Identification of patients with evolving coronary syndromes by using statistical models with data from the time of presentation

Objective: To derive statistical models for the diagnosis of acute coronary syndromes by using clinical and ECG information at presentation and to assess performance, portability, and calibration of these models, as well as how they may be used with cardiac marker proteins. Design and methods: Data from 3462 patients in four UK teaching hospitals were used. Inputs for 8, 14, 25, and 43 factor logistic regression models were selected by using log10 likelihood ratios (log10 LRs). Performance was analysed by receiver operating characteristic curves. Results: A 25 factor model derived from 1253 patients from one centre was selected for further study. On training data, 98.2% of ST elevation myocardial infarctions (STEMIs) and 96.2% of non-ST elevation myocardial infarctions (non-STEMIs) were correctly classified, whereas only 2.1% of non-cardiac cases were incorrectly classified. On data from three other centres, 97.3% of STEMIs and 91.9% of non-STEMIs were correctly classified. Differences in log10 LRs for individual inputs from different centres accounted for the decline in performance when models were applied to unseen data. Classification was improved when output was combined with either clinical opinion or marker proteins. Conclusions: Logistic regression models based on data available at presentation can classify patients with chest pain with a high degree of accuracy, particularly when combined with clinical opinion or marker proteins.

[1]  C. Heeschen,et al.  Elevated troponin T and C-reactive protein predict impaired outcome for 4 years in patients with refractory unstable angina, and troponin T predicts benefit of treatment with abciximab in combination with PTCA. , 2003, European heart journal.

[2]  S. Zarich,et al.  The Goldman algorithm revisited: prospective evaluation of a computer-derived algorithm versus unaided physician judgment in suspected acute myocardial infarction. , 1999, American heart journal.

[3]  L Goldman,et al.  A Critical Pathway for Management of Patients with Acute Chest Pain Who Are at Low Risk for Myocardial Ischemia: Recommendations and Potential Impact , 1997, Annals of Internal Medicine.

[4]  Richard J. Mammone,et al.  Artificial neural networks for speech and vision , 1994 .

[5]  E. Antman,et al.  A simple risk index for rapid initial triage of patients with ST-elevation myocardial infarction: an InTIME II substudy☆ , 2002 .

[6]  Hugo A. Katus,et al.  Myocardial infarction redefined--a consensus document of The Joint European Society of Cardiology/American College of Cardiology Committee for the redefinition of myocardial infarction. , 2000, European heart journal.

[7]  C. Heeschen,et al.  Predictive value of C-reactive protein and troponin T in patients with unstable angina: a comparative analysis. CAPTURE Investigators. Chimeric c7E3 AntiPlatelet Therapy in Unstable angina REfractory to standard treatment trial. , 2000, Journal of the American College of Cardiology.

[8]  Ook.,et al.  PREDICTION OF THE NEED FOR INTENSIVE CARE IN PATIENTS WHO COME TO EMERGENCY DEPARTMENTS WITH ACUTE CHEST PAIN , 2000 .

[9]  Robert Woolard,et al.  Missed Diagnoses of Acute Cardiac Ischemia in the Emergency Department , 2000 .

[10]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[11]  R B D'Agostino,et al.  A predictive instrument to improve coronary-care-unit admission practices in acute ischemic heart disease. A prospective multicenter clinical trial. , 1984, The New England journal of medicine.

[12]  R Ruthazer,et al.  Missed diagnoses of acute cardiac ischemia in the emergency department. , 2000, The New England journal of medicine.

[13]  R. Roberts,et al.  An evaluation of a chest pain diagnostic protocol to exclude acute cardiac ischemia in the emergency department. , 1997, Archives of internal medicine.

[14]  R. Califf,et al.  Troponin and C-reactive protein have different relations to subsequent mortality and myocardial infarction after acute coronary syndrome: a GUSTO-IV substudy. , 2003, Journal of the American College of Cardiology.

[15]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[16]  E. Antman,et al.  TIMI Risk Score for ST-Elevation Myocardial Infarction: A Convenient, Bedside, Clinical Score for Risk Assessment at Presentation: An Intravenous nPA for Treatment of Infarcting Myocardium Early II Trial Substudy , 2000, Circulation.

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

[18]  E. Fody,et al.  The Erlanger chest pain evaluation protocol: a one-year experience with serial 12-lead ECG monitoring, two-hour delta serum marker measurements, and selective nuclear stress testing to identify and exclude acute coronary syndromes. , 2002, Annals of emergency medicine.

[19]  P O Collinson,et al.  Multicentre evaluation of the diagnostic value of cardiac troponin T, CK-MB mass, and myoglobin for assessing patients with suspected acute coronary syndromes in routine clinical practice , 2003, Heart.

[20]  R D Sidman,et al.  Measurement of cardiac troponin T is an effective method for predicting complications among emergency department patients with chest pain. , 1998, Annals of emergency medicine.

[21]  Steve Goodacre,et al.  How useful are clinical features in the diagnosis of acute, undifferentiated chest pain? , 2002, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[22]  W. Baxt,et al.  A neural network aid for the early diagnosis of cardiac ischemia in patients presenting to the emergency department with chest pain. , 2002, Annals of emergency medicine.

[23]  L. Cooper,et al.  When Networks Disagree: Ensemble Methods for Hybrid Neural Networks , 1992 .

[24]  R. D'Agostino,et al.  A comparison of performance of mathematical predictive methods for medical diagnosis: identifying acute cardiac ischemia among emergency department patients. , 1995, Journal of investigative medicine : the official publication of the American Federation for Clinical Research.

[25]  G. Guyatt,et al.  The rational clinical examination. Is this patient having a myocardial infarction? , 1998, JAMA.

[26]  A R Zinsmeister,et al.  A clinical trial of a chest-pain observation unit for patients with unstable angina. Chest Pain Evaluation in the Emergency Room (CHEER) Investigators. , 1998, The New England journal of medicine.

[27]  W. Baxt,et al.  A neural computational aid to the diagnosis of acute myocardial infarction. , 2002, Annals of emergency medicine.

[28]  W. Gibler,et al.  Can electrocardiographic criteria predict adverse cardiac events and positive cardiac markers? , 2003, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[29]  E. Cook,et al.  Cost-effectiveness of a new short-stay unit to "rule out" acute myocardial infarction in low risk patients. , 1994, Journal of the American College of Cardiology.

[30]  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.

[31]  J P Ornato,et al.  Use of the Acute Cardiac Ischemia Time-Insensitive Predictive Instrument (ACI-TIPI) To Assist with Triage of Patients with Chest Pain or Other Symptoms Suggestive of Acute Cardiac Ischemia: A Multicenter, Controlled Clinical Trial , 1998, Annals of Internal Medicine.

[32]  H S Fraser,et al.  An artificial neural network system for diagnosis of acute myocardial infarction (AMI) in the accident and emergency department: evaluation and comparison with serum myoglobin measurements. , 1997, Computer methods and programs in biomedicine.

[33]  William J. Long,et al.  Using Classification Tree and Logistic Regression Methods to Diagnose Myocardial Infarction , 1998, MedInfo.

[34]  M. Sayre,et al.  A rapid diagnostic and treatment center for patients with chest pain in the emergency department. , 1995, Annals of emergency medicine.

[35]  W. Baxt,et al.  Prospective validation of artificial neural network trained to identify acute myocardial infarction , 1996, The Lancet.

[36]  R. Harrison,et al.  Early diagnosis of acute myocardial infarction using clinical and electrocardiographic data at presentation: derivation and evaluation of logistic regression models. , 1996, European heart journal.

[37]  S. Goodacre,et al.  Clinical predictors of acute coronary syndromes in patients with undifferentiated chest pain. , 2003, QJM : monthly journal of the Association of Physicians.

[38]  E F Cook,et al.  Ruling out acute myocardial infarction. A prospective multicenter validation of a 12-hour strategy for patients at low risk. , 1991, The New England journal of medicine.

[39]  Ian T. Nabney,et al.  Netlab: Algorithms for Pattern Recognition , 2002 .

[40]  W. Baxt.  Use of an artificial neural network for the diagnosis of myocardial infarction. , 1991, Annals of internal medicine.

[41]  Gordon H. Guyatt,et al.  Is This Patient Having a Myocardial Infarction , 1998 .