Predictive modeling of hospital readmission rates using electronic medical record-wide machine learning: A case-study using mount sinai heart failure cohort

Pacific Symposium on Biocomputing

Volumn 0, Issue 212679, 2017, Pages 276-287

  Shameer, Khader ^a,b   Johnson, Kipp W ^a,b   Yahi, Alexandre ^c   Miotto, Riccardo ^a,b   Li, L I ^a,b   Ricks, Doran ^b   Jebakaran, Jebakumar ^a   Kovatch, Patricia ^a   Sengupta, Partho P ^a   Gelijns, Annetine ^b   Moskovitz, Alan ^b   Darrow, Bruce ^a   Reich, David L ^a   Kasarskis, Andrew ^a   Tatonetti, Nicholas P ^c   Pinney, Sean ^a   Dudley, Joel T ^a,b  

^a MOUNT SINAI SCHOOL OF MEDICINE   (United States)

^b MOUNT SINAI HEALTH SYSTEM   (United States)

^c NewYork Presbyterian Hospital   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; CARDIOLOGY; E-LEARNING; FACSIMILE; FEATURE EXTRACTION; HEALTH CARE; HEART; HOSPITALS; LEARNING SYSTEMS; MEDICAL COMPUTING; TELEMEDICINE;

5-FOLD CROSS VALIDATION METHOD; CLINICAL DECISION SYSTEM; CORRELATION BASED FEATURE SELECTIONS (CFS); ELECTRONIC MEDICAL RECORD; LABORATORY MEASUREMENTS; MYOCARDIAL INFARCTION; OPERATION GUIDELINES; REGULATORY AUTHORITIES;

DIAGNOSIS;

ALGORITHM; BAYES THEOREM; BIOLOGY; COHORT ANALYSIS; ELECTRONIC HEALTH RECORD; HEART FAILURE; HOSPITAL READMISSION; HUMAN; MACHINE LEARNING; NEW YORK; STATISTICAL MODEL; STATISTICS AND NUMERICAL DATA;

ALGORITHMS; BAYES THEOREM; COHORT STUDIES; COMPUTATIONAL BIOLOGY; ELECTRONIC HEALTH RECORDS; HEART FAILURE; HUMANS; MACHINE LEARNING; MODELS, STATISTICAL; NEW YORK CITY; PATIENT READMISSION;

EID: 85018435860     PISSN: 23356928     EISSN: 23356936     Source Type: Journal    
DOI: 10.1142/9789813207813_0027     Document Type: Conference Paper

References (36)

1. Shameer, K. et al. A genome-and phenome-wide association study to identify genetic variants influencing platelet count and volume and their pleiotropic effects. Hum Genet 133, 95-109, doi:10.1007/s00439-013-1355-7 (2014).
2. Glicksberg, B. S. et al. An integrative pipeline for multi-modal discovery of disease relationships. Pac Symp Biocomput, 407-418 (2015).
3. Badgeley, M. A. et al. EHDViz: clinical dashboard development using open-source technologies. BMJ Open 6, e010579, doi:10.1136/bmjopen-2015-010579 (2016).
4. Shameer, K. et al. Translational bioinformatics in the era of real-time biomedical, health care and wellness data streams. Brief Bioinform, doi:10.1093/bib/bbv118 (2016).
5. Hamad, R., Modrek, S., Kubo, J., Goldstein, B. A. & Cullen, M. R. Using "big data" to capture overall health status: properties and predictive value of a claims-based health risk score. PloS one 10, e0126054, doi:10.1371/journal.pone.0126054 (2015).
6. Roski, J., Bo-Linn, G. W. & Andrews, T. A. Creating value in health care through big data: opportunities and policy implications. Health affairs 33, 1115-1122, doi:10.1377/hlthaff.2014.0147 (2014).
7. Houle, D., Govindaraju, D. R. & Omholt, S. Phenomics: the next challenge. Nat Rev Genet 11, 855-866, doi:10.1038/nrg2897 (2010).
8. Karasik, D. How pleiotropic genetics of the musculoskeletal system can inform genomics and phenomics of aging. Age (Dordr) 33, 49-62, doi:10.1007/s11357-010-9159-3 (2011).
9. Thavendiranathan, P. et al. Prediction of 30-day heart failure-specific readmission risk by echocardiographic parameters. Am J Cardiol 113, 335-341, doi:10.1016/j.amjcard.2013.09.025 (2014).
10. Padhukasahasram, B., Reddy, C. K., Li, Y. & Lanfear, D. E. Joint impact of clinical and behavioral variables on the risk of unplanned readmission and death after a heart failure hospitalization. PloS one 10, e0129553, doi:10.1371/journal.pone.0129553 (2015).
11. Kansagara, D. et al. Risk prediction models for hospital readmission: a systematic review. JAMA: the journal of the American Medical Association 306, 1688-1698, doi:10.1001/jama.2011.1515 (2011).
12. Inouye, S. et al. Predicting readmission of heart failure patients using automated follow-up calls. BMC medical informatics and decision making 15, 22, doi:10.1186/s12911-015-0144-8 (2015).
13. Adib-Hajbaghery, M., Maghaminejad, F. & Abbasi, A. The role of continuous care in reducing readmission for patients with heart failure. J Caring Sci 2, 255-267, doi:10.5681/jcs.2013.031 (2013).
14. Bourge, R. C. et al. Randomized controlled trial of an implantable continuous hemodynamic monitor in patients with advanced heart failure: the COMPASS-HF study. J Am Coll Cardiol 51, 1073-1079, doi:10.1016/j.jacc.2007.10.061 (2008).
15. Whellan, D. J. et al. Development of a method to risk stratify patients with heart failure for 30-day readmission using implantable device diagnostics. Am J Cardiol 111, 79-84, doi:10.1016/j.amjcard.2012.08.050 (2013).
16. Hosseinzadeh, A., Izadi, M., Verma, A., Precup, D. & Buckeridge, D. in Proceedings of the Twenty-Seventh AAAI Conference on Artificial Intelligence 1532-1538 (AAAI Press, Bellevue, Washington, 2013).
17. Duggal, R., Shukla, S., Chandra, S., Shukla, B. & Khatri, S. K. Predictive risk modelling for early hospital readmission of patients with diabetes in India. International Journal of Diabetes in Developing Countries, 1-10, doi:10.1007/s13410-016-0511-8 (2016).
18. Gewehr, J. E., Szugat, M. & Zimmer, R. BioWeka--extending the Weka framework for bioinformatics. Bioinformatics 23, 651-653, doi:10.1093/bioinformatics/btl671 (2007).
19. Hall, M. et al. The WEKA Data Mining Software: An Update. SIGKDD Explor Newsl 11, 10-18 (2009).
20. Pyka, M., Balz, A., Jansen, A., Krug, A. & Hullermeier, E. A WEKA interface for fMRI data. Neuroinformatics 10, 409-413, doi:10.1007/s12021-012-9144-3 (2012).
21. Smith, T. C. & Frank, E. Introducing Machine Learning Concepts with WEKA. Methods Mol Biol 1418, 353-378, doi:10.1007/978-1-4939-3578-9_17 (2016).
22. Guyon, I., Andr, #233 & Elisseeff. An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157-1182 (2003).
23. Hastie, T., Tibshirani, R. & Friedman, J. The Elements of Statistical Learning. (Springer New York Inc., 2001).
24. Doughty, R. N. & White, H. D. Carvedilol: use in chronic heart failure. Expert Rev Cardiovasc Ther 5, 21-31, doi:10.1586/14779072.5.1.21 (2007).
25. Richardson, L. G. Psychosocial issues in patients with congestive heart failure. Prog Cardiovasc Nurs 18, 19-27 (2003).
26. MacMahon, K. M. & Lip, G. Y. Psychological factors in heart failure: a review of the literature. Arch Intern Med 162, 509-516 (2002).
27. Schweitzer, R. D., Head, K. & Dwyer, J. W. Psychological factors and treatment adherence behavior in patients with chronic heart failure. J Cardiovasc Nurs 22, 76-83 (2007).
28. Ramasamy, R. et al. Psychological and social factors that correlate with dyspnea in heart failure. Psychosomatics 47, 430-434, doi:10.1176/appi.psy.47.5.430 (2006).
29. Iribarren, C. et al. Glycemic control and heart failure among adult patients with diabetes. Circulation 103, 2668-2673 (2001).
30. Futoma, J., Morris, J. & Lucas, J. A comparison of models for predicting early hospital readmissions. J Biomed Inform 56, 229-238, doi:10.1016/j.jbi.2015.05.016 (2015).
31. LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436-444, doi:10.1038/nature14539 (2015).
32. Schmidhuber, J. Deep learning in neural networks: an overview. Neural Netw 61, 85-117, doi:10.1016/j.neunet.2014.09.003 (2015).
33. Miotto, R., Li, L., Kidd, B. A. & Dudley, J. T. Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records. Sci Rep 6, 26094, doi:10.1038/srep26094 (2016).
34. Benjamin S. Glicksberg, Marcus A. Badgeley, Khader Shameer, Roman Kosoy, Noam D. Beckmann, Nam Pho, Jörg Hakenberg, Meng Ma, Kristin L. Ayers, Gabriel E. Hoffman, Shuyu Dan Li, Eric E. Schadt, Chirag J. Patel, Rong Chen, and Joel T. Dudley. Comparative Analyses of Population-scale Phenomic Data in Electronic Medical Records Reveal Race-specific Disease Networks. Bioinformatics ISCB Special Issue, doi:10.1093/bioinformatics/btw282 (2016).
35. Sengupta, P. P. et al. Cognitive Machine Learning Algorithm for Cardiac Imaging: A Pilot Study for Differentiating Constrictive Pericarditis From Restrictive Cardiomyopathy. Circ Cardiovasc Imaging 9, doi:10.1161/CIRCIMAGING.115.004330 (2016).
36. Li, L., Lee, N. J., Glicksberg, B. S., Radbill, B. D. & Dudley, J. T. Data-Driven Identification of Risk Factors of Patient Satisfaction at a Large Urban Academic Medical Center. PLoS One 11, e0156076, doi:10.1371/journal.pone.0156076 (2016).