Automatic Speech Recognition System to Record Progress Notes in a Mobile EHR: A Pilot Study Carolina Paula VARGAS a,1 , Alejandro GAIERA a , Andres BRANDÁN a , Alejandro RENATO a , Sonia BENITEZ a and Daniel LUNA a a Health Informatics Department, Hospital Italiano de Buenos Aires, Argentina ORCiD ID: Carolina Paula Vargas https://orcid.org/0000-0002-7701-3251., Sonia Benitez https://orcid.org/0000-0001-6648-1984. Abstract. Creating notes in the EHR is one of the most problematic aspects for health professionals. The main challenges are the time spent on this task and the quality of the records. Automatic speech recognition technologies aim to facilitate clinical documentation for users, optimizing their workflow. In our hospital, we internally developed an automatic speech recognition system (ASR) to record progress notes in a mobile EHR. The objective of this article is to describe the pilot study carried out to evaluate the implementation of ASR to record progress notes in a mobile EHR application. As a result, the specialty that used ASR the most was Home Medicine. The lack of access to a computer at the time of care and the need to perform short and fast evolutions were the main reasons for users to use the system. Keywords. Speech recognition software, mobile applications, electronic health records 1. Introduction Clinical records are a significant part of the daily workflow of healthcare professionals. Documenting the evolution of patients in clinical history is critical to the continuity of care processes. However, this task consumes much of the work time of users, most of whom in many cases must dedicate overtime [1], increasing their labor burden. Concerned about speeding up the clinical documentation process, professionals use inappropriate methods such as omission of data or use of copy/paste in progress notes [2] of the Electronic Health Record (EHR), reducing their quality. As an opportunity for technological improvement to facilitate clinical documentation, the incorporation of an automatic speech recognition system (ASR) to the EHR has grown in recent years. This technology allows the sound recognition of words and their automatic decoding, providing users with the possibility of performing records in a synchronous and agile manner. The literature on the implementation of ASR integrated to the EHR in mobile format for clinical settings is scarce. Although there is published evidence that evaluates the risks and benefits of using the system [3], and comparisons of this against 1 Corresponding Author: Carolina Paula Vargas, email: carolina.vargas@hospitalitaliano.org.ar. MEDINFO 2023 — The Future Is Accessible J. Bichel-Findlay et al. (Eds.) © 2024 International Medical Informatics Association (IMIA) and IOS Press. This article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License 4.0 (CC BY-NC 4.0). doi:10.3233/SHTI230940 124