Hospital readmissions of patients put a high burden not only on the health care system, but also on the patients since complications after discharge generally lead to additional burdens. Estimating the risk of readmission after discharge from inpatient care has been the subject of several publications in recent years. In those publications the authors mostly tried to directly infer the readmission risk (within a certain time frame) from the clinical data recorded in the medical routine such as primary diagnosis, co-morbidities, length of stay, or questionnaires. Instead of using these data directly as inputs for a prediction model, we are exploiting latent embeddings for the nominal parts of the data (e.g., diagnosis and procedure codes). These latent embeddings have been used with great success in the natural language processing domain and can be constructed in a preprocessing step. We show in our experiments, that a prediction model that exploits these latent embeddings can lead to improved readmission predictive models.
This is a preview of subscription content, access via your institution.
Buy single article
Instant access to the full article PDF.
Tax calculation will be finalised during checkout.
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
Tax calculation will be finalised during checkout.
Admission and discharge reason, therapy (also medication) and department codes.
Primary diagnosis, secondary diagnosis, LOINC Lab, therapies/medication, admission reason, discharge reason and department codes.
Bengio Y, Ducharme R, Vincent P, Janvin C (2003) A neural probabilistic language model. J Mach Learn Res 3:1137–1155
Billings J, Blunt I, Stevenson A, Georghiou T, Lewis G, Bardsley M (2012) Development of a predictive model to identify inpatients at risk of readmission within 30 days of discharge (parr-30). BMJ Open
Choudhry S, Li J, Davis D, Erdmann C, Sikka R, Sutariya B (2013) A public-private partnership develops and externally validates a 30-day hospital readmission risk prediction model. Online J Public Health Inform 5(2)
Collobert R, Weston J, Bottou L, Karlen M, Kavukcuoglu K, Kuksa P (2011) Natural language processing (almost) from scratch. J Mach Learn Res 12:2493–2537
Donzé J, Aujesky D, Williams D, Schnipper JL (2013) Potentially avoidable 30-day hospital readmissions in medical patients. JAMA 173:632–638
Dormann H, Neubert A, Criegee-Rieck M, Egger T, Radespiel-Troger M, Azaz-Livshits T, Levy M, Brune K, Hahn EG (2004) Readmissions and adverse drug reactions in internal medicine: the economic impact. J Int Med 255:653–663
Hasan O, Meltzer DO, Shaykevich SA, Bell CM et al (2009) Hospital readmission in general medicine patients: a prediction model. J Gen Intern Med 25:211–219
Hebert C, Shivade C, Foraker R, Wasserman J, et al (2014) Diagnosis-specific readmission risk prediction using electronic health data: A retrospective cohort study. BMC Med Inform Decis Making 14
Hendricks V, Schmidt S, Vogt A, Gysan D, Latz V, Schwang I, Griebenow R, Riedel R (2014) Case management program for patients with chronic heart failure. effectiveness in terms of mortality, hospital admissions and costs. Deutsches Aerzteblatt. International 111:264–270
Huang EH, Socher R, Manning CD, Ng AY (2012) Improving word representations via global context and multiple word prototypes. In: Annual Meeting of the Association for Computational Linguistics (ACL)
Jack BW, Chetty VK, Anthony D, Greenwald JL et al (1999) A reengineered hospital discharge program to decrease rehospitalization: a randomized trial. JAMA 281:613–620
Jencks SF, Williams MV, Coleman EA New England Journal of Medicine 14:1418–1428
Lebret R, Collobert R (2014) Word embeddings through hellinger pca. In: Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Association for Computational Linguistics. pp 482–490
Naylor MD, Brooten D, Campbell R, Jacobsen BS et al (1999) A comprehensive discharge planning and home follow-up of hospitalized elders: a randomized clinical trial. JAMA 281:613–620
OECD (2013) Health at a glance 2013: OECD indicators. http://dx.doi.org/10.1787/health_glance-2013-en
Department of Health (2013) Payment by results guidance for 2013–2014. Department of Health, London
Ohman E, Granger CB, Harrington RA, Lee KL (2000) Risk stratification and therapeutic decision making in acute coronary syndromes. JAMA 286(7):876–878
Robinson P Hospitals readmissions and the 30 day threshold. http://www.chks.co.uk/userfiles/files/CHKS%20Report%20Hospital%20readmissions.pdf
Rümenapf G, Geiger S, Schneider B, Amendt K, Wilhelm N, Morbach S, Nagel N (2013) Readmissions of patients with diabetes mellitus and foot ulcers after infra-popliteal bypass surgery: attacking the problem by an integrated case management model. Eur J Vasc Med 42:56–67
Smitht D, Giobbie-Hurder A, Weinberger M, Oddone EZ et al (2000) Predicting non-elective hospital readmissions: a multi site study. J Clin Epidemiol 53:1113–1118
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958
Turney PD, Pantel P (2010) From frequency to meaning: vector space models of semantics. pp 141–188
Yu S, Van Esbroeck A, Farooq F, Fung G, Anand V, Krishnapuram B (2013) Predicting readmission risk with institution specific prediction models. In: ICHI, pp 415–420
The project receives funding from the German Federal Ministry of Economics and Technology; Grant Number 01MT14001A.
About this article
Cite this article
Krompaß, D., Esteban, C., Tresp, V. et al. Exploiting Latent Embeddings of Nominal Clinical Data for Predicting Hospital Readmission. Künstl Intell 29, 153–159 (2015). https://doi.org/10.1007/s13218-014-0344-x
- Hospital readmission
- Latent embeddings
- Latent factors
- Logistic regression
- Neural network