Abstract
Hospital readmissions consume large amounts of medical resources and negatively impact the healthcare system. Predicting the readmission rate early one can alleviate the financial and medical consequences. Most related studies only select the patient’s structural features or text features for modeling analysis, which offer an incomplete picture of the patient. Based on structured data (including demographic data, clinical data, administrative data) and medical record text, this paper uses deep learning methods to construct an optimal model for hospital readmission prediction, tested on a dataset of heart disease patients’ 30-day readmission. The results show that when only structured data is used, the deep learning model is much better than the Naive Bayes model and slightly better than the Support Vector Machine model. Adding a text model to the deep learning model improves performance, increasing accuracy and F1-score by 2% and 6%, respectively. This indicates that textual information contributes greatly to hospital readmission predictions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Basu Roy, S., et al.: Dynamic hierarchical classification for patient risk-of-readmission. In: Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1691–1700. ACM (2015)
Mcilvennan, C.K., Eapen, Z.J., Allen, L.A.: Hospital readmissions reduction program. Circulationl 31(20), 1796–1803 (2015)
Center for Health Information and Analysis: Performance of the Massachusetts Health Care System Series: A Focus on Provider Quality (2015)
Benbassat, J., Taragin, M.: Hospital readmissions as a measure of quality of health care: advantages and limitations. Arch. Intern. Med. 160(8), 1074–1081 (2000)
Kamalesh, M., Subramanian, U., Ariana, A., Sawada, S., Peterson, E.: Diabetes status and racial differences in post–myocardial infarction mortality. Am. Heart J. 150(5), 912–919 (2005)
Mahmoud, A.N., et al.: Prevalence, causes, and predictors of 30 day readmissions following hospitalization with acute myocardial infarction complicated by cardiogenic shock: findings from the 2013–2014 National readmissions database. J. Am. Heart Assoc. 7(6), e008235 (2018)
McManus, D.D., Saczynski, J.S., Lessard, D., Waring, M.E., Allison, J., Parish, D.C., TRACE-CORE Investigators.: Reliability of predicting early hospital readmission after discharge for an acute coronary syndrome using claims-based data. Am. J. Cardiol. 117(4), 501–507 (2016)
Yu, S., Farooq, F., Van Esbroeck, A., Fung, G., Anand, V., Krishnapuram, B.: Predicting readmission risk with institution-specific prediction models. Artif. Intell. Med. 65(2), 89–96 (2015)
Hasan, O., et al.: Hospital readmission in general medicine patients: a prediction model. J. Gen. Intern. Med. 25(3), 211–219 (2010)
Braga, P., Portela, F., Santos, M.F., Rua, F.: Data mining models to predict patient’s readmission in intensive care units. In: Proceedings of the 6th International Conference on Agents and Artificial Intelligence, ICAART 2014, vol. 1, pp. 604–610. SCITEPRESS (2014)
Eigner, I., Reischl, D., Bodendorf, F.: Development and evaluation of ensemble-based classification models for predicting unplanned hospital readmissions after hysterectomy (2018)
Wang, H., Cui, Z., Chen, Y., Avidan, M., Abdallah, A.B., Kronzer, A.: Predicting hospital readmission via cost-sensitive deep learning. IEEE/ACM Trans. Comput. Biol. Bioinform. (TCBB) 15(6), 1968–1978 (2018)
Rajkomar, A., et al.: Scalable and accurate deep learning with electronic health records. NPJ Digit. Med. 1(1), 18 (2018)
Xiao, C., Ma, T., Dieng, A.B., Blei, D.M., Wang, F.: Readmission prediction via deep contextual embedding of clinical concepts. PLoS ONE 13(4), e0195024 (2018)
Craig, E., Arias, C., Gillman, D.: Predicting readmission risk from doctors’ notes. arXiv preprint arXiv:1711.10663 (2017)
Golas, S.B., et al.: A machine learning model to predict the risk of 30-day readmissions in patients with heart failure: a retrospective analysis of electronic medical records data. BMC Med. Inf. Decis. Making 18(1), 44 (2018)
Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Advances in Neural Information Processing Systems, pp. 649–657 (2015)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Cheng, Y., Wang, F., Zhang, P., Hu, J.: Risk prediction with electronic health records: a deep learning approach. In: Proceedings of the 2016 SIAM International Conference on Data Mining, pp. 432–440. Society for Industrial and Applied Mathematics (2016)
Saxe, J., Berlin, K.: eXpose: a character-level convolutional neural network with embeddings for detecting malicious URLs, file paths and registry keys. arXiv preprint arXiv:1702.08568 (2017)
Hearst, M.A., Dumais, S.T., Osuna, E., et al.: Support vector machines. IEEE Intell. Syst. Appl. 13(4), 18–28 (1998)
Rish, I.: An empirical study of the naive Bayes classifier. In: Workshop on Empirical Methods in Artificial Intelligence, IJCAI 2001, vol. 3, no. 22, pp. 41–46 (2001)
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China under Grant 71701091 and Grant 71701043, in part by the CityU SRG under Grant 7005195, in part by the Fundamental Research Funds for the Central Universities under Grant 2242019K40157, and in part by the Chinese Ministry of Education Project of Humanities and Social Science under Grant 17YJC870020.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Da, J. et al. (2019). Prediction of Hospital Readmission for Heart Disease: A Deep Learning Approach. In: Chen, H., Zeng, D., Yan, X., Xing, C. (eds) Smart Health. ICSH 2019. Lecture Notes in Computer Science(), vol 11924. Springer, Cham. https://doi.org/10.1007/978-3-030-34482-5_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-34482-5_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-34481-8
Online ISBN: 978-3-030-34482-5
eBook Packages: Computer ScienceComputer Science (R0)