Utilizing Chinese Admission Records for MACE Prediction of Acute Coronary Syndrome

Background: Clinical major adverse cardiovascular event (MACE) prediction of acute coronary syndrome (ACS) is important for a number of applications including physician decision support, quality of care assessment, and efficient healthcare service delivery on ACS patients. Admission records, as typical media to contain clinical information of patients at the early stage of their hospitalizations, provide significant potential to be explored for MACE prediction in a proactive manner. Methods: We propose a hybrid approach for MACE prediction by utilizing a large volume of admission records. Firstly, both a rule-based medical language processing method and a machine learning method (i.e., Conditional Random Fields (CRFs)) are developed to extract essential patient features from unstructured admission records. After that, state-of-the-art supervised machine learning algorithms are applied to construct MACE prediction models from data. Results: We comparatively evaluate the performance of the proposed approach on a real clinical dataset consisting of 2930 ACS patient samples collected from a Chinese hospital. Our best model achieved 72% AUC in MACE prediction. In comparison of the performance between our models and two well-known ACS risk score tools, i.e., GRACE and TIMI, our learned models obtain better performances with a significant margin. Conclusions: Experimental results reveal that our approach can obtain competitive performance in MACE prediction. The comparison of classifiers indicates the proposed approach has a competitive generality with datasets extracted by different feature extraction methods. Furthermore, our MACE prediction model obtained a significant improvement by comparison with both GRACE and TIMI. It indicates that using admission records can effectively provide MACE prediction service for ACS patients at the early stage of their hospitalizations.

[1]  Girish N. Nadkarni,et al.  Incorporating temporal EHR data in predictive models for risk stratification of renal function deterioration , 2014, J. Biomed. Informatics.

[2]  S. Girotra,et al.  Acute Coronary Syndrome , 2015, Journal of intensive care medicine.

[3]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[4]  E W Steyerberg,et al.  Predictors of outcome in patients with acute coronary syndromes without persistent ST-segment elevation. Results from an international trial of 9461 patients. The PURSUIT Investigators. , 2000, Circulation.

[5]  Gediminas Adomavicius,et al.  Data mining for censored time-to-event data: a Bayesian network model for predicting cardiovascular risk from electronic health record data , 2014, Data Mining and Knowledge Discovery.

[6]  Fei Wang,et al.  Towards actionable risk stratification: A bilinear approach , 2015, J. Biomed. Informatics.

[7]  Silvana Quaglini,et al.  Cardiovascular Risk Calculators: Understanding Differences and Realising Economic Implications , 2003, MIE.

[8]  Huilong Duan,et al.  A genetic fuzzy system for unstable angina risk assessment , 2014, BMC Medical Informatics and Decision Making.

[9]  Kenji Inoue,et al.  Reevaluation of cardiac risk scores and multiple biomarkers for the prediction of first major cardiovascular events and death in the drug-eluting stent era. , 2016, International journal of cardiology.

[10]  Paulo Carvalho,et al.  Long term cardiovascular risk models' combination , 2011, Comput. Methods Programs Biomed..

[11]  W. Rutishauser,et al.  C-reactive protein as a marker for acute coronary syndromes. , 1997, European heart journal.

[12]  Ye Ye,et al.  Comparison of machine learning classifiers for influenza detection from emergency department free-text reports , 2015, J. Biomed. Informatics.

[13]  Pradeep Kumar Ray,et al.  Coronary artery disease risk assessment from unstructured electronic health records using text mining , 2015, J. Biomed. Informatics.

[14]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[15]  Constantinos S. Pattichis,et al.  Assessment of the Risk Factors of Coronary Heart Events Based on Data Mining With Decision Trees , 2010, IEEE Transactions on Information Technology in Biomedicine.

[16]  Wei Luo,et al.  Stabilized sparse ordinal regression for medical risk stratification , 2014, Knowledge and Information Systems.

[17]  Dong-Ling Xu,et al.  A belief rule-based decision support system for clinical risk assessment of cardiac chest pain , 2012, Eur. J. Oper. Res..

[18]  Lei Liu,et al.  Extracting important information from Chinese Operation Notes with natural language processing methods , 2014, J. Biomed. Informatics.

[19]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[20]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[21]  Carlos Aguiar,et al.  TIMI, PURSUIT, and GRACE risk scores: sustained prognostic value and interaction with revascularization in NSTE-ACS. , 2005, European heart journal.

[22]  B. Gersh,et al.  The Problem With Composite End Points in Cardiovascular Studies: The Story of Major Adverse Cardiac Events and Percutaneous Coronary Intervention , 2009 .

[23]  Robert Gibbons,et al.  Using Electronic Health Record Data to Develop and Validate a Prediction Model for Adverse Outcomes in the Wards* , 2012, Critical care medicine.

[24]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[25]  John F. Hurdle,et al.  Extracting Information from Textual Documents in the Electronic Health Record: A Review of Recent Research , 2008, Yearbook of Medical Informatics.

[26]  Huilong Duan,et al.  Lexical Characteristics Analysis of Chinese Clinical Documents , 2015, 2015 7th International Conference on Information Technology in Medicine and Education (ITME).

[27]  W John Boscardin,et al.  Risk stratification for in-hospital mortality in acutely decompensated heart failure: classification and regression tree analysis. , 2005, JAMA.

[28]  Ben J. Marafino,et al.  Efficient and sparse feature selection for biomedical text classification via the elastic net: Application to ICU risk stratification from nursing notes , 2015, J. Biomed. Informatics.

[29]  Jason Roy,et al.  Prediction Modeling Using EHR Data: Challenges, Strategies, and a Comparison of Machine Learning Approaches , 2010, Medical care.

[30]  Honglak Lee,et al.  Efficient L1 Regularized Logistic Regression , 2006, AAAI.

[31]  A. Bayés‐Genís,et al.  D-Dimer is an early diagnostic marker of coronary ischemia in patients with chest pain. , 2000, American heart journal.

[32]  Andreas Christmann,et al.  Support vector machines , 2008, Data Mining and Knowledge Discovery Handbook.

[33]  Á. Avezum,et al.  Predictors of hospital mortality in the global registry of acute coronary events. , 2003, Archives of internal medicine.

[34]  Nan Liu,et al.  Risk Scoring for Prediction of Acute Cardiac Complications from Imbalanced Clinical Data , 2014, IEEE Journal of Biomedical and Health Informatics.

[35]  E. Antman,et al.  The TIMI risk score for unstable angina/non-ST elevation MI: A method for prognostication and therapeutic decision making. , 2000, JAMA.

[36]  Huilong Duan,et al.  A probabilistic topic model for clinical risk stratification from electronic health records , 2015, J. Biomed. Informatics.

[37]  Huilong Duan,et al.  On mining latent treatment patterns from electronic medical records , 2015, Data Mining and Knowledge Discovery.

[38]  I. Graham,et al.  Value and limitations of existing scores for the assessment of cardiovascular risk: a review for clinicians. , 2009, Journal of the American College of Cardiology.

[39]  M. Pencina,et al.  General Cardiovascular Risk Profile for Use in Primary Care: The Framingham Heart Study , 2008, Circulation.

[40]  Xiaojin Zhu,et al.  Introduction to Semi-Supervised Learning , 2009, Synthesis Lectures on Artificial Intelligence and Machine Learning.

[41]  Jonathan M. Garibaldi,et al.  A hybrid model for automatic identification of risk factors for heart disease , 2015, J. Biomed. Informatics.