Sharing Annotated Audio Recordings of Clinic Visits With Patients-Development of the Open Recording Automated Logging System (ORALS): Study Protocol

The Feasibility and Acceptability of Sharing Video Recordings of Amyotrophic Lateral Sclerosis Clinical Encounters With Patients and Their Caregivers: Pilot Randomized Clinical Trial

BACKGROUND

Multidisciplinary clinics (MDCs) provide benefits to patients with amyotrophic lateral sclerosis (ALS) and their caregivers, but MDC visits are information-heavy and can last 4 hours, with patients and caregivers meeting with multiple specialists within each MDC visit. There are questions about the effectiveness of current methods of sharing information from MDCs with patients. Video recordings are a promising new method of sharing information that may allow patients and caregivers to revisit the MDC and remind them of clinical recommendations and conversations.

OBJECTIVE

The objective of this trial is to determine the feasibility and acceptability of sharing information through video recordings of ALS MDC visits with patients and caregivers.

METHODS

This study was a randomized, controlled pilot trial with 3 months of follow-up from April 2021 to March 2022 in a rural multidisciplinary neurology clinic. We recruited patients with ALS, their caregivers, and their clinicians. Patients and their caregivers were randomized to either receive their normal after-visit summary (treatment as usual) or to receive their normal after-visit summary and a video recording of their MDC visit (video). Each specialist visit had its own recording and was accessible by patients and caregivers using a secure web-based platform called HealthPAL over a 3-month follow-up period. Primary study outcomes were feasibility and acceptability of the video intervention measured by recruitment rate (target: 70%), percentage of participants watching videos (target: 75%), and the Feasibility of Intervention Measure and Acceptability of Intervention Measure (targets: 3/5). We hypothesized that video recording would be feasible and acceptable to patients and their caregivers.

RESULTS

Of the 30 patients approached, 24 were recruited, while all caregivers (n=21) and clinicians (n=34) approached were recruited. A total of 144 specialist visits were recorded, approximately 12 specialist visits at a median of one MDC visit per patient. Of the recorded patients, 75% (9/12) viewed videos. High median intervention feasibility (4, SD 0.99) and acceptability (4, SD 1.22) of intervention measures were reported by patients and caregivers in the intervention arm. High median intervention feasibility (5, SD 0.21) and acceptability (4.88, SD 0.4) were reported by clinicians. Of the 24 patients, 50% (n=12) did not complete a 3-month follow-up, primarily due to death (n=10).

CONCLUSIONS

Video recording is highly feasible and acceptable for patients, caregivers, and clinicians at a rural ALS clinic. Our level of attrition is a useful benchmark for future studies in MDC populations. Despite high rates of patient death, 1-week assessments highlight the value of recordings for both patients and caregivers.

TRIAL REGISTRATION

ClinicalTrials.gov NCT04719403; https://clinicaltrials.gov/study/NCT04719403.

CUSCO: An Unobtrusive Custom Secure Audio-Visual Recording System for Ambient Assisted Living

The ubiquity of digital technology has facilitated detailed recording of human behaviour. Ambient technology has been used to capture behaviours in a broad range of applications ranging from healthcare and monitoring to assessment of cooperative work. However, existing systems often face challenges in terms of autonomy, usability, and privacy. This paper presents a portable, easy-to-use and privacy-preserving system for capturing behavioural signals unobtrusively in home or in office settings. The system focuses on the capture of audio, video, and depth imaging. It is based on a device built on a small-factor platform that incorporates ambient sensors which can be integrated with the audio and depth video hardware for multimodal behaviour tracking. The system can be accessed remotely and integrated into a network of sensors. Data are encrypted in real time to ensure safety and privacy. We illustrate uses of the device in two different settings, namely, a healthy-ageing IoT application, where the device is used in conjunction with a range of IoT sensors to monitor an older person's mental well-being at home, and a healthcare communication quality assessment application, where the device is used to capture a patient-clinician interaction for consultation quality appraisal. CUSCO can automatically detect active speakers, extract acoustic features, record video and depth streams, and recognise emotions and cognitive impairment with promising accuracy.

Methodological innovations to strengthen evidence-based serious illness communication

BACKGROUND/OBJECTIVE

A growing population of those affected by serious illness, prognostic uncertainty, patient diversity, and healthcare digitalization pose challenges for the future of serious illness communication. Yet, there is paucity of evidence to support serious illness communication behaviors among clinicians. Herein, we propose three methodological innovations to advance the basic science of serious illness communication.

RESULTS

First, advanced computation techniques - e.g. machine-learning techniques and natural language processing - offer the possibility to measure the characteristics and complex patterns of audible serious illness communication in large datasets. Second, immersive technologies - e.g., virtual- and augmented reality - allow for experimentally manipulating and testing the effects of specific communication strategies, and interactional and environmental aspects of serious illness communication. Third, digital-health technologies - e.g., shared notes and videoconferences - can be used to unobtrusively observe and manipulate communication, and compare in-person to digitally-mediated communication elements and effects. Immersive and digital health technologies allow integration of physiological measurement (e.g. synchrony or gaze) that may advance our understanding of patient experience.

CONCLUSION/PRACTICE IMPLICATIONS

New technologies and measurement approaches, while imperfect, will help advance our understanding of the epidemiology and quality of serious illness communication in an evolving healthcare environment.

Audio Recording Patient-Nurse Verbal Communications in Home Health Care Settings: Pilot Feasibility and Usability Study

Background

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

Objective

This study aimed to evaluate the functionality and usability of several audio-recording devices for the audio recording of patient-nurse verbal communications in the HHC settings and elicit HHC stakeholder (patients and nurses) perspectives about the facilitators of and barriers to integrating audio recordings into clinical workflows.

Methods

This study was conducted at a large urban HHC agency located in New York, United States. We evaluated the usability and functionality of 7 audio-recording devices in a laboratory (controlled) setting. A total of 3 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 questionnaire and participated in a short, structured interview to elicit feedback about each device. We also evaluated the accuracy of the automatic transcription of audio-recorded encounters for the 3 devices using the Amazon Web Service Transcribe. Word error rate was used to measure the accuracy of automated speech transcription. To understand the facilitators of and barriers to integrating audio recording of encounters into clinical workflows, we conducted semistructured interviews with 3 HHC nurses and 10 HHC patients. Thematic analysis was used to analyze the transcribed interviews.

Results

Saramonic Blink500 received the best overall evaluation score. The System Usability Scale score and word error rate for Saramonic Blink500 were 65% and 26%, respectively, and nurses found it easier to approach patients using this device than with the other 2 devices. Overall, patients found the process of audio recording to be satisfactory and convenient, with minimal impact on their communication with nurses. Although, in general, nurses also found the process easy to learn and satisfactory, they suggested that the audio recording of HHC encounters can affect their communication patterns. In addition, nurses were not aware of the potential to use audio-recorded encounters to improve health care services. Nurses also indicated that they would need to involve their managers to determine how audio recordings could be integrated into their clinical workflows and for any ongoing use of audio recordings during patient care management.

Conclusions

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

Use of Voice Recordings in the Consultation of Patients Seeking Genital Gender-Affirming Surgery: An Opportunity for Broader Application Throughout Surgery?

Introduction

It has been demonstrated that patient memory for medical information is often poor and inaccurate. The use of audio recordings for patient consultation has been described; however, to our knowledge this is the first reported use of audio recordings in consultation for gender-affirming surgery. Our aim was to determine whether, and specifically how, audio recording the consultation of patients presenting for genital gender-affirming surgery would be of benefit to patients.

Materials and Methods

We began to offer all new patients the opportunity to have their consultations recorded. At the end of the consultation the recording was uploaded to a USB, which was given to the patient to keep. We then surveyed all patients who had received a copy of their recorded consultation to query the utility of having access to an audio recording of their consultation.

Results

71/72 (98.6%) patients who were given the option to have their consultation recorded chose to do so. 50/71 (70%) of patients who had their consultation recorded responded to our survey. Patients reported that having access to a voice recording of their consultation was beneficial and was viewed overwhelmingly positively.

Conclusions

Routine audio recording of patient consultations is highly beneficial to patients, with little cost to providers, and should be considered as a valuable addition to the new patient consultation. This approach may have applications in broader clinical contexts where patients face numerous, complex, and nuanced management options. The study would benefit from continued application and a larger (multi-center, international) sample.

Mobile Audio Recording Technology to Promote Informed Decision Making in Advanced Prostate Cancer

PURPOSE

Men with metastatic castration-resistant prostate cancer increasingly encounter complex treatment decisions. Consultation audio recordings and summaries promote patient informed decision making but are underutilized. Mobile recording software applications may increase access. Little is known regarding the feasibility of implementation in clinical encounters.

METHODS

We conducted a mixed-methods pilot study in men with progressive metastatic castration-resistant prostate cancer. We instructed patients to use a mobile software application to record an oncology visit. Patients could share the recording with our patient scribing program to receive a written summary. We assessed feasibility and acceptability with postvisit surveys. We measured patient-reported helpfulness of the intervention in decision making and change in Decisional Conflict Scale-informed subscale. We conducted semistructured interviews to explore implementation and analyzed transcripts using thematic analysis.

RESULTS

Across 20 patients, 18 (90%) recorded their visits. Thirteen of 18 (72%) listened to the recording, and 14 of 18 (78%) received a summary. Eighteen of 20 (90%) visits were telehealth. Fourteen patients (70% of all 20; 78% of 18 question respondents) found the application easy to use. Nine patients (50% of 18 recording patients; 90% of 10 question respondents) reported that the recording helped treatment decision making. Decisional conflict decreased from baseline to 1-week postvisit (47.4-28.5, P < .001). Interviews revealed benefits, facilitators, contextual factors, and technology and patient-related barriers to recordings and summaries.

CONCLUSION

In this single-institution academic setting, a mobile application for patients to record consultations was a feasible, acceptable, and potentially valued intervention that improved decision making in the telehealth setting. Studies in larger, diverse populations are needed.

Natural language processing for automated annotation of medication mentions in primary care visit conversations

OBJECTIVES

The objective of this study is to build and evaluate a natural language processing approach to identify medication mentions in primary care visit conversations between patients and physicians.

MATERIALS AND METHODS

Eight clinicians contributed to a data set of 85 clinic visit transcripts, and 10 transcripts were randomly selected from this data set as a development set. Our approach utilizes Apache cTAKES and Unified Medical Language System controlled vocabulary to generate a list of medication candidates in the transcribed text and then performs multiple customized filters to exclude common false positives from this list while including some additional common mentions of the supplements and immunizations.

RESULTS

Sixty-five transcripts with 1121 medication mentions were randomly selected as an evaluation set. Our proposed method achieved an F-score of 85.0% for identifying the medication mentions in the test set, significantly outperforming existing medication information extraction systems for medical records with F-scores ranging from 42.9% to 68.9% on the same test set.

DISCUSSION

Our medication information extraction approach for primary care visit conversations showed promising results, extracting about 27% more medication mentions from our evaluation set while eliminating many false positives in comparison to existing baseline systems. We made our approach publicly available on the web as an open-source software.

CONCLUSION

Integration of our annotation system with clinical recording applications has the potential to improve patients' understanding and recall of key information from their clinic visits, and, in turn, to positively impact health outcomes.

Supporting communication of visit information to informal caregivers: A systematic review

Importance

When caregivers cannot attend the clinic visit for the person they provide care for, patients are the predominant source of clinic visit information; however, poor patient recall inhibits the quality of information shared, resulting in poor caregiver preparedness and contributing to caregiver morbidity. Technological solutions exist to sharing clinic visit information, but their effectiveness is unclear.

Objectives

To assess if and how technology is being used to connect informal caregivers to patient clinic visit information when they cannot otherwise attend, and its impact on caregiver and patient outcomes.

Evidence review

MEDLINE, Cochrane, Scopus, and CINAHL were searched through 5/3/2020 with no language restrictions or limits. ClinicalTrials.gov and other reference lists were included in the search. Randomized controlled trials (RCTs) and nonrandomized trials that involved using a technological medium e.g., video or the electronic health record, to communicate visit information to a non-attending caregiver were included. Data were collected and screened using a standardized data collection form. Cochrane’s Risk of Bias 2.0 and the Newcastle-Ottawa Scale were used for RCTs and nonrandomized trials, respectively. All data were abstracted by two independent reviewers, with disagreements resolved by a third reviewer.

Findings

Of 2115 studies identified in the search, four met criteria for inclusion. Two studies were randomized controlled trials and two were nonrandomized trials. All four studies found positive effects of their intervention on caregiver outcomes of interest, and three out of four studies found statistically significant improvements in key outcomes for caregivers receiving visit information. Improved outcomes included caregiver happiness, caregiver activation, caregiver preparedness, and caregiver confidence in managing patient health.

Conclusions and relevance

Our review suggests that using technology to give a caregiver access to clinical visit information could be beneficial to various caregiver outcomes. There is an urgent need to address the lack of research in this area.

Detecting conversation topics in primary care office visits from transcripts of patient-provider interactions

Objective

Amid electronic health records, laboratory tests, and other technology, office-based patient and provider communication is still the heart of primary medical care. Patients typically present multiple complaints, requiring physicians to decide how to balance competing demands. How this time is allocated has implications for patient satisfaction, payments, and quality of care. We investigate the effectiveness of machine learning methods for automated annotation of medical topics in patient-provider dialog transcripts.

Materials and Methods

We used dialog transcripts from 279 primary care visits to predict talk-turn topic labels. Different machine learning models were trained to operate on single or multiple local talk-turns (logistic classifiers, support vector machines, gated recurrent units) as well as sequential models that integrate information across talk-turn sequences (conditional random fields, hidden Markov models, and hierarchical gated recurrent units).

Results

Evaluation was performed using cross-validation to measure 1) classification accuracy for talk-turns and 2) precision, recall, and F1 scores at the visit level. Experimental results showed that sequential models had higher classification accuracy at the talk-turn level and higher precision at the visit level. Independent models had higher recall scores at the visit level compared with sequential models.

Conclusions

Incorporating sequential information across talk-turns improves the accuracy of topic prediction in patient-provider dialog by smoothing out noisy information from talk-turns. Although the results are promising, more advanced prediction techniques and larger labeled datasets will likely be required to achieve prediction performance appropriate for real-world clinical applications.

Meaningful shared decision-making: complex process demanding cognitive and emotional skills

BACKGROUND

Shared decision-making (SDM) takes place when clinicians help patient identify best course of action in the context of their preferences.

METHODS

The aim of this paper is a narrative review of the literature with special focus on the humanistic dimensions of SDM.

RESULTS

We show that SDM is largely underused in practice, because of many barriers such as time constraints and poor skills.

CONCLUSIONS

We suggest that listening and empathy are key challenges in communicating uncertainty, which require emotional intelligence and trust building skills. To promote implementation, we propose the development of tools, simulation-based training and the design of improved measures for SDM quality. While essential for patients, we believe that SDM may restore meaning in healthcare.

Heart sounds: a pilot randomised trial to determine the feasibility and acceptability of audio recordings to improve discharge communication for cardiology inpatients protocol

Introduction

Ineffective hospital discharge communication can significantly impact patient understanding, safety and treatment adherence. This may be especially true for cardiology inpatients who leave the hospital with complex discharge plans delivered in a time-pressured discharge discussion. The goal of this pilot trial was to determine if providing supplemental audio-recorded discharge instructions is feasible and to explore its impact on cardiology patients' ability to understand and self-manage their care .

Methods and analysis

We will conduct a parallel-group, randomised controlled trial in adult cardiology inpatients with balanced blocking by a physician. Patients (n=50) will be randomised to usual care (verbal discussion and written summary) or intervention (usual care, plus audio-recorded discharge discussion provided to patients on a portable electronic recording device). Enrolled patients will complete study assessments immediately prior to the discharge discussion, immediately postdischarge discussion and 1 week after hospital discharge by telephone. Primary outcomes include the proportion of eligible providers and inpatients who agree to take part in the trial, the proportion of inpatients who receive the audio recording in accordance with a fidelity checklist, and the proportion who use the audio recording. We will analyse preliminary data about the impact of audio recording on patient activation, health confidence, provider communication ability, adherence and 30-day readmissions.

Ethics and dissemination

This trial was approved by The Committee for the Protection of Human Subjects (CPHS) at Dartmouth College (CPHS# 00031211). Findings will be disseminated in scientific journals and at meetings.

Trial registration number

NCT03735342

Protocol version

1.0

Audio-/Videorecording Clinic Visits for Patient's Personal Use in the United States: Cross-Sectional Survey

BACKGROUND

Few clinics in the United States routinely offer patients audio or video recordings of their clinic visits. While interest in this practice has increased, to date, there are no data on the prevalence of recording clinic visits in the United States.

OBJECTIVE

Our objectives were to (1) determine the prevalence of audiorecording clinic visits for patients' personal use in the United States, (2) assess the attitudes of clinicians and public toward recording, and (3) identify whether policies exist to guide recording practices in 49 of the largest health systems in the United States.

METHODS

We administered 2 parallel cross-sectional surveys in July 2017 to the internet panels of US-based clinicians (SERMO Panel) and the US public (Qualtrics Panel). To ensure a diverse range of perspectives, we set quotas to capture clinicians from 8 specialties. Quotas were also applied to the public survey based on US census data (gender, race, ethnicity, and language other than English spoken at home) to approximate the US adult population. We contacted 49 of the largest health systems (by clinician number) in the United States by email and telephone to determine the existence, or absence, of policies to guide audiorecordings of clinic visits for patients' personal use. Multiple logistic regression models were used to determine factors associated with recording.

RESULTS

In total, 456 clinicians and 524 public respondents completed the surveys. More than one-quarter of clinicians (129/456, 28.3%) reported that they had recorded a clinic visit for patients' personal use, while 18.7% (98/524) of the public reported doing so, including 2.7% (14/524) who recorded visits without the clinician's permission. Amongst clinicians who had not recorded a clinic visit, 49.5% (162/327) would be willing to do so in the future, while 66.0% (346/524) of the public would be willing to record in the future. Clinician specialty was associated with prior recording: specifically oncology (odds ratio [OR] 5.1, 95% CI 1.9-14.9; P=.002) and physical rehabilitation (OR 3.9, 95% CI 1.4-11.6; P=.01). Public respondents who were male (OR 2.11, 95% CI 1.26-3.61; P=.005), younger (OR 0.73 for a 10-year increase in age, 95% CI 0.60-0.89; P=.002), or spoke a language other than English at home (OR 1.99; 95% CI 1.09-3.59; P=.02) were more likely to have recorded a clinic visit. None of the large health systems we contacted reported a dedicated policy; however, 2 of the 49 health systems did report an existing policy that would cover the recording of clinic visits for patient use. The perceived benefits of recording included improved patient understanding and recall. Privacy and medicolegal concerns were raised.

CONCLUSIONS

Policy guidance from health systems and further examination of the impact of recordings-positive or negative-on care delivery, clinician-related outcomes, and patients' behavioral and health-related outcomes is urgently required.