JMIR Publications

ABSTRACT

Background:

Patients’ spontaneous speech can act as a biomarker for identifying pathological entities, such as pulmonary hypertension and mental illness. Despite this potential, audio-recording patients’ spontaneous speech is not part of clinical workflows, and healthcare organizations often do not have dedicated policies about audio-recording of clinical encounters. No previous studies investigated the best practical approach for integrating audio-recording patient-clinician encounters into clinical workflows, particularly in the home healthcare (HHC) setting.

Objective:

The aims of this study were: 1) To evaluate the functionality and usability of several audio-recording devices for audio-recording of patient-nurse verbal communications in the HHC setting; 2) To elicit HHC stakeholders’ (patients’ and nurses’) perspectives about the facilitators and barriers of integrating audio-recordings into the clinical workflows.

Methods:

This study was conducted at a large urban HHC agency located in New York. We evaluated the usability and functionality of seven audio-recording devices in a laboratory (controlled) settings Three devices, Saramonic Blink500, Sony ICD-TX6, and Black Vox 365 were further evaluated in a clinical setting (patients’ homes) by HHC nurses who completed the System Usability Scale (SUS) questionnaire and participated in a short, structured interview to elicit feedback about each device. We also evaluated the accuracy of automatic transcription of audio-recorded encounters for the three devices using Amazon Web Service (AWS) Transcribe. Word Error Rate (WER) was used for measuring the accuracy of automated speech transcription. To understand the facilitators and barriers of integrating audio-recording of encounters into clinical workflows, we conducted semi-structured interviews with three HHC nurses and ten HHC patients. Thematic analysis was used to analyze the transcribed interviews.

Results:

Saramonic Blink500 received the best overall evaluation score, followed by SONY ICD, and Black Vox 365. The SUS score and WER for Saramonic Blink500 was 65% and 26% respectively, and nurses found it easier to approach patients using this device compared to the two other devices. Overall, patients found the process of audio-recording satisfactory and convenient with minimal impact on their communications with nurses. Although in general, nurses also found the process easy to learn and satisfactory, they suggested that audio-recording of HHC encounters can affect their communication patterns. Additionally, nurses were not aware of the potential to use audio-recorded encounters to improve healthcare services offered to patients. Nurses also indicated that they would need their managers involved to determine how it could be integrated into their clinical workflows and for any ongoing use of audio-recording during patient care management.

Conclusions:

This study established the feasibility of audio-recording of HHC patient-nurse encounters. Training of HHC nurses about the importance of the audio-recording process and support of a clinical managers are essential factors for the successful implementation