Data-Driven Decisions for Reducing Readmissions for Heart Failure: General Methodology and Case Study
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
BACKGROUND: Several studies have focused on stratifying patients according to their level of readmission risk, fueled in part by incentive programs in the U.S. that link readmission rates to the annual payment update by Medicare. Patient-specific predictions about readmission have not seen widespread use because of their limited accuracy and questions about the efficacy of using measures of risk to guide clinical decisions. We construct a predictive model for readmissions for congestive heart failure (CHF) and study how its predictions can be used to perform patient-specific interventions. We assess the cost-effectiveness of a methodology that combines prediction and decision making to allocate interventions. The results highlight the importance of combining predictions with decision analysis. METHODS: We construct a statistical classifier from a retrospective database of 793 hospital visits for heart failure that predicts the likelihood that patients will be rehospitalized within 30 days of discharge. We introduce a decision analysis that uses the predictions to guide decisions about post-discharge interventions. We perform a cost-effectiveness analysis of 379 additional hospital visits that were not included in either the formulation of the classifiers or the decision analysis. We report the performance of the methodology and show the overall expected value of employing a real-time decision system. FINDINGS: For the cohort studied, readmissions are associated with a mean cost of $13,679 with a standard error of $1,214. Given a post-discharge plan that costs $1,300 and that reduces 30-day rehospitalizations by 35%, use of the proposed methods would provide an 18.2% reduction in rehospitalizations and save 3.8% of costs. CONCLUSIONS: Classifiers learned automatically from patient data can be joined with decision analysis to guide the allocation of post-discharge support to CHF patients. Such analyses are especially valuable in the common situation where it is not economically feasible to provide programs to all 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.
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“While prior research has explored applications of machine learning to domains where human judgments are part of the data labeling process (crime [7, 21, 43], medical diagnosis [6, 22]), the selective labels problem is often overlooked, with evaluation of the models typically carried out by computing traditional metrics such as AUC or accuracy only on the data points for which ground truth labels”
From The Selective Labels Problem: Evaluating Algorithmic Predictions in the Presence of Unobservables (2017) · cites this paper as [6]
Experimental — accuracy not yet measured
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
Regression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482
Rehospitalizations among Patients in the Medicare Fee-for-Service Program
Jencks, S. F., Williams, M. V., & Coleman, E. A. (2009) · New England Journal of Medicine · doi:10.1056/nejmsa0803563 · Cited by 5,164
Rich, M. W., Beckham, V., Wittenberg, C., Leven, C. L., Freedland, K. E., & Carney, R. M. (1995) · New England Journal of Medicine · doi:10.1056/nejm199511023331806 · Cited by 2,328
The Care Transitions Intervention: Results of a Randomized Controlled Trial
Coleman, E. A., Parry, C., Chalmers, S., & Min, S.-J. (2006) · Archives of Internal Medicine · doi:10.1001/archinte.166.17.1822 · Cited by 1,937
Risk Prediction Models for Hospital Readmission: A Systematic Review
Kansagara, D., Englander, H., Salanitro, A., Kagen, D., Theobald, C., Freeman, M., & Kripalani, S. (2011) · JAMA · doi:10.1001/jama.2011.1515 · Cited by 1,707
The Medicare Payment Advisory Commission.
Pw, C. (1998) · PubMed · Cited by 1,172
Hernandez, A. F. (2010) · JAMA · doi:10.1001/jama.2010.533 · Cited by 1,032
van Walraven, C., Dhalla, I. A., Bell, C., Etchells, E., Stiell, I. G., Zarnke, K., Austin, P. C., & Forster, A. J. (2010) · Canadian Medical Association Journal · doi:10.1503/cmaj.091117 · Cited by 960
Peikes, D., Chen, A., Schore, J., & Brown, R. (2009) · JAMA · doi:10.1001/jama.2009.126 · Cited by 767
Krumholz, H. M., Amatruda, J., Smith, G. L., Mattera, J. A., Roumanis, S. A., Radford, M. J., Crombie, P., & Vaccarino, V. (2002) · Journal of the American College of Cardiology · doi:10.1016/s0735-1097(01)01699-0 · Cited by 656
Research works printed but not linked: 2
- Center for Medicare and Medicaid Services (2009) Proposed changes to the hospital inpatient prospective payment system for acute care hospitals. Federal Register. May 22;74(98): 24166. Available at: http://edocket.access.gpo.gov/2009/pdf/E9-10458.pdf.
- L Wang, 2012, Predicting risk of hospitalization or death among patients with heart failure in the veterans health administration, Am J Cardiol, 110(9), 1342, 10.1016/j.amjcard.2012.06.038 · DOI
Cited by
Artificial Intelligence and Black‐Box Medical Decisions: Accuracy versus Explainability
London, A. J. (2019) · Hastings Center Report · doi:10.1002/hast.973 · Cited by 801
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
Bansal, G., Wu, T., Zhou, J., Fok, R., Nushi, B., Kamar, E., Ribeiro, M. T., & Weld, D. S. (2020) · arXiv · doi:10.48550/arxiv.2006.14779 · Cited by 754
“ns, but the people retains agency and have accountability on the final decisions. Examples include AI systems that predict likely hospital-readmission to assist doctors with correlated care decisions [5, 11, 65] and AIs that estimate recidivism to help judges decide whether to grant bail to defendants [1, 25]. In such…”
BackgroundDoes the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
Bansal, G., Wu, T., Zhou, J., Fok, R., Nushi, B., Kamar, E., Ribeiro, M. T., & Weld, D. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445717 · Cited by 757
“ns, but the people retains agency and have accountability on the final decisions. Examples include AI systems that predict likely hospital-readmission to assist doctors with correlated care decisions [5, 11, 65] and AIs that estimate recidivism to help judges decide whether to grant bail to defendants [1, 25]. In such…”
BackgroundMachine Learning for Healthcare: On the Verge of a Major Shift in Healthcare Epidemiology
Wiens, J., & Shenoy, E. S. (2018) · Clinical Infectious Diseases · doi:10.1093/cid/cix731 · Cited by 574
“[23, 24]) to prediction tasks (eg, predicting 30-day readmissions [25]).”
BackgroundBeyond prediction: using big data for policy problems
Athey, S. (2017) · Science · doi:10.1126/science.aal4321 · Cited by 575
Will Humans-in-the-Loop Become Borgs? Merits and Pitfalls of Working with AI
Fügener, A., Grahl, J., Gupta, A., & Ketter, W. (2021) · MIS Quarterly · doi:10.25300/misq/2021/16553 · Cited by 469
“Possible applications are discussed in Bansal et al. (2019a) and include medical decision making (e.g., Bayati et al. 2014 on the prediction of readmission rates to support physicians) or legal support (e.g., Angwin et al. 2016 on recidivism prediction to support judges).”
BackgroundBeyond Accuracy: The Role of Mental Models in Human-AI Team Performance
Bansal, G., Nushi, B., Kamar, E., Lasecki, W. S., Weld, D. S., & Horvitz, E. (2019) · Proceedings of the AAAI Conference on Human Computation and Crowdsourcing · doi:10.1609/hcomp.v7i1.5285 · Cited by 466
“Following Bansal et al. (2019), we focus on a simple form of human-AI teamwork that is common in many real-world settings, such as a 30-day readmission classifier supporting a doctor (Bayati et al. 2014) or a recidivism predictor supporting judges in courts (Angwin et al. 2016).”
BackgroundSelf-citationAnalysis of machine learning techniques for heart failure readmissions
Mortazavi, B. J., Downing, N. S., Bucholz, E. M., Dharmarajan, K., Manhapra, A., Li, S.-X., Negahban, S. N., & Krumholz, H. M. (2016) · Circulation: Cardiovascular Quality and Outcomes · doi:10.1161/circoutcomes.116.003039 · Cited by 401
“This technique has been applied to preliminary learning work with electronic health records.(20) SVM is a methodology that creates clearer separation of classes of variables using nonlinear decision boundaries, or hyperplanes, from complex, multidimensional data in possibly infinite dimensional spaces.”
MethodBig data analytics to improve cardiovascular care: promise and challenges
Rumsfeld, J. S., Joynt, K. E., & Maddox, T. M. (2016) · Nature Reviews Cardiology · doi:10.1038/nrcardio.2016.42 · Cited by 398
Explanations Can Reduce Overreliance on AI Systems During Decision-Making
Vasconcelos, H., Jörke, M., Grunde-McLaughlin, M., Gerstenberg, T., Bernstein, M. S., & Krishna, R. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579605 · Cited by 402
“The intuition runs that, if people see an explanation that is incorrect, they will more carefully scrutinize the prediction and be less likely to overrely [6, 10, 11].”
BackgroundUpdates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff
Bansal, G., Nushi, B., Kamar, E., Weld, D. S., Lasecki, W. S., & Horvitz, E. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33012429 · Cited by 284
“In our studies, we focus on a simple, but common, model of human-AI teamwork that abstracts many real-world settings, e.g., a 30-day readmission classifier supporting a doctor (Bayati et al. 2014), a recidivism predictor supporting judges in courts (Angwin et al. 2016).”
BackgroundMethodInfluentialSelf-citationGolas, S. B., Shibahara, T., Agboola, S., Otaki, H., Sato, J., Nakae, T., Hisamitsu, T., Kojima, G., Felsted, J., Kakarmath, S., et al. (2018) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-018-0620-z · Cited by 287
“Citing the mixed results of readmission prediction models for HF patients which use traditional methods, recent studies [7, 11 – 14] are testing whether machine learning methods, which can take into account higher-order and nonlinear interactions between predictors, might demonstrate higher…”
ResultOnline Decision Making with High-Dimensional Covariates
Bastani, H., & Bayati, M. (2020) · Operations Research · doi:10.1287/opre.2019.1902 · Cited by 263
Self-citationNaiseh, M., Al-Thani, D., Jiang, N., & Ali, R. (2023) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2022.102941 · Cited by 170
Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations
Chen, V., Liao, Q. V., Wortman Vaughan, J., & Bansal, G. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3610219 · Cited by 220
“Providing decision-makers with explanations of the AI’s predictions is thought to improve appropriate reliance because decision-makers will be less likely to follow the AI prediction if an explanation suggests flawed model reasoning [5, 12, 17].”
BackgroundPredicting all-cause risk of 30-day hospital readmission using artificial neural networks
Jamei, M., Nisnevich, A., Wetchler, E., Sudat, S., & Liu, E. (2017) · PLOS ONE · doi:10.1371/journal.pone.0181173 · Cited by 145
Awan, S. E., Bennamoun, M., Sohel, F. A., Sanfilippo, F. M., & Dwivedi, G. (2019) · ESC Heart Failure · doi:10.1002/ehf2.12419 · Cited by 157
“Lastly, some of the previous studies have reported slightly higher AUCs than ours.(9,11,13) However, our MLP-based approach produces a comparable AUC of 0.”
ResultThe Selective Labels Problem: Evaluating Algorithmic Predictions in the Presence of Unobservables
Lakkaraju, H., Kleinberg, J., Leskovec, J., Ludwig, J., & Mullainathan, S. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098066 · Cited by 138
“While prior research has explored applications of machine learning to domains where human judgments are part of the data labeling process (crime [7, 21, 43], medical diagnosis [6, 22]), the selective labels problem is oen overlooked, with evaluation of the models typically carried out by computing traditional metrics…”
BackgroundMachine learning in heart failure: ready for prime time
Awan, S. E., Sohel, F. A., Sanfilippo, F. M., Bennamoun, M., & Dwivedi, G. (2017) · Current Opinion in Cardiology · doi:10.1097/hco.0000000000000491 · Cited by 128
“Who goes first? Influences of human-AI workflow on decision making in clinical imaging,”
Fogliato, R., Chappidi, S., Lungren, M., Fisher, P., Wilson, D., Fitzke, M., Parkinson, M., Horvitz, E., Inkpen, K., & Nushi, B. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533193 · Cited by 103
Self-citationHospital Readmissions Reduction Program: An Economic and Operational Analysis
Zhang, D., Gurvich, I., Mieghem, J. A. V., Park, E., Young, R. S. K., & Williams, M. V. (2016) · Management Science · doi:10.1287/mnsc.2015.2280 · Cited by 101
“…et al. 1999, Hansen et al. 2013, Hu et al. 2014), keeping patients longer in the in-patient unit (Bartel et al. 2014), using machine learning techniques (Bayati et al. 2014), and conducting a nurse-directed multidisciplinary intervention (Rich et al. 1995) – can effectively reduce readmissions.”
MethodHuang, C., Li, S.-X., Caraballo, C., Masoudi, F. A., Rumsfeld, J. S., Spertus, J. A., Normand, S.-L. T., Mortazavi, B. J., & Krumholz, H. M. (2021) · Circulation: Cardiovascular Quality and Outcomes · doi:10.1161/circoutcomes.120.007526 · Cited by 83
Bao, Y., Gong, W., & Yang, K. (2023) · Systems · doi:10.3390/systems11090442 · Cited by 80
“Embracing AI as a collaborative partner empowers humans to tackle complex challenges more effectively and paves the way for a promising future with human–AI synergy [87].”
Using Future Information to Reduce Waiting Times in the Emergency Department via Diversion
Xu, K., & Chan, C. W. (2016) · Manufacturing & Service Operations Management · doi:10.1287/msom.2015.0573 · Cited by 102
Shaping a multidisciplinary understanding of team trust in human-AI teams: a theoretical framework
Ulfert, A., Georganta, E., Jorge, C. C., Mehrotra, S., & Tielman, M. L. (2023) · European Journal of Work and Organizational Psychology · doi:10.1080/1359432x.2023.2200172 · Cited by 123
“For instance, an AI team member may support doctors with predictions of likely hospital readmission based on correlated care decisions (e.g., Bayati et al., 2014; Caruana et al., 2015).”
BackgroundHou, C., Zhu, G., & Sudarshan, V. (2025) · British Journal of Educational Technology · doi:10.1111/bjet.13613 · Cited by 72
Risk factors for 30-day readmission in patients with congestive heart failure
Mirkin, K. A., Enomoto, L. M., Caputo, G. M., & Hollenbeak, C. S. (2017) · Heart & Lung · doi:10.1016/j.hrtlng.2017.06.005 · Cited by 76
Diagnosing bias in data-driven algorithms for healthcare
Wiens, J., Price, W. N., & Sjoding, M. W. (2020) · Nature Medicine · doi:10.1038/s41591-019-0726-6 · Cited by 69
Matheny, M. E., Goldsack, J. C., Saria, S., Shah, N. H., Gerhart, J., Cohen, I. G., Price, W. N., Patel, B., Payne, P. R. O., Embí, P. J., et al. (2025) · Health Affairs · doi:10.1377/hlthaff.2024.01003 · Cited by 55
Self-citationLeveraging Big Data Tools and Technologies: Addressing the Challenges of the Water Quality Sector
Romero, J. P., Hallett, S. H., & Jude, S. (2017) · Sustainability · doi:10.3390/su9122160 · Cited by 60
“Examples may be drawn from the visual analysis of air quality [19], the cost-effective allocation of CO2 emissions [24], the evaluation and identification of cost-effective acid mine drainage management [25], the forecasting of risk in criminal justice decision [26], the reduction of readmission risk in hospital patie…”
BackgroundDonaho, E. K., Hall, A. C., Gass, J. A., Elayda, M. A., Lee, V., Pairé, S., & Meyers, D. E. (2015) · Journal of the American Heart Association · doi:10.1161/jaha.115.002296 · Cited by 51
“In 2009, the mean cost of a HF admission was $13 000.(42) There is a human cost to the HF readmission statistics, as well as clear societal and”
BackgroundBrom, H., Brooks Carthon, J. M., Ikeaba, U., & Chittams, J. (2020) · Journal of Nursing Care Quality · doi:10.1097/ncq.0000000000000412 · Cited by 47
“16,17 In the next phase of this project, our work group plans to use the readmission profile developed from our machine-learning algorithm to automatically identify patients at high risk for 30-day readmissions.”
BackgroundMethodInfluentialTiming It Right: Balancing Inpatient Congestion vs. Readmission Risk at Discharge
Shi, P., Helm, J. E., Deglise‐Hawkinson, J., & Pan, J. (2018) · Operations Research · doi:10.1287/opre.2020.2044 · Cited by 53
Data-Driven Artificial Intelligence for Calibration of Hyperspectral Big Data
Sagan, V., Maimaitijiang, M., Paheding, S., Bhadra, S., Gosselin, N., Burnette, M., Demieville, J., Hartling, S., LeBauer, D. S., Newcomb, M. S., et al. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3091409 · Cited by 43
“For example, data-driven approaches have yielded recent successes in drug discovery [10]–[12], health care [13]–[15], and urban planning [16], [17].”
BackgroundSharma, V., Kulkarni, V., McAlister, F. A., Eurich, D. T., Keshwani, S., Simpson, S. H., Voaklander, D. C., & Samanani, S. (2021) · Journal of Cardiac Failure · doi:10.1016/j.cardfail.2021.12.004 · Cited by 50
Liu, X., Hu, M., Helm, J. E., Lavieri, M. S., & Skolarus, T. A. (2018) · Production and Operations Management · doi:10.1111/poms.12858 · Cited by 41
“Bayati et al. (2014) builds a classification model to predict readmissions and analyzed intervention decisions.”
BackgroundLv, H., Yang, X., Wang, F., Wang, S., Du, X., Tan, Q., Hao, Z., Liu, Y., Yan, J., & Xia, Y. (2021) · Journal of Medical Internet Research · doi:10.2196/24996 · Cited by 55
“…methods, recent research is adopting ML techniques for predicting HF mortality, readmission, and medication adherence, which might demonstrate better performance in their predictions because of their consideration of higher order and nonlinear relationships between multidimensional variables [21].”
Ben‐Assuli, O., Heart, T., Klempfner, R., & Padman, R. (2023) · Decision Support Systems · doi:10.1016/j.dss.2023.113982 · Cited by 43
Using passively collected sedentary behavior to predict hospital readmission
Bae, S., Dey, A. K., & Low, C. A. (2016) · Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2971648.2971750 · Cited by 38
“Previous research has identified medical predictors of readmission [2][6], but behavioral factors including inadequate levels of activity in the hospital may also play an important and relatively unexplored role [11].”
BackgroundPrediction of Adverse Events in Patients Undergoing Major Cardiovascular Procedures
Mortazavi, B. J., Desai, N., Zhang, J., Coppi, A., Warner, F., Krumholz, H. M., & Negahban, S. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2017.2675340 · Cited by 38
“These targeted models for care can help identify patient risk factors and predictors [10], [11] as well as potentially address costs of care [12], [13].”
BackgroundMethodData-driven decision making in patient management: a systematic review
Lyu, G. (2025) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-025-03072-x · Cited by 76
“…by DDDM has enhanced the patient risk classification for heart failure and enhanced the chances of reducing hospital readmission in cardiology [8] In the field of neurological and mental health, DDDM has helped in precise predictive modeling to help clinicians to determine the probability of…”
InfluentialChoosing Wisely clinical decision support adherence and associated inpatient outcomes.
Heekin, A. M., Kontor, J. T., Sax, H. C., Keller, M. S., Wellington, A., & Weingarten, S. R. (2018) · PubMed · Cited by 30
Predicting preventable hospital readmissions with causal machine learning
Marafino, B. J., Schuler, A., Liu, V. X., Escobar, G. J., & Baiocchi, M. (2020) · Health Services Research · doi:10.1111/1475-6773.13586 · Cited by 33
“11 Instead of prioritizing the patients most at risk, we prioritize those with the treatment effects ̂𝜏 i 0 that are largest in magnitude, that is, the most negative.”
BackgroundAPLUS: A Python library for usefulness simulations of machine learning models in healthcare
Wornow, M., Gyang Ross, E., Callahan, A., & Shah, N. H. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104319 · Cited by 26
Evaluating Patient Readmission Risk: A Predictive Analytics Approach
Choudhury, A., & Greene, C. (2018) · American Journal of Engineering and Applied Sciences · doi:10.3844/ajeassp.2018.1320.1331 · Cited by 30
“Bayati et al. (2014) evaluated the cost-effectiveness and efficiency of the methodology that combines prediction and decision making.”
Predicting Emergency Department Visits.
Poole, S. F., Grannis, S. J., & Shah, N. H. (2016) · PubMed Central · Cited by 25
Analysis of Medicare Pay-for-Performance ContractsPreprint
Bastani, H., Bayati, M., Braverman, M., & Johari, R. (2016) · SSRN Electronic Journal · doi:10.2139/ssrn.2839143 · Cited by 24
“On the other hand, empirical estimates place the cost of a 30-day heart failure readmission to be $13,679 with a standard error of $1,214 (in 2010 dollars), where the number of samples was 793 (Bayati et al. 2014).”
BackgroundSelf-citationThe consequences of AI training on human decision-making
Treiman, L. S., Ho, C.-J., & Kool, W. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2408731121 · Cited by 32
Ssebyala, S. N., Kintu, T. M., Muganzi, D. J., Dresser, C. J., Demetres, M. R., Lai, Y., Mercy, K., Li, C., Wang, F., Setoguchi, S., et al. (2024) · PLOS Climate · doi:10.1371/journal.pclm.0000338 · Cited by 21
From Prediction to Action: Improving User Experience With Data-Driven Resource Allocation
Bao, Y., Wu, H., & Liu, X. (2017) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2017.2680918 · Cited by 21
“The problem of patient readmission in hospitals with congestive heart failure is considered by [19].”
BackgroundDynamic Batch Learning in High-Dimensional Sparse Linear Contextual Bandits
Ren, Z., & Zhou, Z. (2023) · Management Science · doi:10.1287/mnsc.2023.4895 · Cited by 55
End-To-End Bias Mitigation: Removing Gender Bias in Deep Learning
Feldman, T., & Peake, A. (2021) · arXiv · doi:10.48550/arxiv.2104.02532 · Cited by 19
“…have been deployed to determine optimal coinsurance rates and tax rates [1], efficiently allocate health inspectors in cities [2], decide which patients receive medical interventions based on predicted risk of heart failure [3], assess risk in numerous criminal justice decisions [4], and much more.”
Li, Q., Yao, X., & Échevin, D. (2020) · Value in Health · doi:10.1016/j.jval.2020.06.009 · Cited by 25
Song, H., & Veeraraghavan, S. K. (2018) · Wiley eBooks · doi:10.1002/9781119300977.ch5 · Cited by 17
Barr, P. J., Haslett, W. R., Dannenberg, M. D., Oh, L., Elwyn, G. J., Hassanpour, S., Bonasia, K., Finora, J. C., Schoonmaker, J. A., Onsando, W. M., et al. (2021) · Journal of Medical Internet Research · doi:10.2196/25512 · Cited by 17
“Such NLP methods have been used to predict hospital readmissions [37], future radiology utilization [38], and medical conditions in clinical decision support systems [39].”
Predicting High Imaging Utilization Based on Initial Radiology Reports:
Hassanpour, S., & Langlotz, C. P. (2015) · Academic Radiology · doi:10.1016/j.acra.2015.09.014 · Cited by 16
“In a recent related work with a different focus, a readmission prediction model identified patients at high risk of being rehospitalized soon after the discharge for congestive heart failure (16).”
BackgroundBurkhardt, H. A., Ding, X., Kerbrat, A. H., Comtois, K. A., & Cohen, T. (2023) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocad062 · Cited by 15
Predicting all-cause 90-day hospital readmission for dental patients using machine learning methods
Li, W., Lipsky, M. S., Hon, E. S., Su, W., Su, S., He, Y., Holubkov, R., Sheng, X., & Hung, M. (2021) · BDJ Open · doi:10.1038/s41405-021-00057-6 · Cited by 15
Improving hospital readmission prediction using individualized utility analysis
Ko, M., Chen, E., Agrawal, A., Rajpurkar, P., Avati, A., Ng, A., Basu, S., & Shah, N. H. (2021) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2021.103826 · Cited by 15
Ganoe, C. H., Wu, W., Barr, P. J., Haslett, W. R., Dannenberg, M. D., Bonasia, K., Finora, J. C., Schoonmaker, J. A., Onsando, W. M., Ryan, J., et al. (2021) · JAMIA Open · doi:10.1093/jamiaopen/ooab071 · Cited by 15
“These methods have been used to predict hospital readmissions,[43] future radiology utilizations,[44] and characterization of significance, change, and urgency of clinical findings in medical records.”
MethodGender-sensitive word embeddings for healthcare
Agmon, S., Gillis, P., Horvitz, E., & Radinsky, K. (2021) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocab279 · Cited by 18
“53 We follow Lin et al 54 for the definition of an unplanned readmission: Patients that were transferred from the ICU to low-level wards or discharged, but within 30 days they either returned to the ICU or died.”
Self-citationStatistical analysis of a low cost method for multiple disease prediction
Bayati, M., Bhaskar, S. A., & Andrea Montanari, A. (2016) · Statistical Methods in Medical Research · doi:10.1177/0962280216680242 · Cited by 14
“An admittedly incomplete list of such studies include: stroke prediction via Cox proportional hazard models,(10) relational functional gradient boosting in myocardial infarction prediction,(11) support vector machines and naive Bayes classifiers for cancer prediction,(12) neural networks for mortality prediction,(13)…”
BackgroundSelf-citationDoes quality help the financial viability of hospitals? A data envelopment analysis approach
Önder, Ö., Cook, W. D., & Kristal, M. M. (2021) · Socio-Economic Planning Sciences · doi:10.1016/j.seps.2021.101105 · Cited by 13
Liu, X., Guo, Y., Li, D., Cui, Z., Liu, Y., Li, C., & Ma, J. (2017) · Medicine · doi:10.1097/md.0000000000007953 · Cited by 11
“These rehospitalizations are responsible for the dramatically increased medical costs of diabetes treatment,([3]) as they place substantial physical and psychological stresses on patients and reflect suboptimal patient outcomes.([4,5]) Diabetes-related readmissionswere primarily driven by the severity of illness, the…”
BackgroundVijayakumar, R., & Cheung, M. W. ‐. (2019) · Social Science Computer Review · doi:10.1177/0894439319888445 · Cited by 13
“Machine learning methods, a diverse set of mathematical algorithms that focus on predicting patterns in the given data, are increasingly popular in many areas of science and policy, such as crime detection, prevention and reform (Berk, 2012; Bhattacharyya, Jha, Tharakunnel, & Westland, 2011; Ngai, Hu, Wong, Chen, & Su…”
BackgroundA Low-Cost Method for Multiple Disease Prediction.
Bayati, M., Bhaskar, S. A., & Andrea Montanari, A. (2015) · PubMed · Cited by 11
Self-citationKakarmath, S. S., Golas, S. B., Felsted, J. A., Kvedar, J. C., Jethwani, K., & Agboola, S. O. (2018) · JMIR Research Protocols · doi:10.2196/resprot.9466 · Cited by 13
“Risk prediction models are designed to aid clinical decision making, and in the context of heart failure, their implementation can potentially result in substantial reductions in rehospitalizations and cost savings [19].”
BackgroundMachine Learning in Microbiology: Finding the Signal in the Noise
Tice, A. M., & Farag, H. A. (2019) · Clinical Microbiology Newsletter · doi:10.1016/j.clinmicnews.2019.06.004 · Cited by 11
Ben‐Assuli, O. (2021) · Information Systems Management · doi:10.1080/10580530.2021.1928341 · Cited by 8
“…visit (Felker et al., 2004; Khanna et al., 2014) as shown here (AbdelRahman et al., 2014; Amalakuhan et al., 2012; Amarasingham et al., 2010; Bayati et al., 2014; Chamberlain et al., 2018; Golas et al., 2018; Goto et al., 2019, 2020; Rico et al., 2016; Roberts et al., 2015; Russo et al.,…”
MethodOptimal monitoring policies for chronic diseases under healthcare warranty
Zhao, H., Liu, Z., Li, M., & Liang, L. (2022) · Socio-Economic Planning Sciences · doi:10.1016/j.seps.2022.101384 · Cited by 9
Rizinde, T., Ngaruye, I., & Cahill, N. D. (2023) · Journal of Personalized Medicine · doi:10.3390/jpm13091393 · Cited by 9
“However, issues with limited electronic health data integration and class imbalance in medical datasets are present in low- and middle-income countries [19].”
BackgroundLi, H., Chen, Y., Gao, H., Chang, J., Su, D., Lei, S., Jiang, D., Hu, X., Tan, M., & Chen, Z. (2019) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph16091554 · Cited by 8
“, the Department of Veterans Affairs) [13], because high readmission rates can be a sign of poor clinical care and can indicate a patient’s worsening condition [40], further causing a high economic burden for the patients [41].”
BackgroundTiming it Right: Balancing Inpatient Congestion Versus Readmission Risk at DischargePreprint
Shi, P., Helm, J. E., Deglise‐Hawkinson, J., & Pan, J. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3202975 · Cited by 8
Chan, T. C. Y., Huang, S. Y. M., & Sarhangian, V. (2024) · Operations Research · doi:10.1287/opre.2022.0066 · Cited by 7
HPCC based framework for COPD readmission risk analysis
Jain, P., Agarwal, A., Behara, R. S., & Baechle, C. (2019) · Journal Of Big Data · doi:10.1186/s40537-019-0189-0 · Cited by 10
“[15] on readmission problem for CHF (congestive heart failure) showed a reduction of 18.”
Data-Guided Approach for Learning and Improving User Experience in Computer Networks
Bao, Y., Liu, X., & Pande, A. (2015) · Asian Conference on Machine Learning · Cited by 6
A Continuous-Class Queueing Model With Proportional Hazards-Based RoutingPreprint
Master, N., Reiman, M., Wang, C., & Wein, L. M. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3390476 · Cited by 6
Bao, Y., Wu, H., & Liu, X. (2016) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2939672.2939871 · Cited by 5
“Specific combinations of prediction and actions have been proposed in many areas, such as clinical treatment [4] and route planning [20, 19, 14].”
BackgroundJain, P., Agarwal, A., & Behara, R. S. (2019) · IEEE International Systems Conference (SysCon) · doi:10.1109/syscon.2019.8836797 · Cited by 5
“Healthcare datasets including discharge summaries written by healthcare practitioners at the time of discharge are of high predictive value [1,5-9].”
BackgroundTheocharopoulos, P. C., Bersimis, S., Georgakopoulos, S. V., Karaminas, A., Tasoulis, S. K., & Plagianakos, V. P. (2024) · Journal of Applied Statistics · doi:10.1080/02664763.2024.2315451 · Cited by 6
“Additionally, another study [7] demonstrated a data-driven decision system to reduce heart failure readmissions, showcasing the potential of these models in enhancing healthcare delivery.”
Complementarities between algorithmic and human decision-making: The case of antibiotic prescribing
Ribers, M. A., & Ullrich, H. (2024) · Quantitative Marketing and Economics · doi:10.1007/s11129-024-09284-1 · Cited by 9
Humans Forgo Reward to Instill Fairness into AI
Treiman, L. S., Ho, C.-J., & Kool, W. (2023) · Proceedings of the AAAI Conference on Human Computation and Crowdsourcing · doi:10.1609/hcomp.v11i1.27556 · Cited by 12
“For example, AI assists viewers with deciding what YouTube movie to watch, doctors with determining patient care (Bayati et al. 2014; Giordano et al. 2021; Jiang et al. 2017; Koh et al. 2022), judges with granting bail (Angwin et al. 2016; Hayashi and Wakabayashi 2017; Zavrˇsnik 2020), and public…”
BackgroundAnalysis of Feature Extraction Methods for Prediction of 30-Day Hospital Readmissions
Sumner, J., & Alaeddini, A. (2019) · Methods of Information in Medicine · doi:10.1055/s-0040-1702159 · Cited by 4
“Some of the models are designed to predict the likelihood of readmission for certain conditions such as cardiovascular and heart-related issues, 7,8 diabetes, 9,10 and kidney disease.”
MethodVallon, J., Panjwani, N., Ling, X., Vij, S., Srinivas, S., Leppert, J. T., Bayati, M., & Buyyounouski, M. K. (2022) · medRxiv · doi:10.1101/2022.03.22.22272635 · Cited by 3
Self-citationCost-Aware Calibration of Classifiers
Yang, M., & Bi, X. (2024) · INFORMS Journal on Data Science · doi:10.1287/ijds.2024.0038 · Cited by 12
Heart Analytics: Analytical Modeling of Cardiovascular Care
Dai, T., Gleason, K. T., Hwang, C., & Davidson, P. M. (2019) · Naval Research Logistics (NRL) · doi:10.1002/nav.21880 · Cited by 3
“For example, Bayati et al. (2014) use a machine-learning tool to classify heart failure patients according to their risks of readmission, and customize patient care accordingly.”
Patient-Specific Readmission Prediction and Intervention for Health Care
Zhang, Y. (2023) · International Journal of Prognostics and Health Management · doi:10.36001/ijphm.2019.v10i3.2626 · Cited by 3
“With a set of tunable parameters such as per patient readmission cost, cost of the intervention program, and efficacy of the intervention programs (Bayati et al., 2014), we report the performance of the methodology and show the overall expected value of employing a real-time decision system.”
MethodInfluentialBattling Antibiotic Resistance: Can Machine Learning Improve Prescribing?Preprint
Ribers, M. A., & Ullrich, H. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3392196 · Cited by 2
Collins, S., & Dias, K. J. (2015) · Cardiopulmonary Physical Therapy Journal · doi:10.1097/cpt.0000000000000011 · Cited by 2
“For details on the models and statistical features of the predictors, the reader is referred to the primary sources.(9,14,15) Those That Get Admitted a Lot AreMore Likely to Get Readmitted.”
MethodRiascos, A. J., & Serna, N. (2018) · International Journal of Knowledge Discovery in Bioinformatics · doi:10.4018/ijkdb.2018070103 · Cited by 2
Health Data Analytics: Current Perspectives, Challenges, and Future Directions
Khedo, K. K., Baichoo, S., Nagowah, S. D., Nagowah, L., Mungloo-Dilmohamud, Z., Cadersaib, Z., & Cheerkoot-Jalim, S. (2020) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-030-42934-8_8 · Cited by 3
A Case for Backward Compatibility for Human-AI TeamsPreprint
Bansal, G., Nushi, B., Kamar, E. S., Weld, D. S., Lasecki, W. S., & Horvitz, E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.01148 · Cited by 10
“This example is motivated by real-world applications for reducing patient readmissions and other costly outcomes in healthcare (Bayati et al., 2014; Caruana et al., 2015), and motivates the need for reducing the cost of disruption caused by updates that violate users’ mental models.”
Self-citationMachine Predictions and Human Decisions with Variation in Payoffs and SkillPreprint
Ribers, M. A., & Ullrich, H. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3736484 · Cited by 3
How Different Explanations Impact Trust Calibration: The Case of Clinical Decision Support SystemsPreprint
Naiseh, M., Al‐Thani, D., Jiang, N., & Ali, R. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4098528 · Cited by 2
Naghshbandi, M., Huang, S. Y. M., Shah, H., Yim, C., Lee, E., Caesar, M., Hope, A. J., Chan, T. C. Y., & Sarhangian, V. (2024) · Canadian Liver Journal · doi:10.3138/canlivj-2024-0020 · Cited by 1
Do People Think Fast or Slow When Training AI?
Treiman, L. S., Ho, C.-J., & Kool, W. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732177 · Cited by 7
“AI is increasingly used in decision making in various domains, including medicine [8, 36, 49, 59] and law [2, 43, 115].”
AbdulQawy, A., Sallam, E. A., & Elkholy, A. (2025) · Egyptian Informatics Journal · doi:10.1016/j.eij.2025.100739 · Cited by 2
Developing HPCC Based COPD Readmission Risk Analysis Platform
Jain, P., Agarwal, A., Behara, R. S., & Beachle, C. (2018) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci46756.2018.00209 · Cited by 1
“The study performed by Mohsen Bayati et al [15] on readmission problem for CHF (Congestive Heart Failure)”
MethodOmary, C. S., Wright, P. P., Kumarasamy, M. A., Franks, N. M., Esper, G. J., Mouzon, H. B., Barrolle, S., Horne, K., & Cranmer, J. N. (2021) · Journal for Healthcare Quality · doi:10.1097/jhq.0000000000000318 · Cited by 1
A Unified Regularization Approach to High-Dimensional Generalized Tensor Bandits
Li, J., Yang, Y.-Y., Wang, Y., & Tang, S. (2025) · International Symposium on Information Theory · doi:10.1109/isit63088.2025.11195554 · Cited by 1
“However, with the adoption of targeted therapies, complex associations between drugs, targets, and diseases have become central to research, involving thousands or even tens of thousands of features related to diseases and drugs [9], [10].”
Metadata
- Authors
- Bayati, M., Braverman, M., Gillam, M., Mack, K. M., Ruiz, G., Smith, M. S., & Horvitz, E.
- Affiliations
- Stanford University (US)
- Princeton University (US)
- MedStar Washington Hospital Center (US)
- Microsoft (United States) (US)
- Corresponding author
- Horvitz, Eric
- Venue
- PLoS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2014-10-08
- Volume
- 9
- Issue
- 10
- Pages
- e109264
- ISSN
- 1932-6203 (ISSN-L)
- PMC
- PMC4190088
- OpenAlex
- W2040236338
- Cited by
- 122
- References
- 26
- Citations by year
- 2026: 1 · 2025: 12 · 2024: 9 · 2023: 11 · 2022: 9 · 2021: 17 · 2020: 6 · 2019: 21 · 2018: 11 · 2017: 11 · 2016: 9 · 2015: 5
- FWCI
- 5.73
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- PLoS ONE (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Science Foundation (1216011)
- Microsoft Research
- Topics
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Heart Failure Treatment and Management
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- heart failure, 30-day readmission, predictive modeling, decision analysis, cost-effectiveness, post-discharge interventions, Hospital Readmissions Reduction Program, real-time decision support
- MeSH terms
- Heart Failure, Humans, Models, Theoretical, Patient Readmission, Retrospective Studies, Databases, Factual
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.