Impact of a Multilingual Ambient AI Scribe: A Real-World Time-Motion Study (Preprint)

BACKGROUND Ambient AI scribes are increasingly used to reduce clinician burnout and cognitive load, though their impact on documentation time remains inconsistent across studies. Most existing real-world impact studies have been conducted in the United States and rely on electronic health record timestamps, which may not accurately reflect actual documentation time. No published studies assessed their effectiveness in multilingual clinical environments, where language diversity may influence outcomes. OBJECTIVE To quantify the impact of an ambient scribe technology on clinician efficiency and patient engagement in a multilingual outpatient setting using direct observational methods and patient surveys. METHODS We conducted a prospective, within-clinician quality improvement study at a large academic medical centre in Singapore from December 2024 to May 2025. Nine clinicians participated in matched observation sessions with and without an in-house ambient scribe tool. The ambient scribe tool supported multiple languages, enabling evaluation in a naturally multilingual clinical environment. Five trained observers used standardised time-motion methodology to capture documentation time, proportion of eye contact, and consultation duration across 169 consultations. Patient surveys were administered following consultations using the ambient scribe. Linear mixed-effects models were used to account for clustering within clinicians. RESULTS Ambient scribe use was associated with a 15.0% reduction in documentation time per consultation (5.3 to 4.5 minutes; P=.036), 10.6% increase in proportion of eye contact time (69.6% to 77.1%, P=.009), and no significant change in consultation duration (11.5 vs 10.9 minutes, P=.415). Effects were consistent across new and follow-up patients. Among consultations with the ambient scribe, 81% were conducted in English, 18% in Mandarin, and 1% in Malay. Patient acceptance was favourable: among 39 surveyed patients, 69% agreed their doctor focused on them more during the consultation, and none expressed discomfort with the technology. CONCLUSIONS This first real-world evaluation of ambient scribe use in a multilingual Asian healthcare setting demonstrates that experienced users achieved reduced documentation time and improved patient engagement without affecting consultation duration. The technology was effective across multiple languages and well accepted by patients. These findings suggest ambient scribes should be viewed as quality-of-care interventions that shift clinician attention from clerical tasks to patient engagement, supporting broader implementation in diverse healthcare settings.