Introduction

Digital exposure notification (EN) approaches may offer considerable advantages over traditional contact tracing in speed, scale, efficacy, and confidentiality in pandemic control. We applied the science of learning health systems to test the effect of framing and digital means, email vs Short Message Service (SMS), on EN adoption among patients of an academic health center.

Methods

We tested three communication approaches of the Apple and Google EN system in a rapid learning cycle involving 15 000 patients pseudorandomly assigned to three groups. The patients in the first group received a 284-word email that presented EN as a tool that can help slow the spread. The patients in the second group received a 32-word SMS that described EN as a new tool to help slow the spread (SlowTheSpreadSMS). Patients in the third group received a 47-word SMS that depicted the system as a new digital tool that can empower them to protect their family and friends (EmpowerSMS). A brief four-question anonymous survey of adoption was included in a reminder message sent 2 days after the initial outreach.

Results

One hundred and sixty people responded to the survey within 1 week: 2.33% from EmpowerSMS, 0.97% from SlowTheSpreadSMS, and 0.53% from emails; 29 (41.43%), 24 (41.38%), and 11 (34.38%) reported having adopted EN from each group, respectively. Patient reported barriers to adoption included iOS version incompatibility, privacy concerns, and low trust of government agencies or companies like Apple and Google. Patients recommended that healthcare systems play an active role in disseminating information about this tool. Patients also recommended advertising on social media and providing reassurance about privacy.

Conclusions

The EmpowerSMS resulted in relatively more survey responses. Both SMS groups had slightly higher, but not statistically significant EN adoption rates compared to email. Findings from the pilot not only informed operational decision-making in our health system but also contributed to EN rollout planning in our State.

Background

Chronic obstructive pulmonary disease (COPD) is the third leading cause of death by disease worldwide and has a 30-day readmission rate of 22.6%. In 2015, COPD was added to the Medicare Hospital Readmission Reductions Program.

Objective

The objective of this paper was to survey the current medical technologies for remote patient monitoring (RPM) tools that forecast COPD exacerbations in order to reduce COPD readmissions.

Methods

We searched literature and digital health news to find commercially available RPM devices focused on predicting COPD exacerbations. These technologies were reviewed and compared according to four criteria: forecasting ability, cost, ease of use, and appearance. A rating system was developed to facilitate the evaluation process.

Results

As of June 2019, a list of handheld and hands-free devices was compiled. We compared features and found substantial variations. Devices that ranked higher on all criteria tended to have a high or unlisted price. Commonly mass-marketed devices like the pulse oximeter and spirometer surprisingly fulfilled the least criteria.

Conclusions

The COPD RPM technologies with most technological promise and compatibility with daily living appear to have high or unlisted prices. Consumers and providers need better access to product information to make informed decisions.

The 23rd annual conference of the Health Care Systems Research Network (HCSRN, formerly the HMO Research Network) was held in San Diego, California, March 21-23, 2017, attracting 387 attendees. As a consortium of 20 research organizations embedded in or affiliated with large health care delivery organizations, the HCSRN has held annual research conferences since 1994. The overall aim of the conferences is to bring researchers, project staff, research funders and other stakeholders together to share latest scientific findings and foster new research ideas and collaborations. The 2017 conference was hosted by the Palo Alto Medical Foundation Research Institute. Each host site takes responsibility for the content and structure of the conference, and the 2017 team introduced several new features. In particular, past conferences used concurrent sessions to present research results in different topical areas, such as chronic disease, cancer, health informatics, mental health or precision medicine. This year, concurrent sessions shifted to panel discussions about how research results were achieved, including the use of methods, partnerships and analytic approaches. The 35 panels were organized into tracks such as engagement, data and informatics, partnerships and research implementation. Scientific results from HCSRN projects were presented via 120 posters in two poster sessions. Plenary sessions included a town hall-style panel with different funding agency representatives, an opening presentation on the range of opportunities and benefits to studying health systems, and a concluding presentation on how researchers can apply design thinking in their work.

Background

Patient portals tethered to electronic health records can improve patient experience, activation, and outcomes. However, adoption of inpatient portals has been challenging. One way to potentially increase inpatient portal usage is to integrate it with a room control (RC) app on a common tablet computer.

Objective

The aim of this study was to perform a retrospective analysis of patient usage of an RC app provided on tablet computers in patient rooms of our new inpatient tower.

Methods

We identified all patients who were admitted for >24 hours to our new inpatient tower over a 90-day period from September 1 to November 30, 2017. After excluding newborn patients from our analysis, we then identified patients who used the RC app at least one time during their admission. We linked these data to patient demographics (including age, sex, and race) and admitting service. We then performed univariable and multivariable logistic regression to assess patterns of RC app usage.

Results

A total of 3411 patients were admitted over the course of the study period; 2242/3411 (65.73%) used the RC app during their hospitalization. Compared with white patients, other/mixed/unknown race and Asian, Hawaiian, Pacific Islander, American Indian race were significantly associated with increased use of the RC app in a multivariable analysis. Increasing age was significantly associated with increased usage of the RC app. Usage of the RC app also varied by admitting services. Compared with general medicine, bone marrow transplant and general surgery patients had increased usage of the RC app. Conversely, critical care, medical specialties, neurology, surgical subspecialties, and obstetrics/gynecology were all associated with decreased usage of the RC app.

Conclusions

Our study shows that one-third of patients are not using the RC app for critical room functions. Future initiatives to increase RC usage should take these populations into consideration. Contrary to common belief, older patients may use tablet-enabled RCs just as often, if not more often, than younger patients. Certain admitting services, such as neurology and surgical subspecialties, may have had lower usage rates owing to accessibility issues. Our study allows hospitals to tailor support for specific patient populations to increase RC app usage.

BACKGROUND: Artificial intelligence (AI) is a rapidly advancing field that is beginning to enter the practice of medicine. Primary care is a cornerstone of medicine and deals with challenges such as physician shortage and burnout which impact patient care. AI and its application via digital health is increasingly presented as a possible solution. However, there is a scarcity of research focusing on primary care physician (PCP) attitudes toward AI. This study examines PCP views on AI in primary care. We explore its potential impact on topics pertinent to primary care such as the doctor-patient relationship and clinical workflow. By doing so, we aim to inform primary care stakeholders to encourage successful, equitable uptake of future AI tools. Our study is the first to our knowledge to explore PCP attitudes using specific primary care AI use cases rather than discussing AI in medicine in general terms. METHODS: From June to August 2023, we conducted a survey among 47 primary care physicians affiliated with a large academic health system in Southern California. The survey quantified attitudes toward AI in general as well as concerning two specific AI use cases. Additionally, we conducted interviews with 15 survey respondents. RESULTS: Our findings suggest that PCPs have largely positive views of AI. However, attitudes often hinged on the context of adoption. While some concerns reported by PCPs regarding AI in primary care focused on technology (accuracy, safety, bias), many focused on people-and-process factors (workflow, equity, reimbursement, doctor-patient relationship). CONCLUSION: Our study offers nuanced insights into PCP attitudes towards AI in primary care and highlights the need for primary care stakeholder alignment on key issues raised by PCPs. AI initiatives that fail to address both the technological and people-and-process concerns raised by PCPs may struggle to make an impact.

Introduction

Medicare beneficiaries often report that the process of choosing a prescription drug plan is frustrating and confusing and many do not enroll in the plan that covers their drugs at the lowest cost.

Methods

We conducted 4 focus groups to understand beneficiaries' experiences in selecting a drug plan to identify what resources and factors were most important to them. Participants were patients served by a multispecialty delivery system and were primarily affluent and Caucasian.

Results

While low cost was essential to many, other characteristics like having the same plan as a partner, company reputation, convenience, and anticipation of possible future health problems were sometimes more important. Although some used resources including insurance brokers, counselors, and websites beyond Medicare.gov, many expressed a desire for greater assistance with and greater simplicity in the choice process.

Conclusion

Although older adults would likely benefit from greater assistance in choosing Medicare Part D prescription drug plans, more research is necessary to understand how to help with decision-making in this context.

Background

Electronic health record (EHR)-based patient messages can contribute to burnout. Messages with a negative tone are particularly challenging to address. In this perspective, we describe our initial evaluation of large language model (LLM)-generated responses to negative EHR patient messages and contend that using LLMs to generate initial drafts may be feasible, although refinement will be needed.

Methods

A retrospective sample (n = 50) of negative patient messages was extracted from a health system EHR, de-identified, and inputted into an LLM (ChatGPT). Qualitative analyses were conducted to compare LLM responses to actual care team responses.

Results

Some LLM-generated draft responses varied from human responses in relational connection, informational content, and recommendations for next steps. Occasionally, the LLM draft responses could have potentially escalated emotionally charged conversations.

Conclusion

Further work is needed to optimize the use of LLMs for responding to negative patient messages in the EHR.

Background Artificial intelligence (AI) is a rapidly advancing field that is beginning to enter the practice of medicine. Primary care is a cornerstone of medicine and deals with challenges such as physician shortage and burnout which impact patient care. AI and its application via digital health is increasingly presented as a possible solution. However, there is a scarcity of research focusing on primary care physician (PCP) attitudes toward AI. This study examines PCP views on AI in primary care. We explore its potential impact on topics pertinent to primary care such as the doctor-patient relationship and clinical workflow. By doing so, we aim to inform primary care stakeholders to encourage successful, equitable uptake of future AI tools. Our study is the first to our knowledge to explore PCP attitudes using specific primary care AI use cases rather than discussing AI in medicine in general terms. Methods From June to August 2023, we conducted a survey among 47 primary care physicians affiliated with a large academic health system in Southern California. The survey quantified attitudes toward AI in general as well as concerning two specific AI use cases. Additionally, we conducted interviews with 15 survey respondents. Results Our findings suggest that PCPs have largely positive views of AI. However, attitudes often hinged on the context of adoption. While some concerns reported by PCPs regarding AI in primary care focused on technology (accuracy, safety, bias), many focused on people-and-process factors (workflow, equity, reimbursement, doctor-patient relationship). Conclusion Our study offers nuanced insights into PCP attitudes towards AI in primary care and highlights the need for primary care stakeholder alignment on key issues raised by PCPs. AI initiatives that fail to address both the technological and people-and-process concerns raised by PCPs may struggle to make an impact.

Compared with people living in the community, researchers often have different frameworks or paradigms for thinking about health and wellness. These differing frameworks are often accompanied by differences in terminology or language. The purpose of this commentary is to describe some of our "Aha!" moments from conducting two pilot studies funded by the Patient-Centered Outcomes Research Institute. Over time, we came to understand how our language and word choices may have been acting as a wedge between ourselves and our community research partners. We learned that fruitful collaborative work must attend to the creation of a common language, which we refer to as the language of engagement. Such patient-centered language can effectively build a bridge between researchers and community partners. We encourage other researchers to think critically about their cultural competency, to be mindful of the social power dynamics between patient and physician, to reflect on how their understanding might differ from those of their patient partners, and to find ways to use a common language that engages patients and other community partners.

OBJECTIVES: Ambient clinical documentation technology uses automatic speech recognition (ASR) and natural language processing (NLP) to turn patient-clinician conversations into clinical documentation. It is a promising approach to reducing clinician burden and improving documentation quality. However, the performance of current-generation ASR remains inadequately validated. In this study, we investigated the impact of non-lexical conversational sounds (NLCS) on ASR performance. NLCS, such as Mm-hm and Uh-uh, are commonly used to convey important information in clinical conversations, for example, Mm-hm as a yes response from the patient to the clinician question are you allergic to antibiotics? MATERIALS AND METHODS: In this study, we evaluated 2 contemporary ASR engines, Google Speech-to-Text Clinical Conversation (Google ASR), and Amazon Transcribe Medical (Amazon ASR), both of which have their language models specifically tailored to clinical conversations. The empirical data used were from 36 primary care encounters. We conducted a series of quantitative and qualitative analyses to examine the word error rate (WER) and the potential impact of misrecognized NLCS on the quality of clinical documentation. RESULTS: Out of a total of 135 647 spoken words contained in the evaluation data, 3284 (2.4%) were NLCS. Among these NLCS, 76 (0.06% of total words, 2.3% of all NLCS) were used to convey clinically relevant information. The overall WER, of all spoken words, was 11.8% for Google ASR and 12.8% for Amazon ASR. However, both ASR engines demonstrated poor performance in recognizing NLCS: the WERs across frequently used NLCS were 40.8% (Google) and 57.2% (Amazon), respectively; and among the NLCS that conveyed clinically relevant information, 94.7% and 98.7%, respectively. DISCUSSION AND CONCLUSION: Current ASR solutions are not capable of properly recognizing NLCS, particularly those that convey clinically relevant information. Although the volume of NLCS in our evaluation data was very small (2.4% of the total corpus; and for NLCS that conveyed clinically relevant information: 0.06%), incorrect recognition of them could result in inaccuracies in clinical documentation and introduce new patient safety risks.