of Research in Orthopaedics · doi:10.18203/issn.2455-4510.intjresorthop20240402
Dasari, P., Rice, R. C., Cabrera, A., Kricfalusi, M., Case, T. R., Gulbrandsen, M. T., Brown, J., & Phipatanakul, W. P. (2024) · International Journal of Research in Orthopaedics · doi:10.18203/issn.2455-4510.intjresorthop20240401
Hofmann, J., Bouras, A., Patel, D. M., Chetla, N., Balaji, N., & Boulis, M. (2024) · medRxiv · doi:10.1101/2024.05.18.24307573
Enhanced Recovery and Prehabilitation in the Perioperative Setting
Esper, S. A., Holder‐Murray, J., & Mahajan, A. (2024) · Springer eBooks · doi:10.1007/978-3-031-72862-4_4
Self-citationKünstliche Intelligenz im Endoskopiemanagement
Denzer, U. W. (2025) · Die Gastroenterologie · doi:10.1007/s11377-024-00843-2
Mirza, M., Mehtab, M., Islam, B., & Shahbaz, S. (2025) · The Healer Journal of Physiotherapy and Rehabilitation Sciences · doi:10.55735/hjprs.v5i1.330
Deshpande, L. K. (2025) · Iterative International Publishers eBooks · doi:10.58532/nbennurapsfsw12
Artificial intelligence in perioperative neurosciences
Shrestha, G. S., Acharya, P., & Mainali, S. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-22273-3.00056-0
Bishara, A. M., Chiu, C., Whitlock, E. L., Douglas, V. C., Lee, S., Butte, A. J., Leung, J. M., & Donovan, A. L. (2022) · Figshare · doi:10.6084/m9.figshare.17799098
Bishara, A. M., Chiu, C., Whitlock, E. L., Douglas, V. C., Lee, S., Butte, A. J., Leung, J. M., & Donovan, A. L. (2022) · Figshare · doi:10.6084/m9.figshare.17799092
Kowadlo, G., Mittelberg, Y., Ghomlaghi, M., Stiglitz, D. K., Kishore, K., Guha, R., Nazareth, J. M., & Weinberg, L. (2024) · Figshare · doi:10.6084/m9.figshare.26691949
Peng, X., Zhu, T., Wang, T., Wang, F., Li, K., & Hao, X. (2022) · Figshare · doi:10.6084/m9.figshare.21077853
Ehrmann, D. (2026) · Die Diabetologie · doi:10.1007/s11428-025-01410-1
He, J., Zhao, J., Luo, Y., Li, M., Han, Y., Wei, D., Wang, Y., & Hou, Z. (2026) · Surgical Endoscopy · doi:10.1007/s00464-026-12576-0
AI-Driven Prediction of ICU Admission After Left Heart Catheterization: A Machine Learning Approach
Atmaja, A. P., Fatichah, C., Anggraini, R. N. E., & Khotimah, W. N. (2025) · International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) · doi:10.1109/isriti68345.2025.11393089
Cafferty, O. B., Jeffries, S. D., Tu, Z., Pelletier, E. D., Sinha, A., Hemmerling, T. M., & collaborators (2026) · Anesthesia & Analgesia · doi:10.1213/ane.0000000000007992
Widnyana, I. M. G., Sudiantara, P. H., Senapathi, T. G. A., & Putra, I. M. P. (2026) · IntechOpen eBooks · doi:10.5772/intechopen.1016011
Zhang, P., Wu, L., Liao, Y., & Li, H. (2026) · Journal of International Medical Research · doi:10.1177/03000605261454051
Özkılıç, M. (2026) · Healthcare · doi:10.3390/healthcare14172785
“Fritz et al. and Hill et al. demonstrated the feasibility of applying advanced analytical methods to postoperative mortality prediction [4,8], while Kendale et al. showed the potential of supervised machine learning for predicting post-induction hypotension [12].”
InfluentialDing, Z., Han, G., Ma, T., Wang, F., Hajagos, J., Kurç, T., & Kumar, A. R. (2026) · medRxiv · doi:10.64898/2026.09.02.26361824
Metadata
- Authors
- Hill, B. L., Brown, R., Gabel, E., Rakocz, N., Lee, C., Cannesson, M., Baldi, P., Olde Loohuis, L., Johnson, R., Jew, B., Maoz, U., Mahajan, A., Sankararaman, S., Hofer, I., & Halperin, E.
- Affiliations
- University of California, Los Angeles (US)
- University of California, Irvine (US)
- California Institute of Technology (US)
- University of Pittsburgh (US)
- Corresponding author
- Hofer, Ira
- ORCID
- Venue
- British Journal of Anaesthesia
- Publisher
- Elsevier BV
- Published
- 2019-12
- Volume
- 123
- Issue
- 6
- Pages
- 877-886
- ISSN
- 0007-0912 (ISSN-L)
- PMC
- PMC6883494
- OpenAlex
- W2980769368
- Cited by
- 103
- References
- 39
- Citations by year
- 2026: 14 · 2025: 16 · 2024: 19 · 2023: 13 · 2022: 21 · 2021: 12 · 2020: 7 · 2019: 1
- FWCI
- 7.40
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- Locations
- British Journal of Anaesthesia (publishedVersion)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- eScholarship (California Digital Library) (submittedVersion)
- CaltechAUTHORS (California Institute of Technology) (submittedVersion, cc-by-nc-nd)
- CaltechAUTHORS (California Institute of Technology) (submittedVersion)
- Chapman University Digital Commons (Chapman University) (submittedVersion)
- Funders
- National Institute of Mental Health (K99MH116115)
- University of California, Los Angeles (DGE- 1650604)
- National Institute of Neurological Disorders and Stroke (T32NS048004)
- National Institutes of Health (III-1705121, R01 NR013912, R01 GM117622, R00GM111744, R35GM125055)
- Alfred P. Sloan Foundation
- National Science Foundation (III-1705121, 1705197)
- Masimo
- Edwards Lifesciences
- Okawa Foundation for Information and Telecommunications
- Topics
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Cardiac, Anesthesia and Surgical Outcomes
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- postoperative mortality prediction, preoperative risk assessment, electronic health record data, random forest, general anesthesia, surgical patients, ASA physical status, Charlson Comorbidity Index
- MeSH terms
- Machine Learning, Adolescent, Adult, Aged, Aged, 80 and over, California, Female, Health Status, Humans, Male, Middle Aged, Postoperative Complications, Risk Factors, Comorbidity, Hospital Mortality, Risk Assessment, Young Adult, Preoperative Period, 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
