Clinical decision support (CDS) tools can 'nudge' clinicians to make the best decisions easy. Although required by "meaningful use" regulations, more than 40% of CDS lead to no change and the remaining lead to improvements that are modest at best. This is because CDS tools often ignore contextual factors and present irrelevant information. Although many tools have undergone patient-specific optimization, 'traditional CDS' are rarely clinician-specific. For example, a traditional CDS tool for beta blockers and heart failure with reduced ejection fraction (HFrEF) addresses common prescribing misconceptions by stating asthma is not a contraindication and providing a safe threshold for blood pressure. For clinicians without these misconceptions, these statements are irrelevant and distract from key information. A 'personalized CDS' would evaluate clinician past prescribing patterns to determine whether prescribing misconceptions might exist and then conditionally present information to address those misconceptions. The objective of this research is to create personalized clinician-specific CDS that overcome shortcomings of traditional CDS. The central hypothesis is a personalized CDS that minimizes irrelevant information will lead to a higher rate of prescribing guideline-directed management and therapy (GDMT) for HFrEF compared to a traditional CDS.

Inclusion Criteria:

• The study subjects are potential users of the CDS, specifically clinicians with prescribing privileges who practice at one of the health system's (UCHealth) outpatient cardiology or primary care clinics. Because we are observing their prescribing behaviors, we are also evaluating patient characteristics which could influence their prescribing decisions.

Exclusion Criteria:

• Clinicians who do not practice in cardiology or primary care clinics or do not practice within UCHealth system.

Data obtained through this study may be provided to qualified researchers with academic interest in related areas of interest. Data shared will be coded, with no PHI included. Approval of the request and execution of all applicable agreements (e.g., data use/sharing agreements) are prerequisites to the sharing of data with the requesting party. Data requests can be submitted starting 9 months after article publication and the data will be made accessible for up to 24 months. Access to trial IPD can be requested by qualified researchers engaging in independent scientific research, and will be provided following review and approval of a research proposal and Statistical Analysis Plan (SAP) and execution of a Data Sharing Agreement.

Data requests can be submitted starting 9 months after article publication and the data will be made accessible for up to 24 months.

Data obtained through this study may be provided to qualified researchers with academic interest in related areas of interest. Data shared will be coded, with no PHI included. Approval of the request and execution of all applicable agreements (e.g., data use/sharing agreements) are prerequisites to the sharing of data with the requesting party. Access to trial IPD can be requested by qualified researchers engaging in independent scientific research, and will be provided following review and approval of a research proposal and Statistical Analysis Plan (SAP) and execution of a Data Sharing Agreement.