Lack of concordance between physician and patient: reports on end-of-life care discussions

Abstract

Objective: To study the effectiveness of patient physician communications regarding health care choices at the end of life. We studied communications occurring between physicians and their patients who had either terminal cancer or congestive heart failure, with less than 6 months to live.

Methods: This pilot study used in-person interviews with 22 physicians and 71 of their (matched) patients. Subjects provided paired responses to questions regarding their conversations related to end-of-life care, including resources, attitudes, and preferences. We calculated the concordance of patient and physician reports about these discussions. We examined the physicians' and the patients' agreement on the patient's diagnosis, and on whether a variety of care options were discussed. We then measured whether physicians' were aware of their patients' preferences for pain management and for place of death. Finally, we measured physicians' knowledge of whether religious/spiritual concerns or financial concerns had affected their patients' decisions regarding end-of-life care. Both bivariate and multivariate models were used.

Results: As a whole, the concordance scores were poor; however, concordance varied across domains of issues discussed. Patients with less education had significantly lower concordance scores.

Discussion: We have identified domains in which the physicians and patients may be least effective in discussing end-of-life care options. Findings may help in designing interventions to improve communication, especially for patients with less education.