key: cord-0755275-k9cwgpio authors: Ford, Dee; Harvey, Jillian B; McElligott, James; King, Kathryn; Simpson, Kit N; Valenta, Shawn; Warr, Emily H; Walsh, Tasia; Debenham, Ellen; Teasdale, Carla; Meystre, Stephane; Obeid, Jihad S; Lenert, Leslie A title: Leveraging Health System Telehealth and Informatics Infrastructure to Create a Continuum of Services for COVID-19 Screening, Testing, and Treatment date: 2020-06-30 journal: J Am Med Inform Assoc DOI: 10.1093/jamia/ocaa157 sha: 94023963699f57a564f75dc22f4bdcc69cfa527a doc_id: 755275 cord_uid: k9cwgpio BACKGROUND: COVID-19 challenges and needs required health systems to rapidly redesign the delivery of care. OBJECTIVE: To describe our approach in using health information technology to provide a continuum of services during the COVID-19 pandemic. MATERIALS AND METHODS: Our health system deployed four COVID-19 telehealth programs, and four biomedical informatics innovations to screen and care for COVID-19 patients. Using programmatic and electronic health record data we describe the implementation and initial utilization. RESULTS: Through collaboration across multi-disciplinary teams and strategic planning, four telehealth program initiatives have been deployed in response to COVID-19: virtual urgent care screening, remote patient monitoring for COVID-19 positive patients, continuous virtual monitoring to reduce workforce risk and utilization of personal protective equipment, and the transition of outpatient care to telehealth. Biomedical Informatics was integral to our institutional response in supporting clinical care through new and reconfigured technologies. Through linking the telehealth systems and the electronic health record, we have the ability to monitor and track patients through a continuum of COVID-19 services. DISCUSSION: COVID-19 has facilitated the rapid expansion and utilization of telehealth and health informatics services. We anticipate that patients and providers will view enhanced telehealth services as an essential aspect of the healthcare system. Continuation of telehealth payment models at federal and private levels will be a key factor in whether this new uptake is sustained. CONCLUSION: There are substantial benefits in utilizing telehealth during the COVID-19, including the ability to rapidly scale the number of patients being screened and providing continuity of care. The World Health Organization declared COVID-19 a global pandemic on March 11, 2020. [1] To ensure safety and meet patient needs, health systems adjusted care processes and deployed new approaches to screen and care for COVID patients, and continue to meet routine care needs. [2] On March 17, 2020 telehealth benefits were expanded for Medicare patients, these regulatory and reimbursement mechanisms allowed healthcare organizations to support the conversion of ambulatory clinic visits to telehealth platforms. [3] The Medical University of South Carolina (MUSC), like many healthcare institutions, experienced a dramatic reduction in ambulatory operations following government social distancing guidelines and increased demand for COVID-19 screening and testing. As one of two federally recognized telehealth Centers of Excellence, [4] MUSC integrated and deployed telehealth into multiple facets of our institutional response to COVID-19. We deployed four COVID-19 telehealth programs, and four biomedical informatics innovations during the initial weeks of the pandemic. The purpose of this study is to describe our approach to using health information technology to provide a continuum of services for COVID-19. We describe our processes, utilization, and lessons learned in using telehealth for screening and testing, reducing healthcare worker exposure, and transforming outpatient to virtual/telehealth care. Study Site. MUSC began its first telehealth programs in 2005 as a strategy to mitigate health disparities experienced by many South Carolinians. [5] [6] [7] Finally, we applied artificial intelligence expertise to data coming from MUSC's virtual urgent care platform (Zipnosis) which, while rich in clinical information, was locked in the "free text" record. Our researchers developed natural language processing tools to extract symptoms, risk factors, and medication treatments from notes to add to the COVID-19 registry. A team applied deep-learning neural networks (DNN) to notes and developed models to predict which patients would eventually have positive SARS-CoV-2 results. DNN algorithms offered substantial improvements over the rule-based algorithms and subsequently were used to prioritize scheduling of testing. [9] Data. Our telehealth and information solutions systems were assessed for functionality and readiness to serve as data collection and monitoring systems along two dimensions: 1) patient-centered clinical service delivery; and 2) management and research data collection capability. Our telehealth tracking, reporting and service management systems and their linkages with our EHR system were assessed and new measures and codes were added to ensure that SARS COV-2 tests would be captured for rapid reporting, and that telehealth process and delivery changes implemented were logged in "real time". We include COVID-19 related virtual visits, testing referrals, lab orders, positive tests, in-patient and remote home monitoring interactions, and ambulatory telehealth visits that occurred between March 7, 2020 and April 22, 2020. To calculate the relationship between the telehealth workforce risk-reduction service and personal protective equipment (PPE) cost savings, we utilize a micro-costing approach using standard cost weights representative of US national costs and prices in April 2020. Screening: COVID-19 and Virtual Urgent Care. We re-designed our existing virtual urgent care (VUC) with the overall goal of keeping patients with symptoms away from typical healthcare access points such as clinics, urgent care settings, and emergency departments in order to reduce risk. VUC traditionally provides rapid access to care for low-risk clinical conditions (e.g. urinary tract infections) among low risk patient populations. Our VUC program, established in 2015, is supported by a team of emergency department based advanced practice providers (APPs). Zipnosis is our technical platform since it provides both asynchronous (i.e. adaptive interview, chat) and synchronous (i.e. video, phone) capabilities. VUC served as a portal of entry into our EHR as the system creates a record for all new patients, allowing for test ordering, resulting, communication to the patient, population of the COVID-19 registry, and continuity with the remote patient monitoring program. Re-engineering VUC to support screening for COVID-19 required numerous changes. We created and trained an emergency staffing pool of APPs from across the health system as anticipated volumes would overwhelm the established VUC APP pool. This included privileging, credentialing, completing scope of practice agreements, finalizing a payment model, and receiving approval on a provider compensation mechanism through both our university and practice plan entities who employ the APPs. After a call to action on March 6, 2020, we trained over 100 APPs in less than two weeks. Next, we removed historical VUC restrictions based on age, comorbid conditions, and presence of dyspnea from the COVID-19 screener. Given the high risk nature of COVID-19, we implemented a quality assurance program to review patient care decisions in real time, communicate information and clarifications with patients and improve overall processes as well as developing screening pathways for Spanishspeaking patients, vulnerable populations (e.g. homeless shelters), and patients without internet access (i.e. phone screenings). Between March 7, 2020 and April 22, 2020, 67,577 patients completed a VUC visit, of those 14,924 met the criteria for COVID-19 testing. The availability of a COVID-19 virtual evaluation was promoted through institutional communications, local media, and state officials as a public health tool for South Carolina citizens to receive a no charge virtual screening. Figure 1 provides the continuum of our COVID-19 care processes and patient volumes associated with each phase. Institutional drive-through respiratory specimen collection sites were established at locations throughout the state. Further optimization enabled patients who qualified for testing to immediately receive a "ticket" allowing them to select a testing facility and self-schedule their test through our EHR patient portal. Via drive-through testing and outpatient labs 10,501 patients were tested, an additional 2,420 tests were performed among inpatients. Treatment: Outpatients with COVID-19 and remote patient monitoring. We have substantial institutional experience with remote patient monitoring (RPM) for a variety of patient conditions including diabetes, hypertension, mental health, asthma, and pediatric burns to name a few. [10] [11] [12] [13] [14] [15] [16] As part of our COVID-19 response, we developed an RPM program for outpatients with COVID-19. The foundation of our COVID-19 RPM program is a parsimonious set of patientreported outcomes (PROs) derived from a validated community acquired pneumonia patient questionnaire. [17] This five-item survey closely queries changes in patient reported dyspnea and is thus highly relevant to COVID-19, in which the most common cause of morbidity and mortality is progressive respiratory failure. [18] This simple and feasible PRO became the foundation for monitoring the vast majority of COVID-19 patients who have mild to moderate symptoms. [18] We also identified blue tooth enabled home pulse oximeters that met requisite technical, security, and usability requirements. We created a risk stratification tool based on underlying patient conditions and offer home pulse oximetry to select sub-groups: high risk for COVID-19 complications, post-hospitalization receiving oxygen therapy at home, and postemergency department evaluation without hospitalization. Finally, a number of patients invited to participate in the RPM program already had thermometers and home pulse oximeters and so we added patient reported biometric data into the PRO tool. From an operational standpoint, patients may complete the PRO tool via their MyChart account or via the smart phone app developed by BMIC. Patients enrolling in the app-based RPM program were provided with a two-dimensional secure barcode that linked information entered into the app with their Epic accounts. Reminders to complete the PRO tool were pushed to the patient daily and there was no limit on number of PRO tool completions per patient per day. Therefore, if symptoms worsen, patients could enter an updated PRO survey and the RPM nursing staff will reach out via phone. Among the 182 patients that opted not to enroll in the program, the most common reason was that they were feeling better but were appreciative of the resource offering. The process of implementing large scale conversion of in-person visits to telehealth visits began in mid-March. The scope of the initiative was the conversion of in-person visits to synchronous video visits when appropriate. To initiate the telehealth conversion, a task force was constructed with governance representation from ambulatory care administration, clinical informatics and telehealth. Subcommittees were formed to focus on provider and patient education, billing and compliance, and platform implementation. Physician leaders were identified in each clinical division and a through a series of webinars were able to coach their peers to enhance adoption. Initially implementation was focused on the processes and capabilities available through the existing video platform embedded within our patient portal. As implementation progressed through the ambulatory divisions, limitations related to the existing video platform for large academic healthcare settings were quickly encountered. For some providers, the video platform embedded in the patient portal, was well adopted, other clinics identified constraints within the platform to https://mc.manuscriptcentral.com/jamia support common academic processes (i.e. visitation and review from both resident and attending). Additional system limitations were noted around ease of use, and technical and bandwidth accessibility when used at scale. To improve the system capabilities and technical barriers identified, a second, independent video platform, was deployed (Doxy.me). The second platform already had an institutional instance on campus, moreover the platform had capabilities to support security requirements, clinical academic processes, ease of use, and had reliable technical capabilities. [21] Infrastructure was then implemented to establish common workflows, patient and provider education, a standardized staffing support model and adaptation of the EHR visit types to facilitate routing for billing. While providers were encouraged to use the newer platform, those who preferred to stay within the initial video platform were supported and the processes and EHR were developed to support both systems. A variety of approaches were used to educate patients. First, the video platform was converted to a web-based platform which included built-in patient education features. Individual clinics onboarded patient education scripting, and clinic support staff prepped patients in advance of the visit. Technology checks were used by a minority of clinics. One barrier was that the patients do not have the ability to test their own connection in the video portal. By the 30-day mark, clinic volumes for the enterprise were at 69% of the prepandemic levels, with 67% of the volume obtained through virtual care. Many departments had achieved 80% of pre-pandemic levels. Some departments such as psychiatry and primary care were exceeding their pre-pandemic clinical volumes. The interdisciplinary teams continue the collaboration in the growth and integration of the telehealth video platforms within the ambulatory setting at MUSC. In addition, medical students were brought on to assist with ambulatory video visits for Departments who made specific requests that included an educational experience. This included assisting with patient education and the ambulatory video visit workflow. As the pandemic continues, a transition from rapid acceleration towards data-driven optimization is underway and includes identifying low uptake divisions and overcoming barriers, reengineering patient communication and scheduling, and strategizing approaches to blend in-person and video visit clinic panels. We maintain a dashboard of video to telephone conversion rates and at peak use 68% of all visits were done virtually, of those 10-15% are audio calls. Loss interactions is monitored as the rate of scheduled visits that are completed. From this metric, visit loss is less than 7%, which compares favorably to in-person baseline. Health systems are attempting to find rapid responses to manage COVID-19 needs using telehealth and informatics [22] [23] [24] [25] . While many video or telephone only platforms struggled with the sudden spike in volume of visits, we were well positioned to serve our state's population. Within a short timeframe, we leveraged the health system's existing telehealth and informatics infrastructure to deploy a continuum of services for the COVID-19 screening and treatment, which provides a unique combination of services across care settings. The asynchronous functionality was crucial during the initial wave of virtual urgent care screenings for COVID-19 due to very high patient volumes during which it would have been impossible to accommodate through video or chat functions. The need for a quality assurance team also emerged quickly as an essential resource to oversee the program from a safety perspective. Additionally, this team was able to quickly pivot with regards to referral for testing as our local testing capacity expanded and recommendations for which patients should be tested changed accordingly. The health system, like many around the world, established and is expanding walk-up and drive-through testing sites and by using virtual urgent care as a common portal of entry, the system was able to streamline access. Finally, one important benefit of establishing a COVID-19 EHR registry derived from the initial virtual urgent visit was that a continuum of care was enabled such that patient test results could be quickly viewed, and the patient contacted with their status. Collaboration between telehealth and biomedical informatics led to the adoption of RPM services to support COVID-19 patients that were well enough to remain at home. From a public health perspective, keeping patients at home helps preserve valuable medical resources for more severely ill patients, reduces well population exposures and enhances the effectiveness of social distancing interventions. From a patient perspective, the RPM keeps patients connected to care, monitors for potential clinical decline, provides education and emotional support, and enables both video evaluation and/or safe referral for in-person evaluation when clinical status warrants. Our goal is to offer this supportive resource to patient's within and external to our health system. This has required identifying patient primary care providers for RPM nurse backup when patient issues warrant escalation to a physician as well as deploying a team of primary care physicians when patients do not have one. Additionally, our biomedical informatics team has encountered substantial barriers with regards to deploying our app-based tool, primarily related to the companies that host these resources. Overall the program has been extremely well received by patients, many of whom are understandably anxious about their diagnosis. Another benefit of both the registry and the RPM program has been a ready pool of volunteers for our health system's convalescent plasma program and other emerging research opportunities. Perhaps the greatest impact of our COVID-19 portfolio of programs has been the ability to conserve PPE during a time when the resources are scarce and healthcare systems are experiencing significant price gouging. [19] Through adaptation of the existing CVM equipment, patients and healthcare workers were able to have two-way conversations in non-emergency situations and thereby reduce the number of times employees had to enter the patient rooms. These benefits extended to bedside staff, consulting physician teams, and the treating physician team. For the sub-set of critically ill COVID-19 patients, staff were able to use the technology to have continuously open lines of communication between the fully donned bedside provider and staff outside. This enabled better overall resource management. An unintended consequence of deploying this system was the inevitable mission creep in which clinicians sought to deploy the technology for reasons other than the pre-specified use case of reducing healthcare worker COVID-19 exposure. By developing a clear strategy and related goals, we largely eliminated mission creep concerns. During a time of social distancing, we transformed ambulatory care delivery to achieve 69% of pre-COVID levels. This finding is similar to other systems that have rapidly transitioned in-person ambulatory visits to video visits. [22, 23] Yet these results remain rare, national trends show the number of visits to ambulatory practices declined by nearly 60% over this same time period, and telehealth services have not been able to fully displace in-person care. [2] We anticipate that our efforts transitioning large swaths of our in-person ambulatory visits to video visits will ultimately be the most enduring aspect of the telehealth implementations to date. While we have experienced the typical challenges around technology and scheduling, uptake has nonetheless been brisk. Finally, strategies to include patient populations without ready access to video conferencing technologies remains an important barrier without a clear solution. Although the utilization of telehealth to improve access to care is often touted in the literature, the adoption has remained slow, with only 8% of Americans reporting to have participated in a video visit. [22, 24] . COVID-19 has led to rapid growth in telehealth utilization and adoption by new providers [26] . The expansion of telehealth reimbursement options at federal and private levels will be key determinant in whether this new uptake is sustained. This study has several limitations. First the reporting of COVID-19 measures are not standardized [27] , therefore, our definitions may differ from others conducting similar work. Second, the real-time nature of the data reporting has the potential to undercount or miscategorize information. However, we utilized trained informaticists to export and clean the data to minimize risk. Finally, this study describes the experiences and early results from one health system. It is possible the results are not generalizable to others. Yet, we suggest other health systems have the opportunity to learn from our experiences to inform their own work. COVID-19 has led to rapid expansion and utilization of telehealth and health informatics services. We found substantial benefits in utilizing telehealth during the COVID-19 pandemic, including the ability to rapidly scale the number of patients being screened, providing continuity of care during times of social distancing, and the ability to monitor and track patients through linking telehealth systems to the EHR. World Health Organization. WHO Director-General's Opening Remarks at media briefing on COVID-19 -11March 2020 What impact has COVID-19 had on outpatient visits. The Commonwealth Fund 2020 President Trump expands telehealth benefits for Medicare beneficiaries REACH MUSC: A telemedicine facilitated network for stroke: Initial operational experience Development and evolution of a statewide outpatient consultation service: Leveraging telemedicine to improve access to specialty care Adapting ITIL for effective telehealth service management. Presentation at the 2019 Health Information Management Systems Society Global Conference An AI approach to COVID-19 infection risk assessment in virtual visits: a case report Mobile devices for the remote acquisition of physiological and behavioral biomarkers in psychiatric clinical research Impact of a Culturally Tailored mHealth Medication Regimen Self-Management Program upon Blood Pressure among Hypertensive Hispanic Adults Pilot Randomized Trial of a Self-Help Behavioral Activation Mobile Application for Utilization in Primary Care Randomized controlled trial of technology-assisted case management in low income adults with Type 2 Diabetes AP Expert outpatient burn care in the home through mobile health technology Treatment satisfaction of home-based telehealth versus in-person delivery of prolonged exposure for combat-related PTSD in veterans Feasibility of Real-time Smartphone Asthma Monitoring for High Risk Children The communityacquired pneumonia symptom questionnaire: a new, patient-based outcome measure to evaluate symptoms in patients with community-acquired pneumonia Interim clinical guidance for management of patients with confirmed Coronavirus Disease (COVID-19) Analysis: PPE costs increase over 1,000% during COVID-19 crisis Using Personal Protective Equipment (PPE) Toward a more usable home-based video telemedicine system: A heuristic evaluation of the clinician user interfaces of home-based video telemedicine system COVID-19 transforms health care through telemedicine: evidence from the field Rapid response to COVID-19 health informatics support for outbreak management. In an academic health system Telehealth transformation: COVID-19 and the rise of virtual care Consumer Survey The transition from reimagining to recreating health care is now Brief Communication: An interactive online dashboard for tracking COVID-19 in U.S. counties, cities and states in real time The authors have no competing interests to declare. All authors provided substantial contributions to the study design, acquisition, analysis and interpretation of data; drafting and revising the manuscript; final approval for publication and agree to be accountable for all aspects of the work.