Computer-based models to identify high-risk adults with asthma: is the glass half empty of half full?

This study developed and evaluated the performance of prediction models for asthma-related adverse outcomes based on the computerized hospital, clinic, and pharmacy utilization databases of a large health maintenance organization. Prediction models identified patients at three- to four-fold increased risk of hospitalization and emergency department visits, and were valid for test samples from the same population. A model that identified 19% of patients as high risk had a sensitivity of 49%, a specificity of 84%, and a positive predictive value of 19%. We conclude that prediction models that are based on computerized utilization data can identify adults with asthma at elevated risk, but may have limited sensitivity and specificity in actual populations.

[1]  M A Fischl,et al.  An index predicting relapse and need for hospitalization in patients with acute bronchial asthma. , 1981, The New England journal of medicine.

[2]  E F Cook,et al.  Empiric comparison of multivariate analytic techniques: advantages and disadvantages of recursive partitioning analysis. , 1984, Journal of chronic diseases.

[3]  B. Brenner.  The acute asthmatic in the emergency department: the decision to admit or discharge. , 1985, The American journal of emergency medicine.

[4]  L. Moses,et al.  Statistical approaches to classification. Methods for developing classification and other criteria rules. , 2010, Arthritis and rheumatism.

[5]  P. Gergen,et al.  An economic evaluation of asthma in the United States. , 1992, The New England journal of medicine.

[6]  D G Altman,et al.  Transfer of technology from statistical journals to the biomedical literature. Past trends and future predictions. , 1994, JAMA.

[7]  A. Buist,et al.  Uses and limitations of mortality and health care utilization statistics in asthma research. , 1994, American journal of respiratory and critical care medicine.

[8]  S. R. Wilson,et al.  Prospective study of hospitalization for asthma. A preliminary risk factor model. , 1995, American journal of respiratory and critical care medicine.

[9]  Miriam Komaromy,et al.  Preventable hospitalizations and access to health care , 1995 .

[10]  A. Buist,et al.  Use of an automated prescription database to identify individuals with asthma. , 1995, Journal of clinical epidemiology.

[11]  David P Miller,et al.  Determinants of the use of coronary angiography and revascularization after thrombolysis for acute myocardial infarction. , 1996, The New England journal of medicine.

[12]  Louis Sherwood,et al.  From Outcomes Research to Disease Management: A Guide for the Perplexed , 1996, Annals of Internal Medicine.

[13]  S. Weiss,et al.  Inhaled steroids and the risk of hospitalization for asthma. , 1997, JAMA.

[14]  D. Malone,et al.  A national estimate of the economic costs of asthma. , 1997, American journal of respiratory and critical care medicine.

[15]  M. Blaiss,et al.  Outcomes analysis in asthma. , 1997, JAMA.

[16]  T. Lieu,et al.  Computer-based models to identify high-risk children with asthma. , 1998, American journal of respiratory and critical care medicine.