Faculty Bibliography

BACKGROUND:Remote patient monitoring (RPM) technologies can support patients living with chronic conditions through self-monitoring of physiological measures and enhance clinicians' diagnostic and treatment decisions. However, to date, large-scale pragmatic RPM implementation within health systems has been limited, and understanding of the impacts of RPM technologies on clinical workflows and care experience is lacking. OBJECTIVE:In this study, we evaluate the early implementation of operational RPM initiatives for chronic disease management within the ambulatory network of an academic medical center in New York City, focusing on the experiences of "early adopter" clinicians and patients. METHODS:Using a multimethod qualitative approach, we conducted (1) interviews with 13 clinicians across 9 specialties considered as early adopters and supporters of RPM and (2) speculative design sessions exploring the future of RPM in clinical care with 21 patients and patient representatives, to better understand experiences, preferences, and expectations of pragmatic RPM use for health care delivery. RESULTS:We identified themes relevant to RPM implementation within the following areas: (1) data collection and practices, including impacts of taking real-world measures and issues of data sharing, security, and privacy; (2) proactive and preventive care, including proactive and preventive monitoring, and proactive interventions and support; and (3) health disparities and equity, including tailored and flexible care and implicit bias. We also identified evidence for mitigation and support to address challenges in each of these areas. CONCLUSIONS:This study highlights the unique contexts, perceptions, and challenges regarding the deployment of RPM in clinical practice, including its potential implications for clinical workflows and work experiences. Based on these findings, we offer implementation and design recommendations for health systems interested in deploying RPM-enabled health care.

BACKGROUND:Chatbots are being piloted to draft responses to patient questions, but patients' ability to distinguish between provider and chatbot responses and patients' trust in chatbots' functions are not well established. OBJECTIVE:This study aimed to assess the feasibility of using ChatGPT (Chat Generative Pre-trained Transformer) or a similar artificial intelligence-based chatbot for patient-provider communication. METHODS:A survey study was conducted in January 2023. Ten representative, nonadministrative patient-provider interactions were extracted from the electronic health record. Patients' questions were entered into ChatGPT with a request for the chatbot to respond using approximately the same word count as the human provider's response. In the survey, each patient question was followed by a provider- or ChatGPT-generated response. Participants were informed that 5 responses were provider generated and 5 were chatbot generated. Participants were asked-and incentivized financially-to correctly identify the response source. Participants were also asked about their trust in chatbots' functions in patient-provider communication, using a Likert scale from 1-5. RESULTS:A US-representative sample of 430 study participants aged 18 and older were recruited on Prolific, a crowdsourcing platform for academic studies. In all, 426 participants filled out the full survey. After removing participants who spent less than 3 minutes on the survey, 392 respondents remained. Overall, 53.3% (209/392) of respondents analyzed were women, and the average age was 47.1 (range 18-91) years. The correct classification of responses ranged between 49% (192/392) to 85.7% (336/392) for different questions. On average, chatbot responses were identified correctly in 65.5% (1284/1960) of the cases, and human provider responses were identified correctly in 65.1% (1276/1960) of the cases. On average, responses toward patients' trust in chatbots' functions were weakly positive (mean Likert score 3.4 out of 5), with lower trust as the health-related complexity of the task in the questions increased. CONCLUSIONS:ChatGPT responses to patient questions were weakly distinguishable from provider responses. Laypeople appear to trust the use of chatbots to answer lower-risk health questions. It is important to continue studying patient-chatbot interaction as chatbots move from administrative to more clinical roles in health care.

BACKGROUND:Low medication adherence is a common cause of high blood pressure but is often unrecognized in clinical practice. Electronic data linkages between electronic health records (EHRs) and pharmacies offer the opportunity to identify low medication adherence, which can be used for interventions at the point of care. We developed a multicomponent intervention that uses linked EHR and pharmacy data to automatically identify patients with elevated blood pressure and low medication adherence. The intervention then combines team-based care with EHR-based workflows to address medication nonadherence. OBJECTIVE:This study aims to describe the design of the Leveraging EHR Technology and Team Care to Address Medication Adherence (TEAMLET) trial, which tests the effectiveness of a multicomponent intervention that leverages EHR-based data and team-based care on medication adherence among patients with hypertension. METHODS:TEAMLET is a pragmatic, cluster randomized controlled trial in which 10 primary care practices will be randomized 1:1 to the multicomponent intervention or usual care. We will include all patients with hypertension and low medication adherence who are seen at enrolled practices. The primary outcome is medication adherence, as measured by the proportion of days covered, and the secondary outcome is clinic systolic blood pressure. We will also assess intervention implementation, including adoption, acceptability, fidelity, cost, and sustainability. RESULTS:As of May 2023, we have randomized 10 primary care practices into the study, with 5 practices assigned to each arm of the trial. The enrollment for the study commenced on October 5, 2022, and the trial is currently ongoing. We anticipate patient recruitment to go through the fall of 2023 and the primary outcomes to be assessed in the fall of 2024. CONCLUSIONS:The TEAMLET trial will evaluate the effectiveness of a multicomponent intervention that leverages EHR-based data and team-based care on medication adherence. If successful, the intervention could offer a scalable approach to address inadequate blood pressure control among millions of patients with hypertension. TRIAL REGISTRATION/BACKGROUND:ClinicalTrials.gov NCT05349422; https://clinicaltrials.gov/ct2/show/NCT05349422. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)/UNASSIGNED:DERR1-10.2196/47930.

BACKGROUND:Diabetes mellitus is a common medical complication of pregnancy, and its treatment is complex. Recent years have seen an increase in the application of mobile health tools and advanced technologies, such as remote patient monitoring, with the aim of improving care for diabetes mellitus in pregnancy. Previous studies of these technologies for the treatment of diabetes in pregnancy have been small and have not clearly shown clinical benefit with implementation. OBJECTIVE:Remote patient monitoring allows clinicians to monitor patients' health data (such as glucose values) in near real-time, between office visits, to make timely adjustments to care. Our objective was to determine if using remote patient monitoring for the management of diabetes in pregnancy leads to an improvement in maternal and neonatal outcomes. STUDY DESIGN/METHODS:This was a retrospective cohort study of pregnant patients with diabetes mellitus managed by the maternal-fetal medicine practice at one academic institution between October 2019 and April 2021. This practice transitioned from paper-based blood glucose logs to remote patient monitoring in February 2020. Remote patient monitoring options included (1) device integration with Bluetooth glucometers that automatically uploaded measured glucose values to the patient's Epic MyChart application or (2) manual entry in which patients manually logged their glucose readings into their MyChart application. Values in the MyChart application directly transferred to the patient's electronic health record for review and management by clinicians. In total, 533 patients were studied. We compared 173 patients managed with paper logs to 360 patients managed with remote patient monitoring (176 device integration and 184 manual entry). Our primary outcomes were composite maternal morbidity (which included third- and fourth-degree lacerations, chorioamnionitis, postpartum hemorrhage requiring transfusion, postpartum hysterectomy, wound infection or separation, venous thromboembolism, and maternal admission to the intensive care unit) and composite neonatal morbidity (which included umbilical cord pH <7.00, 5 minute Apgar score <7, respiratory morbidity, hyperbilirubinemia, meconium aspiration, intraventricular hemorrhage, necrotizing enterocolitis, sepsis, pneumonia, seizures, hypoxic ischemic encephalopathy, shoulder dystocia, trauma, brain or body cooling, and neonatal intensive care unit admission). Secondary outcomes were measures of glycemic control and the individual components of the primary composite outcomes. We also performed a secondary analysis in which the patients who used the two different remote patient monitoring options (device integration vs manual entry) were compared. Chi-square, Fisher's exact, 2-sample t, and Mann-Whitney tests were used to compare the groups. A result was considered statistically significant at P<.05. RESULTS:Maternal baseline characteristics were not significantly different between the remote patient monitoring and paper groups aside from a slightly higher baseline rate of chronic hypertension in the remote patient monitoring group (6.1% vs 1.2%; P=.011). The primary outcomes of composite maternal and composite neonatal morbidity were not significantly different between the groups. However, remote patient monitoring patients submitted more glucose values (177 vs 146; P=.008), were more likely to achieve glycemic control in target range (79.2% vs 52.0%; P<.0001), and achieved the target range sooner (median, 3.3 vs 4.1 weeks; P=.025) than patients managed with paper logs. This was achieved without increasing in-person visits. Remote patient monitoring patients had lower rates of preeclampsia (5.8% vs 15.0%; P=.0006) and their infants had lower rates of neonatal hypoglycemia in the first 24 hours of life (29.8% vs 51.7%; P<.0001). CONCLUSION/CONCLUSIONS:Remote patient monitoring for the management of diabetes mellitus in pregnancy is superior to a traditional paper-based approach in achieving glycemic control and is associated with improved maternal and neonatal outcomes.

BACKGROUND:The improvements in care resulting from clinical decision support (CDS) have been significantly limited by consistently low health care provider adoption. Health care provider attitudes toward CDS, specifically psychological and behavioral barriers, are not typically addressed during any stage of CDS development, although they represent an important barrier to adoption. Emerging evidence has shown the surprising power of using insights from the field of behavioral economics to address psychological and behavioral barriers. Nudges are formal applications of behavioral economics, defined as positive reinforcement and indirect suggestions that have a nonforced effect on decision-making. OBJECTIVE:Our goal is to employ a user-centered design process to develop a CDS tool-the pulmonary embolism (PE) risk calculator-for PE risk stratification in the emergency department that incorporates a behavior theory-informed nudge to address identified behavioral barriers to use. METHODS:All study activities took place at a large academic health system in the New York City metropolitan area. Our study used a user-centered and behavior theory-based approach to achieve the following two aims: (1) use mixed methods to identify health care provider barriers to the use of an active CDS tool for PE risk stratification and (2) develop a new CDS tool-the PE risk calculator-that addresses behavioral barriers to health care providers' adoption of CDS by incorporating nudges into the user interface. These aims were guided by the revised Observational Research Behavioral Information Technology model. A total of 50 clinicians who used the original version of the tool were surveyed with a quantitative instrument that we developed based on a behavior theory framework-the Capability-Opportunity-Motivation-Behavior framework. A semistructured interview guide was developed based on the survey responses. Inductive methods were used to analyze interview session notes and audio recordings from 12 interviews. Revised versions of the tool were developed that incorporated nudges. RESULTS:Functional prototypes were developed by using Axure PRO (Axure Software Solutions) software and usability tested with end users in an iterative agile process (n=10). The tool was redesigned to address 4 identified major barriers to tool use; we included 2 nudges and a default. The 6-month pilot trial for the tool was launched on October 1, 2021. CONCLUSIONS:Clinicians highlighted several important psychological and behavioral barriers to CDS use. Addressing these barriers, along with conducting traditional usability testing, facilitated the development of a tool with greater potential to transform clinical care. The tool will be tested in a prospective pilot trial. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)/UNASSIGNED:DERR1-10.2196/42653.

BACKGROUND:Patient-reported outcomes (PROs) capture patients' views on their health conditions and its management, and are increasingly used in clinical trials, including those targeting type 2 diabetes (T2D). Mobile health (mHealth) tools offer novel solutions for collecting PRO data in real time. Although patients are at the center of any PRO-based intervention, few studies have examined user engagement with PRO mHealth tools. OBJECTIVE:This study aimed to evaluate user engagement with a PRO mHealth tool for T2D management, identify patterns of user engagement and similarities and differences between the patients, and identify the characteristics of patients who are likely to drop out or be less engaged with a PRO mHealth tool. METHODS:We extracted user engagement data from an ongoing clinical trial that tested the efficacy of a PRO mHealth tool designed to improve hemoglobin A1c levels in patients with uncontrolled T2D. To date, 61 patients have been randomized to the intervention, where they are sent 6 PRO text messages a day that are relevant to T2D self-management (healthy eating and medication adherence) over the 12-month study. To analyze user engagement, we first compared the response rate (RR) and response time between patients who completed the 12-month intervention and those who dropped out early (noncompleters). Next, we leveraged latent class trajectory modeling to classify patients from the completer group into 3 subgroups based on similarity in the longitudinal engagement data. Finally, we investigated the differences between the subgroups of completers from various cross-sections (time of the day and day of the week) and PRO types. We also explored the patient demographics and their distribution among the subgroups. RESULTS:Overall, 19 noncompleters had a lower RR to PRO questions and took longer to respond to PRO questions than 42 completers. Among completers, the longitudinal RRs demonstrated differences in engagement patterns over time. The completers with the lowest engagement showed peak engagement during month 5, almost at the midstage of the program. The remaining subgroups showed peak engagement at the beginning of the intervention, followed by either a steady decline or sustained high engagement. Comparisons of the demographic characteristics showed significant differences between the high engaged and low engaged subgroups. The high engaged completers were predominantly older, of Hispanic descent, bilingual, and had a graduate degree. In comparison, the low engaged subgroup was composed mostly of African American patients who reported the lowest annual income, with one of every 3 patients earning less than US $20,000 annually. CONCLUSIONS:There are discernible engagement phenotypes based on individual PRO responses, and their patterns vary in the timing of peak engagement and demographics. Future studies could use these findings to predict engagement categories and tailor interventions to promote longitudinal engagement. TRIAL REGISTRATION/BACKGROUND:Clinicaltrials.gov NCT03652389; https://clinicaltrials.gov/ct2/show/NCT03652389. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)/UNASSIGNED:RR2-10.2196/18554.