Skip to main content

Advertisement

SpringerLink
Log in

Utilizing electronic health records to predict multi-type major adverse cardiovascular events after acute coronary syndrome

  • Regular Paper
  • Published:
Knowledge and Information Systems Aims and scope Submit manuscript

Abstract

Acute coronary syndrome (ACS), as a leading cause of death worldwide, is responsible for over 1.5 million hospital admissions in China each year. Major adverse cardiovascular event (MACE) after ACS often occurs suddenly resulting in high mortality and morbidity. Timely and accurate prediction of MACE after ACS could assist clinicians to pay more attention to high-risk patients and improve the quality and efficiency of care accordingly. Traditional prediction of MACE after ACS is based on aggressive medical therapy and guideline-driven treatment of a small set of coronary risk factors and is designed to predict one specific type of MACE. With the rapid development of electronic health records (EHR), more and more data-driven approaches have been proposed to explore the huge potentials of EHR data. However, existing data-driven approaches have typically been conducted by building one common predictive model and neglecting the relations among multi-type MACEs. In this paper, we propose a novel boosted regularized multi-label learning approach for multi-type MACE prediction. In detail, we formulate the prediction problem of multi-type MACE as a multi-label classification problem and incorporate the relational information among multi-type MACEs into modeling by using regularization terms to encode the corresponding relational information. In addition and to address the problem that some types of MACE are rarely occur, we utilize a boosting weighted sampling strategy to iteratively select a small subset of patient samples to train new multi-type MACE prediction models that can correct the previously wrongly predicted patient samples. A case study was conducted on a real ACS clinical dataset consisting of 2930 patient samples and collected from a Chinese hospital to validate the effectiveness of the proposed model. The performance of our best model remains robust and reaches 0.7 and 0.640 for both ischemic and hemorrhagic event prediction, respectively, in terms of AUC, and had over 2.7% and 23.1% performance gain in comparison with the state-of-the-art GRACE and CRUSADE model, respectively. The experimental results show the efficiency of our model in improving the performances on multi-type MACE prediction after ACS, by comparing with both traditional ACS risk stratification models which are widely adopted in the medical domain and state-of-the-art multi-label learning methods without efforts on incorporating the relational information of multi-type MACE into learning. In addition, we illustrate some interesting results pertaining to predictive risk factors to specific types of MACE, some of which are not only consistent with existing medical domain knowledge, but also contain suggestive hypotheses that could be validated by further investigations in the medical domain.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Notes

  1. In this study, matrices and vectors are denoted as boldface uppercase letters and boldface lowercase letters, respectively.

References

  1. Amsterdam EA, Wenger NK, Brindis RG, Casey DE, Ganiats TG, Holmes DR (2014) 2014 AHA/ACC guideline for the management of patients with Non-ST-elevation acute coronary syndromes: a report of the american college of cardiology/american heart association task force on practice guidelines. Circulation 130(25):e344–e426

    Google Scholar 

  2. Chen W, Gao R, Liu L, Zhu M, Wang W, Wang Y (2016) Report on cardiovascular disease in China 2015. Chin Circ J 6(31):521–528

    Google Scholar 

  3. Clark M (2015) Prediction of clinical risks by analysis of preclinical and clinical adverse events. J Biomed Inform 54:167–173

    Article  Google Scholar 

  4. Huang Z, Chan T-M, Dong W (2017) MACE prediction of acute coronary syndrome via boosted resampling classification using electronic medical records. J Biomed Inform 66:161–170

    Article  Google Scholar 

  5. Antman EM, Cohen M (2000) The TIMI risk score for unstable angina/non-ST elevation MI. J Am Med Assoc 284(7):835–842

    Article  Google Scholar 

  6. Granger CB, Goldberg RJ, Dabbous O, Pieper KS, Eagle K, Cannon CP (2003) Predictors of hospital mortality in the global registry of acute coronary events. JAMA Intern Med 163(19):2345–2353

    Article  Google Scholar 

  7. Chen AY, Subherwal S, Bach RG et al (2009) Baseline risk of major bleeding in non-ST-segment-elevation myocardial infarction: the CRUSADE (can rapid risk stratification of unstable angina patients suppress adverse outcomes with early implementation of the ACC/AHA guidelines) bleeding score. Circulation 119:1873–1882

    Article  Google Scholar 

  8. Anderson JL, Adams CD, Antman EM, Bridges CR, Califf RM, Casey DE et al (2011) ACCF/AHA focused update incorporated into the ACC/AHA 2007 guidelines for the management of patients with unstable angina/Non-ST-elevation myocardial infarction: A report of the american college of cardiology foundation/american heart association tas. Circulation 28:410–528

    Google Scholar 

  9. Qian B, Wang X, Cao N, Li H, Jiang Y-G (2015) A relative similarity based method for interactive patient risk prediction. Data Min Knowl Discov 29(4):1070–1093

    Article  MathSciNet  Google Scholar 

  10. Vanhouten JP, Starmer JM, Lorenzi NM, Maron DJ, Lasko TA (2014) Machine learning for risk prediction of acute coronary syndrome. In: AMIA Annu Symp Proc, pp. 1940–1949,

  11. Wang X, Wang F, Jianying H, Sorrentino R (2015) Towards actionable risk stratification: a bilinear approach. J Biomed Inform 53:147–155

    Article  Google Scholar 

  12. Moskovitch R, Shahar Y (2015) Classification-driven temporal discretization of multivariate time series. Data Min Knowl Discov 29(4):871–913

    Article  MathSciNet  Google Scholar 

  13. Rothman MJ, Tepas JJ III, Nowalk AJ, Levin JE, Rimar JM, Marchetti A, Hsiao AL (2017) Development and validation of a continuously age-adjusted measure of patient condition for hospitalized children using the electronic medical record. J Biomed Inform 66:180–193

    Article  Google Scholar 

  14. Kipnis P, Turk BJ, Wulf DA, LaGuardia JC, Liu V, Churpek MM, Romero-Brufau S, Escobar GJ (2016) Development and validation of an electronic medical record-based alert score for detection of inpatient deterioration outside the ICU. J Biomed Inform 64:10–19

    Article  Google Scholar 

  15. Taslimitehrani V, Dong G, Pereira NL, Panahiazar M, Pathak J (2016) Developing EHR-driven heart failure risk prediction models using CPXR(Log) with the probabilistic loss function. J Biomed Inform 60:260–269

    Article  Google Scholar 

  16. Belkin M, Niyogi P, Sindhwani V (2006) Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J Mach Learn Res 7:2399–2434

    MathSciNet  MATH  Google Scholar 

  17. Zhu X, Suk H-I, Wang L, Lee S-W, Shen D (2017) A novel relational regularization feature selection method for joint regression and classification in AD diagnosis. Med Image Anal 38:205–214

    Article  Google Scholar 

  18. Wang S, Chang X, Li X, Long G, Yao L, Sheng QZ (2016) Diagnosis code assignment using sparsity-based disease correlation embedding. IEEE Trans Knowl Data Eng 28(12):3191–3202

    Article  Google Scholar 

  19. Andrew YN (2004) Feature selection, L1 vs. L2 regularization, and rotational invariance. In: Proceedings of the Twenty-first International Conference on Machine Learning, ICML ’04, pp. 78–86, New York, NY, USA, ACM

  20. Read J, Pfahringer B, Holmes G, Frank E (2011) Classifier chains for multi-label classification. Mach Learn 85(3):333–359

    Article  MathSciNet  Google Scholar 

  21. Tsoumakas G, Katakis I (2007) Multi-label classification: an overview. Int J Data Warehous Min 1–13:2007

    Google Scholar 

  22. Tsoumakas G, Katakis I, Vlahavas I (2011) Random k-labelsets for multilabel classification. IEEE Trans Knowl Data Eng 23(7):1079–1089

    Article  Google Scholar 

  23. Zhang M-L, Zhou Z-H (2005) A k-nearest neighbor based algorithm for multi-label classification. In: 2005 IEEE International Conference on Granular Computing, vol 2, pp. 718–721

  24. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Int Res 16(1):321–357

    MATH  Google Scholar 

  25. The GRACE Investigators (2001) Rationale and design of the GRACE (Global Registry of Acute Coronary Events) Project: a multinational registry of patients hospitalized with acute coronary syndromes. Am Heart J 141(2):190–199

  26. Meadors GF, Dawber TR, Moore FE (1951) Epidemiological approaches to heart disease: the Framingham Study. Am J Public Health N Health 41(3):279–286

    Article  Google Scholar 

  27. The PURSUIT Trial Investigators (1998) Inhibition of platelet glycoprotein IIb/IIIa with eptifibatide in patients with acute coronary syndromes. N Engl J Med 339(7):436–443

  28. Antman EM, Cohen M, Bernink PM (2000) The TIMI risk score for unstable angina/NON-ST elevation MI: a method for prognostication and therapeutic decision making. JAMA 284(7):835–842

    Article  Google Scholar 

  29. Conroy RM, Pyörälä K, Fitzgerald AP, Sans S, Menotti A, De Backer G (2003) Estimation of ten-year risk of fatal cardiovascular disease in europe: the score project. Eur Heart J 24(11):987

    Article  Google Scholar 

  30. Yangfeng W, Liu X, Li X, Li Y, Zhao L, Chen Z, Li Y, Rao X, Zhou B, Detrano R, Liu K (2006) Estimation of 10-year risk of fatal and nonfatal ischemic cardiovascular diseases in Chinese adults. Circulation 114(21):2217–2225

    Article  Google Scholar 

  31. Zhe Zheng L, Zhang SH, Li X, Yuan X, Gao H (2012) Risk factors and in-hospital mortality in chinese patients undergoing coronary artery bypass grafting: analysis of a large multi-institutional chinese database. J Thoracic Cardiovascular Surg 144(2):355–359.e1

    Article  Google Scholar 

  32. Jionglin W, Roy J, Stewart WF (2010) Prediction modeling using EHR data: challenges, strategies, and a comparison of machine learning approaches. Medical Care 48(6):S106–S113

    Google Scholar 

  33. Dong W, Huang Z, Ji L, Duan H (2014) A genetic fuzzy system for unstable angina risk assessment. BMC Med Inform Decis Mak 14(1):12

    Article  Google Scholar 

  34. Syprgmm C, Yuen TC, Edelson DP (2014) Using electronic health record data to develop and validate a prediction model for adverse outcomes in the wards. Crit Care Med 42(4):841–848

    Article  Google Scholar 

  35. Bandyopadhyay S, Wolfson J, Vock DM, Vazquez-Benitez G, Adomavicius G, Elidrisi M, Johnson PE, O’Connor PJ (2015) Data mining for censored time-to-event data: a bayesian network model for predicting cardiovascular risk from electronic health record data. Data Min Knowl Discov 29(4):1033–1069

    Article  MathSciNet  Google Scholar 

  36. Huang Z, Dong W, Duan H (2015) A probabilistic topic model for clinical risk stratification from electronic health records. J Biomed Inform 58:28–36

    Article  Google Scholar 

  37. Karaolis MA, Moutiris JA, Hadjipanayi D, Pattichis CS (2010) Assessment of the risk factors of coronary heart events based on data mining with decision trees. IEEE Trans Inform Technol Biomed 14(3):559–566

    Article  Google Scholar 

  38. Solomon JW, Nielsen RD (2015) Predicting changes in systolic blood pressure using longitudinal patient records. J Biomed Inform 58(Supplement):S197–S202

    Article  Google Scholar 

  39. Jonnagaddala J, Liaw S-T, Ray P, Kumar M, Chang N-W, Dai H-J (2015) Coronary artery disease risk assessment from unstructured electronic health records using text mining. J Biomed Inform 58(Supplement):S203–S210

    Article  Google Scholar 

  40. Dabbous O, Granger CB, Goldberg RJ (2003) Predictors of hospital mortality in the global registry of acute coronary events. Arch Intern Med 163(19):2345–2353

    Article  Google Scholar 

  41. Antman EM, McCabe CH, Gurfinkel EP, Turpie AGG, Bernink PJLM, Salein D, de Luna AB, Fox K, Lablanche J-M, Radley D, Premmereur J, Braunwald E (1999) Enoxaparin prevents death and cardiac ischemic events in unstable angina/non–q-wave myocardial infarction. Circulation 100(15):1593–1601

    Article  Google Scholar 

  42. Boersma E, Pieper KS, Steyerberg EW, Wilcox RG, Chang W-C, Lee KL, Akkerhuis KM, Harrington RA, Deckers JW, Armstrong PW, Lincoff AM, Califf RM, Topol EJ, Simoons ML (2000) Predictors of outcome in patients with acute coronary syndromes without persistent st-segment elevation. Circulation 101(22):2557–2567

    Article  Google Scholar 

  43. Pencina MJ, Agostino RBD, Vasan RS et al (2008) General cardiovascular risk profile for use in primary care. Circulation 117(6):743

    Article  Google Scholar 

  44. Giugliano RP, Braunwald E (2014) The year in acute coronary syndrome. J Am Coll Cardiol 63(3):201–214

    Article  Google Scholar 

  45. Singh A, Nadkarni G, Gottesman O, Ellis SB, Bottinger EP, Guttag JV (2015) Incorporating temporal EHR data in predictive models for risk stratification of renal function deterioration. J Biomed Inform 53:220–228

    Article  Google Scholar 

  46. Jung K, Shah NH (2015) Implications of non-stationarity on predictive modeling using EHRs. J Biomed Inform 58:168–174

    Article  Google Scholar 

  47. Huang Z, Dong W, Duan H, Liu J (2018) A regularized deep learning approach for clinical risk prediction of acute coronary syndrome using electronic health records. IEEE Trans Biomed Eng 65(5):956–968

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the National Nature Science Foundation of China under Grant No 61672450. The author would like to give special thanks to all experts who cooperated in the evaluation of the proposed method. In addition, the authors would like to thank the editor and the anonymous reviewers for their constructive comments on an earlier draft of this paper.

Author information

Authors and Affiliations

  1. College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China

    Zhengxing Huang & Yi Lu

  2. Department of Cardiology, Chinese PLA General Hospital, Beijing, China

    Wei Dong

Authors
  1. Zhengxing Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yi Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wei Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhengxing Huang.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Huang, Z., Lu, Y. & Dong, W. Utilizing electronic health records to predict multi-type major adverse cardiovascular events after acute coronary syndrome. Knowl Inf Syst 60, 1725–1752 (2019). https://doi.org/10.1007/s10115-018-1270-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10115-018-1270-2

Keywords

Search

Navigation