Hp. Selker et al., PATIENT-SPECIFIC PREDICTIONS OF OUTCOMES IN MYOCARDIAL-INFARCTION FORREAL-TIME EMERGENCY USE - A THROMBOLYTIC PREDICTIVE INSTRUMENT, Annals of internal medicine, 127(7), 1997, pp. 538-556
Background: Thrombolytic therapy can be life-saving in patients with a
cute myocardial infarction. However, if given too late or insufficient
ly selectively, it may provide little benefit but still cause serious
complications and incur substantial costs. Objective: To develop a thr
ombolytic predictive instrument for real-time use in emergency medical
service settings that could 1) identify patients likely to benefit fr
om thrombolysis and 2) facilitate the earliest possible use of this th
erapy. Design: Creation and validation of logistic regression-based pr
edictive instruments based on secondary analysis of clinical data. Pat
ients: 4911 patients who had acute myocardial infarction and ST-segmen
t elevation on electrocardiogram; 3483 received thrombolytic therapy.
Measurements: Data were obtained from 13 major clinical trials and reg
istries and directly from medical records, including electrocardiogram
s obtained at presentation. Input variables include presenting clinica
l and electrocardiographic features; predictive models generate probab
ilities for acute (30-day) mortality if and if not treated with thromb
olysis, 1-year mortality rates if and if not treated with thrombolysis
, cardiac arrest if and if not treated with thrombolysis, thrombolysis
-related intracranial hemorrhage, and thrombolysis-related major bleed
ing episode requiring transfusion. Together, these models constitute t
he thrombolytic predictive instrument. Results: The predictive models
generated the following mean predictions for patients in the Thromboly
tic Predictive Instrument Database: 30-day mortality rate, 7.1%; 1-yea
r mortality rate, 10.9%; rate of cardiac arrest, 3.7%; rate of thrombo
lysis-related intracranial hemorrhage, 0.6%; and rate of other thrombo
lysis-related major bleeding episodes, 5.0%. They discriminated well b
etween persons having and those not having the predicted outcome; area
s under the receiver-operating characteristic (ROC) curve were between
0.77 and 0.84 for the five outcomes. Calibration between each instrum
ent's predicted and observed rates was excellent. Validation of the pr
edictive instruments for 30-day and 1-year mortality, done on a separa
te test dataset, yielded areas under the ROC curve of 0.76 for each. C
onclusions: After the basic features of a clinical presentation are en
tered into a computerized electrocardiograph, the predictions of the t
hrombolytic predictive instrument can be printed on the electrocardiog
ram report. This decision aid may facilitate earlier and more appropri
ate use of thrombolytic therapy in patients with acute myocardial infa
rction.