Development and Validation of a Polypharmacy Knowledge Assessment Instrument

Abstract

Objective. To develop a brief instrument for academic pharmacists or physicians to use in assessing postgraduate residents' knowledge of polypharmacy. Methods. Five clinicians used a modified Delphi process to create a 26-item multiple-choice test to assess knowledge of polypharmacy in geriatric primary care. The test was distributed to 74 participants: 37 internal medicine (MD) residents, six nurse practitioner (NP) residents, nine primary care attendings, 12 pharmacists and pharmacy residents, and 10 geriatrics attendings and fellows. Construct validity was assessed using factor analysis and item response theory. Overall group differences were examined using a Kruskal-Wallis test, and between group differences were assessed using the Wilcoxon rank sum test. Results. The response rate for the survey was 89%. Factor analysis resulted in a one factor solution. Item response theory modeling yielded a 12-item and six-item test. For the 12-item test, the mean scores of geriatricians and pharmacists (88%) were higher than those of MD and NP residents (58%) and primary care attendings (61%). No differences were found between MD and NP residents and primary care attendings. Findings for the six-item test were similar. Conclusion. Both the 12-item and six-item versions of this polypharmacy test showed acceptable internal consistency and known groups validity and could be used in other academic settings. The similar scores between MD and NP residents and primary care attendings, which were significantly lower than scores for pharmacists and geriatricians, support the need for increased educational interventions.

Keywords: deprescribing; geriatrics; polypharmacy; primary care education, interprofessional education.

Figure 1.

Factor Analysis. The scree plot of test data (•) shows a distinct “elbow” after the first factor and indicates that a one factor solution is appropriate. This was confirmed using parallel analysis.

Figure 2.

Effect Sizes for Different Test Lengths. The 25 test items were ranked from highest to lowest quality using item information curves. The ability of each test version to distinguish between the four testing groups was assessed using a Kruskal-Wallis test (•). Additionally, items were ranked randomly (). A 6-item (dashed line) and 12-item (dotted line) test demonstrated similar ability to distinguish test-takers by profession and training level.

Figure 3.

Test Performance by Training Level. Panels A and B show the average test performance by profession [Mean (SD)] and training level for the 6- and 12-item tests. MD=Medical Doctorate, NP=Nurse Practitioner, PGY=post-graduate year after medical school.