Clinical practice guidelines are an essential tool for translating research findings into practice. Ideally, adherence to evidence-based guidelines should reduce unnecessary variation in the utilization of health care resources, contain costs and improve clinical outcomes. However, successful implementation of guidelines at the local level requires overcoming multiple barriers. One such barrier is a perception that the general recommendations found in guidelines do not apply to specific patients or practice settings. To address this and other known barriers to implementation, we propose to extend previous work in which we developed and tested a computer-based decision support system that generates evidence-based, patient-specific recommendations for the prevention of sudden cardiac death in at-risk populations. In the proposed research, we adapt our system and evaluate its impact on the management of patients with solitary pulmonary nodules. Management of lung nodules is a very attractive target for computer-based decision support. It is a common problem in both primary care and specialty settings, multiple possible management strategies exist, and the optimal management approach depends on pre-test probability, the risk of surgical complications, and several other factors.
We aim to demonstrate that decision support can improve diagnosis and management in patients with solitary pulmonary nodules. To achieve this overall goal, we have three specific aims: (1) to develop ALCHEMIST-SPN, an interactive decision support system for management of patients with solitary pulmonary nodules, by linking a published decision analysis model and an existing architecture for computer-based decision support; (2) to validate the predictions generated by the ALCHEMIST-SPN decision support system; and (3) to conduct a controlled, cross-over trial of computer-based decision support for pulmonary nodule management by asking physician participants to manage a series of clinical vignettes that are based on actual patients with pulmonary nodules of known cause. By completing these aims, we will: (1) demonstrate the usefulness of an innovative strategy for creating and implementing evidence-based practice recommendations; (2) confirm that our system for decision support can be generalized to a management problem that is considerably more complicated than the one evaluated in our previous work; and (3) set the stage for a randomized trial of computer-based decision support with ALCHEMIST-SPN in real world clinical settings.
| Balekian, Alex A; Silvestri, Gerard A; Simkovich, Suzanne M et al. (2013) Accuracy of clinicians and models for estimating the probability that a pulmonary nodule is malignant. Ann Am Thorac Soc 10:629-35 |
| Schultz, E M; Sanders, G D; Trotter, P R et al. (2008) Validation of two models to estimate the probability of malignancy in patients with solitary pulmonary nodules. Thorax 63:335-41 |
| Schultz, Ellen M; Silvestri, Gerard A; Gould, Michael K (2008) Variation in experts'beliefs about lung cancer growth, progression, and prognosis. J Thorac Oncol 3:422-6 |
| Gould, Michael K; Ananth, Lakshmi; Barnett, Paul G et al. (2007) A clinical model to estimate the pretest probability of lung cancer in patients with solitary pulmonary nodules. Chest 131:383-8 |
