Clinician Perceptions on Using Decision Tools to Support Prediction-Based Shared Decision Making for Lung Cancer...

Area of Science:

• Health Services Research
• Clinical Decision Making
• Medical Informatics

Background:

• Personalized shared decision making (SDM) can be enhanced by incorporating a patient's full risk factor profile.
• Encounter tools with prediction models offer a pathway to personalized SDM, yet clinician feasibility perceptions are underexplored.

Purpose of the Study:

• To examine primary care clinicians' reactions to using an encounter tool for personalized SDM regarding lung cancer screening (LCS).
• To identify clinician perceptions of the feasibility and challenges of integrating prediction-based SDM tools into routine practice.

Main Methods:

• A qualitative study involving field notes from academic detailing visits with 96 primary care clinicians across multiple Veterans Affairs sites.
• Thematic content analysis was used to categorize clinician feedback on the rationale and use of the DecisionPrecision (DP) encounter tool for LCS discussions.

Main Results:

• Six categories of clinician willingness to use the DP tool were identified, ranging from "Enthusiastic Potential Adopter" to "Definite Non-Adopter."
• While 52 clinicians found prediction-based SDM appealing, nearly all identified practical challenges to implementation.

Conclusions:

• Many clinicians recognize the value of prediction for personalizing LCS decisions.
• Further support and strategies are needed to overcome barriers and facilitate the adoption of prediction-based SDM encounter tools in clinical practice.