Talley, Heather Laine

Abstract Pharmacogenomic (PGx) biomarkers integrated using machine learning can be embedded within the electronic health record (EHR) to provide clinicians with individualized predictions of drug treatment outcomes. Currently, however, drug alerts in the EHR are largely generic (not patient‐specific) and contribute to increased clinician stress and burnout. Improving the usability of PGx alerts is an urgent need. Therefore, this work aimed to identify principles for optimal PGx alert design through a health‐system‐wide, mixed‐methods study. Clinicians representing multiple practices and care settings ( N = 1062) in urban, rural, and underserved regions were invited to complete an electronic survey comparing the usability of three drug alerts for citalopram, as a case study. Alert 1 contained a generic warning of pharmacogenomic effects on citalopram metabolism. Alerts 2 and 3 provided patient‐specific predictions of citalopram efficacy with varying depth of information. Primary outcomes included the System's Usability Scale score (0–100 points) of each alert, the perceived impact of each alert on stress and decision‐making, and clinicians' suggestions for alert improvement. Secondary outcomes included the assessment of alert preference by clinician age, practice type, and geographic setting. Qualitative information was captured to provide context to quantitative information. The final cohort comprised 305 geographically and clinically diverse clinicians. A simplified, individualized alert (Alert 2) was perceived as beneficial for decision‐making and stress compared with a more detailed version (Alert 3) and the generic alert (Alert 1) regardless of age, practice type, or geographic setting. Findings emphasize the need for clinician‐guided design of PGx alerts in the era of digital medicine.

Background: Depression is common in the primary care setting and tobacco use is more prevalent among individuals with depression. Recent research has linked smoking to poorer outcomes of depression treatment. We hypothesized that in adult primary care patients with the diagnosis of depression, current smoking would have a negative impact on clinical outcomes, regardless of treatment type (usual primary care [UC] vs collaborative care management [CCM]). Methods: A retrospective chart review study of 5155 adult primary care patients with depression in a primary care practice in southeast Minnesota was completed. Variables obtained included age, gender, marital status, race, smoking status, initial Patient Health Questionnaire–9 (PHQ-9), and 6-month PHQ-9. Clinical remission (CR) was defined as 6-month PHQ-9 <5. Persistent depressive symptoms (PDS) were defined as PHQ-9 ≥10 at 6 months. Treatment in both CCM and UC were compared. Results: Using intention to treat analysis, depressed smokers treated with CCM were 4.60 times as likely (95% CI 3.24-6.52, P < .001) to reach CR and were significantly less likely to have PDS at 6 months (adjusted odds ratio [AOR] 0.19, 95% CI 0.14-0.25, P < .001) compared with smokers in UC. After a 6-month follow-up, depressed smokers treated with CCM were 1.75 times as likely (95% CI 1.18-2.59, P = .006) to reach CR and were significantly less likely to have PDS (AOR 0.45, 95% CI 0.31-0.64, P < .001) compared with smokers in UC. Conclusions: CCM significantly improved depression outcomes for smokers at 6 months compared with UC. However, in the UC group, smoking outcomes were not statistically different at 6 months for either remission or PDS. Also, nonsmokers in CCM had the best clinical outcomes at 6 months in both achieving clinical remission and reduction of PDS when compared with smokers in UC as the reference group.