Clinical Scorecard: AI Scribes and Same-Day Clinical Note Completion Across Patient Language Preferences and Interpreter Use
At a Glance
Category
Detail
Condition
Same-day note closure by patient language preference and interpreter modality
Key Mechanisms
AI scribe use was associated with same-day note closure; associations varied by encounter communication category.
Target Population
Adult primary care encounters at 14 clinics in one Boston academic medical center, May 2025 to May 2026
Care Setting
In-person adult primary care visits, including language-concordant and interpreter-mediated encounters
Key Highlights
The cross-sectional study included 209,009 encounters, 117,121 patients, and 286 clinicians.
Adjusted AI scribe use was associated with a 10.2 percentage-point higher probability of same-day note closure in NELP language-concordant encounters (95% CI, 7.4-12.9; P < .001).
In English language-concordant encounters, AI scribe use was associated with a 1.7 percentage-point higher probability of same-day note closure (95% CI, 0.9-2.6; P < .001).
Associations for nonconcordant encounters involving interpreters or no interpreter were inconclusive because confidence intervals were wide.
The study was observational; the reported associations should not be interpreted as causal effects.
Guideline-Based Recommendations
Diagnosis
Management
The authors recommend combining AI scribe adoption with investment in bilingual workforce development.
The authors recommend that developers prioritize models supporting interpreter-mediated workflows.
Monitoring & Follow-up
Risks
The authors suggest acoustically complex conversations, including multiple speakers and language switching, may affect AI scribe performance.
The retrospective, single-system design, clinician-selected use, and potential residual confounding limit interpretation and generalizability.
Patient & Prescribing Data
Adult primary care patients seen in person; NELP encounters accounted for 7.6% of encounters.
AI scribe use was associated with higher same-day note closure in language-concordant encounters, with the largest adjusted association in NELP language-concordant visits. Findings for interpreter-mediated and nonconcordant visits were inconclusive.
Clinical Best Practices
Interpret the reported results as associations, not causal effects.
Consider language concordance and interpreter modality when evaluating AI scribe performance.
Support bilingual workforce development alongside AI scribe adoption, as recommended by the authors.
