Characterizing Patient-Clinician Communication in Secure Medical Messages: Retrospective Study

Automatic uncovering of patient primary concerns in portal messages using a fusion framework of pretrained language models

OBJECTIVES

The surge in patient portal messages (PPMs) with increasing needs and workloads for efficient PPM triage in healthcare settings has spurred the exploration of AI-driven solutions to streamline the healthcare workflow processes, ensuring timely responses to patients to satisfy their healthcare needs. However, there has been less focus on isolating and understanding patient primary concerns in PPMs-a practice which holds the potential to yield more nuanced insights and enhances the quality of healthcare delivery and patient-centered care.

MATERIALS AND METHODS

We propose a fusion framework to leverage pretrained language models (LMs) with different language advantages via a Convolution Neural Network for precise identification of patient primary concerns via multi-class classification. We examined 3 traditional machine learning models, 9 BERT-based language models, 6 fusion models, and 2 ensemble models.

RESULTS

The outcomes of our experimentation underscore the superior performance achieved by BERT-based models in comparison to traditional machine learning models. Remarkably, our fusion model emerges as the top-performing solution, delivering a notably improved accuracy score of 77.67 ± 2.74% and an F1 score of 74.37 ± 3.70% in macro-average.

DISCUSSION

This study highlights the feasibility and effectiveness of multi-class classification for patient primary concern detection and the proposed fusion framework for enhancing primary concern detection.

CONCLUSIONS

The use of multi-class classification enhanced by a fusion of multiple pretrained LMs not only improves the accuracy and efficiency of patient primary concern identification in PPMs but also aids in managing the rising volume of PPMs in healthcare, ensuring critical patient communications are addressed promptly and accurately.

Using large language model to guide patients to create efficient and comprehensive clinical care message

OBJECTIVE

This study aims to investigate the feasibility of using Large Language Models (LLMs) to engage with patients at the time they are drafting a question to their healthcare providers, and generate pertinent follow-up questions that the patient can answer before sending their message, with the goal of ensuring that their healthcare provider receives all the information they need to safely and accurately answer the patient's question, eliminating back-and-forth messaging, and the associated delays and frustrations.

METHODS

We collected a dataset of patient messages sent between January 1, 2022 to March 7, 2023 at Vanderbilt University Medical Center. Two internal medicine physicians identified 7 common scenarios. We used 3 LLMs to generate follow-up questions: (1) Comprehensive LLM Artificial Intelligence Responder (CLAIR): a locally fine-tuned LLM, (2) GPT4 with a simple prompt, and (3) GPT4 with a complex prompt. Five physicians rated them with the actual follow-ups written by healthcare providers on clarity, completeness, conciseness, and utility.

RESULTS

For five scenarios, our CLAIR model had the best performance. The GPT4 model received higher scores for utility and completeness but lower scores for clarity and conciseness. CLAIR generated follow-up questions with similar clarity and conciseness as the actual follow-ups written by healthcare providers, with higher utility than healthcare providers and GPT4, and lower completeness than GPT4, but better than healthcare providers.

CONCLUSION

LLMs can generate follow-up patient messages designed to clarify a medical question that compares favorably to those generated by healthcare providers.

Use of the patient portal among older adults with diagnosed dementia and their care partners

INTRODUCTION

Care partners are at the forefront of dementia care, yet little is known about patient portal use in the context of dementia diagnosis.

METHODS

We conducted an observational cohort study of date/time-stamped patient portal use for a 5-year period (October 3, 2017-October 2, 2022) at an academic health system. The cohort consisted of 3170 patients ages 65+ with diagnosed dementia with 2+ visits within 24 months. Message authorship was determined by manual review of 970 threads involving 3065 messages for 279 patients.

RESULTS

Most (71.20%) older adults with diagnosed dementia were registered portal users but far fewer (10.41%) had a registered care partner with shared access. Care partners authored most (612/970, 63.09%) message threads, overwhelmingly using patient identity credentials (271/279, 97.13%).

DISCUSSION

The patient portal is used by persons with dementia and their care partners. Organizational efforts that facilitate shared access may benefit the support of persons with dementia and their care partners. Highlights Patient portal registration and use has been increasing among persons with diagnosed dementia. Two thirds of secure messages from portal accounts of patients with diagnosed dementia were identified as being authored by care partners, primarily using patient login credentials. Care partners who accessed the patient portal using their own identity credentials through shared access demonstrate similar levels of activity to patients without dementia. Organizational initiatives should recognize and support the needs of persons with dementia and their care partners by encouraging awareness, registration, and use of proper identity credentials, including shared, or proxy, portal access.

Ways to Improve Workflow and Morale in an Ophthalmology Clinic: Survey Advice from Clinic Staff

Objective

We aim to improve job workflow and satisfaction amongst clinic staff at an academic ophthalmology department.

Methods

We analyzed survey data given over a 2-week period in July 2021. The participants were support staff (N = 18) from an academic ophthalmology department. Paper surveys were distributed to participants and returned anonymously for analysis. Results: The survey contained 9 Likert-style categorical questions, 2 of which were free response options. A total of 22 participants attempted the survey, 18 of these (82%) were complete and included in analysis. About half of the staff were satisfied with the current workflow 10/18 (56%). Staff who were clinical care coordinators had the lowest average satisfaction (2/5 on a 5-point scale) and the nursing team had the highest average (4.75/5). The most common staff suggestion for improving workflow efficiency was to train residents on forwarding and answering messages more effectively.

Conclusion

This survey suggests that assigning patient message processing to the nursing staff can improve job satisfaction and workflow. Staff told us that the most exciting part of the job was appreciation from coworkers 9/30 (30%) and from physicians 8/30 (27%). The findings provide advice to physicians for optimizing communication, and staff experience, within their own ophthalmology clinics.

Patient portal interventions: a scoping review of functionality, automation used, and therapeutic elements of patient portal interventions

Objectives

We sought to understand the objectives, targeted populations, therapeutic elements, and delivery characteristics of patient portal interventions.

Materials and Methods

Following Arksey and O-Malley's methodological framework, we conducted a scoping review of manuscripts published through June 2022 by hand and systematically searching PubMed, PSYCHInfo, Embase, and Web of Science. The search yielded 5403 manuscripts; 248 were selected for full-text review; 81 met the eligibility criteria for examining outcomes of a patient portal intervention.

Results

The 81 articles described: trials involving comparison groups (n = 37; 45.7%), quality improvement initiatives (n = 15; 18.5%), pilot studies (n = 7; 8.6%), and single-arm studies (n = 22; 27.2%). Studies were conducted in primary care (n = 33, 40.7%), specialty outpatient (n = 24, 29.6%), or inpatient settings (n = 4, 4.9%)-or they were deployed system wide (n = 9, 11.1%). Interventions targeted specific health conditions (n = 35, 43.2%), promoted preventive services (n = 19, 23.5%), or addressed communication (n = 19, 23.4%); few specifically sought to improve the patient experience (n = 3, 3.7%). About half of the studies (n = 40, 49.4%) relied on human involvement, and about half involved personalized (vs exclusively standardized) elements (n = 42, 51.8%). Interventions commonly collected patient-reported information (n = 36, 44.4%), provided education (n = 35, 43.2%), or deployed preventive service reminders (n = 14, 17.3%).

Discussion

This scoping review finds that most patient portal interventions have delivered education or facilitated collection of patient-reported information. Few interventions have involved pragmatic designs or been deployed system wide.

Conclusion

The patient portal is an important tool in real-world efforts to more effectively support patients, but interventions to date rely largely on evidence from consented participants rather than pragmatically implemented systems-level initiatives.

MediLinker: a blockchain-based decentralized health information management platform for patient-centric healthcare

Patients' control over how their health information is stored has been an ongoing issue in health informatics. Currently, most patients' health information is stored in centralized but siloed health information systems of healthcare institutions, rarely connected to or interoperable with other institutions outside of their specific health system. This centralized approach to the storage of health information is susceptible to breaches, though it can be mitigated using technology that allows for decentralized access. One promising technology that offers the possibility of decentralization, data protection, and interoperability is blockchain. In 2019, our interdisciplinary team from the University of Texas at Austin's Dell Medical School, School of Information, Department of Electrical and Computer Engineering, and Information Technology Services developed MediLinker-a blockchain-based decentralized health information management platform for patient-centric healthcare. This paper provides an overview of MediLinker and outlines its ongoing and future development and implementation. Overall, this paper contributes insights into the opportunities and challenges in developing and implementing blockchain-based technologies in healthcare.

Patient Trust in Physicians Matters-Understanding the Role of a Mobile Patient Education System and Patient-Physician Communication in Improving Patient Adherence Behavior: Field Study

BACKGROUND

The ultimate goal of any prescribed medical therapy is to achieve desired outcomes of patient care. However, patient nonadherence has long been a major problem detrimental to patient health and, thus, is a concern for all health care providers. Moreover, nonadherence is extremely costly for global medical systems because of unnecessary complications and expenses. Traditional patient education programs often serve as an intervention tool to increase patients' self-care awareness, disease knowledge, and motivation to change patient behaviors for better adherence. Patient trust in physicians, patient-physician relationships, and quality of communication have also been identified as critical factors influencing patient adherence. However, little is known about how mobile patient education technologies help foster patient adherence.

OBJECTIVE

This study aimed to empirically investigate whether and how a mobile patient education system (MPES) juxtaposed with patient trust can increase patient adherence to prescribed medical therapies.

METHODS

This study was conducted based on a field survey of 125 patients in multiple states in the United States who have used an innovative mobile health care system for their health care education and information seeking. Partial least squares techniques were used to analyze the collected data.

RESULTS

The results revealed that patient-physician communication and the use of an MPES significantly increase patients' trust in their physicians. Furthermore, patient trust has a prominent effect on patient attitude toward treatment adherence, which in turn influences patients' behavioral intention and actual adherence behavior. Based on the theory of planned behavior, the results also indicated that behavioral intention, response efficacy, and self-efficacy positively influenced patients' actual treatment adherence behavior, whereas descriptive norms and subjective norms do not play a role in this process.

CONCLUSIONS

Our study is one of the first that examines the relationship between patients who actively use an MPES and their trust in their physicians. This study contributes to this context by enriching the trust literature, addressing the call to identify key patient-centered technology determinants of trust, advancing the understanding of patient adherence mechanisms, adding a new explanation of the influence of education mechanisms delivered via mobile devices on patient adherence, and confirming that the theory of planned behavior holds in this patient adherence context.

Midwest rural-urban disparities in use of patient online services for COVID-19

PURPOSE

Rural populations are disproportionately affected by the COVID-19 pandemic. We characterized urban-rural disparities in patient portal messaging utilization for COVID-19, and, of those who used the portal during its early stage in the Midwest.

METHODS

We collected over 1 million portal messages generated by midwestern Mayo Clinic patients from February to August 2020. We analyzed patient-generated messages (PGMs) on COVID-19 by urban-rural locality and incorporated patients' sociodemographic factors into the analysis.

FINDINGS

The urban-rural ratio of portal users, message senders, and COVID-19 message senders was 1.18, 1.31, and 1.79, indicating greater use among urban patients. The urban-rural ratio (1.69) of PGMs on COVID-19 was higher than that (1.43) of general PGMs. The urban-rural ratios of messaging were 1.72-1.85 for COVID-19-related care and 1.43-1.66 for other health care issues on COVID-19. Compared with urban patients, rural patients sent fewer messages for COVID-19 diagnosis and treatment but more messages for other reasons related to COVID-19-related health care (eg, isolation and anxiety). The frequent senders of COVID-19-related messages among rural patients were 40+ years old, women, married, and White.

CONCLUSIONS

In this Midwest health system, rural patients were less likely to use patient online services during a pandemic and their reasons for its use differ from urban patients. Results suggest opportunities for increasing equity in rural patient engagement in patient portals (in particular, minority populations) for COVID-19. Public health intervention strategies could target reasons why rural patients might seek health care in a pandemic, such as social isolation and anxiety.

Patient Portal Messaging for Asynchronous Virtual Care During the COVID-19 Pandemic: Retrospective Analysis

BACKGROUND

During the COVID-19 pandemic, patient portals and their message platforms allowed remote access to health care. Utilization patterns in patient messaging during the COVID-19 crisis have not been studied thoroughly. In this work, we propose characterizing patients and their use of asynchronous virtual care for COVID-19 via a retrospective analysis of patient portal messages.

OBJECTIVE

This study aimed to perform a retrospective analysis of portal messages to probe asynchronous patient responses to the COVID-19 crisis.

METHODS

We collected over 2 million patient-generated messages (PGMs) at Mayo Clinic during February 1 to August 31, 2020. We analyzed descriptive statistics on PGMs related to COVID-19 and incorporated patients' sociodemographic factors into the analysis. We analyzed the PGMs on COVID-19 in terms of COVID-19-related care (eg, COVID-19 symptom self-assessment and COVID-19 tests and results) and other health issues (eg, appointment cancellation, anxiety, and depression).

RESULTS

The majority of PGMs on COVID-19 pertained to COVID-19 symptom self-assessment (42.50%) and COVID-19 tests and results (30.84%). The PGMs related to COVID-19 symptom self-assessment and COVID-19 test results had dynamic patterns and peaks similar to the newly confirmed cases in the United States and in Minnesota. The trend of PGMs related to COVID-19 care plans paralleled trends in newly hospitalized cases and deaths. After an initial peak in March, the PGMs on issues such as appointment cancellations and anxiety regarding COVID-19 displayed a declining trend. The majority of message senders were 30-64 years old, married, female, White, or urban residents. This majority was an even higher proportion among patients who sent portal messages on COVID-19.

CONCLUSIONS

During the COVID-19 pandemic, patients increased portal messaging utilization to address health care issues about COVID-19 (in particular, symptom self-assessment and tests and results). Trends in message usage closely followed national trends in new cases and hospitalizations. There is a wide disparity for minority and rural populations in the use of PGMs for addressing the COVID-19 crisis.