ArticlePharmaceutical medicine2026
Evaluating AI-Enabled Voice to Text for Medical Affairs Documentation and Insight Capture: The RAPID Randomized Crossover Trial.
Article in Pharmaceutical medicine, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
11 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
BACKGROUND AND
objectivesArtificial 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.
methodsThis 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.
resultsAll 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.
conclusionsV2T (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.
Indexed as
Identifiers
42701995What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.