Research Paper: Automated Identification of a Physician's Primary Patients

OBJECTIVE To develop and validate an automated method for determining the set of patients for whom a given primary care physician holds overall clinical responsibility. DESIGN The study included all adult patients (16,185) seen at least once in an ambulatory setting during a three-year period by 18 primary care physicians in ten practices. The physicians indicated whether they considered themselves to be the physician primarily responsible for the overall clinical care of each visiting patient. Statistical models were constructed to predict the physicians' designations using predictor variables derived from electronically available appointment schedules and demographic information. MEASUREMENTS Predictive accuracy was assessed primarily using the area under the receiver-operating characteristic curve (AUC), and secondarily using positive predictive value (PPV) and sensitivity. RESULTS A minimal set of six variables was identified as predictive of the physicians' designations. The constructed model had a median AUC for individual physicians of 0.92 (interquartile interval: 0.90-0.96), a PPV of 0.94 (interquartile interval: 0.87-0.95), and a sensitivity of 0.95 (interquartile interval: 0.87-0.97). CONCLUSION A statistical model using a minimal set of commonly available electronic data can accurately predict the set of patients for whom a physician holds primary clinical responsibility. Further research examining the generalization of the model to other settings would be valuable.

[1]  J A Hanley,et al.  Sampling variability of nonparametric estimates of the areas under receiver operating characteristic curves: an update. , 1997, Academic radiology.

[2]  J E Anderson,et al.  Validation of the patient roster in a primary care practice. , 1985, Health services research.

[3]  J Hurley,et al.  Defining the practice population in fee-for-service practice. , 1997, Health services research.

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

[5]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[6]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[7]  David G. Stork,et al.  Pattern Classification , 1973 .

[8]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[9]  M. Bass,et al.  Approaches to the denominator problem in primary care research. , 1976, The Journal of family practice.

[10]  R C Fraser,et al.  The reliability and validity of the age-sex register as a population denominator in general practice. , 1978, The Journal of the Royal College of General Practitioners.

[11]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[12]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

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

[14]  Robert C. Holte,et al.  Very Simple Classification Rules Perform Well on Most Commonly Used Datasets , 1993, Machine Learning.

[15]  D C Morrell,et al.  Patterns of demand in general practice. , 1970, The Journal of the Royal College of General Practitioners.

[16]  J E Anderson.  Primary Care's Denominator Problem. , 1985, Canadian family physician Medecin de famille canadien.

[17]  Geoffrey I. Webb,et al.  Averaged One-Dependence Estimators: Preliminary Results , 2002, AusDM.

[18]  E. McGlynn,et al.  Health system reform and quality. , 1996, JAMA.

[19]  B W Smith,et al.  The Quadratic Odds Estimation (QOE) method for calculating practice denominators. , 1988, Medical care.

[20]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[21]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

[22]  W R Phillips,et al.  In search of a solution to the primary care denominator problem. , 1982, The Journal of family practice.

[23]  M. Brenner,et al.  Approaches to the denominator in practice-based epidemiology: a critical overview. , 1998, Journal of epidemiology and community health.

[24]  S. James Kilpatrick,et al.  Primary Care Research: Encounter Records and the Denominator Problem , 1984 .