Evaluating AI-Enabled Voice to Text for Medical Affairs Documentation and Insight Capture: The RAPID Randomized Crossover Trial.

Authors

Riaz Abbas, Jeongin Son, Marloes Oosterhof, Yosuke Amagai, Jackie Tang, Cheng Zhang, Bin Li, Caidan Luo, Seigo Susa, Ka Weng Mah, Helen Lin

Published in

Pharmaceutical medicine. Sep 06, 2026. Epub Sep 06, 2026.

Abstract

Artificial intelligence (AI) transcription systems using large language models (LLMs) and natural language processing (NLP) may reduce documentation burden. Medical science liaisons (MSLs) face challenges documenting scientific interactions with health care professionals (HCPs). This Amgen study evaluated whether AI-enabled transcription improved MSL documentation experience and insight documentation compared with existing practice (EP) of manual customer relationship management (CRM) entry.
This randomized crossover study enrolled 27 MSLs from six Amgen Asia-Pacific affiliates; 78% used non-English languages during V2T documentation. Participants were randomized 1:1 to voice-to-text (V2T) using Microsoft Copilot then EP, or EP then V2T (Copilot), with four-week study periods. The primary outcome was composite MSL Satisfaction Questionnaire (MSLSQ) score across efficiency, speed to CRM entry, cognitive load, ease of use, and insight structuring. Secondary assessment compared blinded therapeutic area (TA) expert ratings of insight quality. Exploratory analyses assessed language effects, interaction counts, and qualitative feedback.
All participants completed both periods. Composite MSLSQ scores were higher with V2T (Copilot) than EP (mean difference + 0.763; p = 0.0114, two-way repeated-measures analysis of variance (ANOVA)). Domain-level primary comparisons favored V2T (Copilot) across all five MSLSQ domains, while Wilcoxon sensitivity analyses most consistently supported improvements in speed to CRM entry, cognitive load, and insight structuring. TA expert-rated insight quality and documented interaction counts were similar. Satisfaction was lower among Japanese and Korean-speaking participants owing to lower transcription accuracy.
V2T (Copilot) improved documentation experience without improving insight quality or field activity. Limitations related to scientific terminology recognition, multilingual transcription, highlight opportunities to optimize AI-supported documentation in Medical Affairs. V2T (Copilot) improved the composite MSL-reported documentation satisfaction score, with the greatest improvements observed in cognitive load, speed to CRM entry, and insight structuring. Performance strengths included reduced documentation burden and improved structuring, while practical limitations included recognition of scientific terminology, lower transcription accuracy in Japanese and Korean, and lack of native CRM integration.

PMID:
42701995
Bibliographic data and abstract were imported from PubMed on 07 Sep 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.