Remote Patient Monitoring Program Research Articles

Pilot Implementation of Remote Patient Monitoring Program for Outpatient Management of CAR-T Cell Therapy

Pilot Implementation of Remote Patient Monitoring Program for Outpatient Management of CAR-T Cell Therapy

Implementation of a multisite, interdisciplinary remote patient monitoring program for ambulatory management of patients with COVID-19

Established technology, operational infrastructure, and nursing resources were leveraged to develop a remote patient monitoring (RPM) program for ambulatory management of patients with COVID-19. The program included two care-delivery models with different monitoring capabilities supporting variable levels of patient risk for severe illness. The primary objective of this study was to determine the feasibility and safety of a multisite RPM program for management of acute COVID-19 illness. We report an evaluation of 7074 patients served by the program across 41 US states. Among all patients, the RPM technology engagement rate was 78.9%. Rates of emergency department visit and hospitalization within 30 days of enrollment were 11.4% and 9.4%, respectively, and the 30-day mortality rate was 0.4%. A multisite RPM program for management of acute COVID-19 illness is feasible, safe, and associated with a low mortality rate. Further research and expansion of RPM programs for ambulatory management of other acute illnesses are warranted.

Remote Patient Monitoring Identifies the Need for Triage in Patients with Acute COVID-19 Infection.

Introduction: Telehealth was frequently used in the provision of care and remote patient monitoring (RPM) during the COVID-19 pandemic. The Precision Recovery Program (PRP) remotely monitored and supported patients with COVID-19 in their home environment. Materials and Methods: This was a single-center retrospective cohort study reviewing data acquired from the PRP clinical initiative. Results: Of the 679 patients enrolled in the PRP, 156 patients were screened by a clinician following a deterioration in symptoms and vital signs on a total of 240 occasions, and included in the analyses. Of these 240 occasions, 162 (67%) were escalated to the PRP physician. Thirty-six patients were referred to emergency department, with 12 (7%) admitted to the hospital. The most common risk factors coinciding with hospital admissions were cardiac (67%), age >65 (42%), obesity (25%), and pulmonary (17%). The most common symptoms reported that triggered a screening event were dyspnea/tachypnea (27%), chest pain (14%), and gastrointestinal issues (8%). Vital signs that commonly triggered a screening event were pulse oximetry (15%), heart rate (11%), and temperature (9%). Discussion: Common factors (risk factors, vital signs, and symptoms) among patients requiring screening, triage, and hospitalization were identified, providing clinicians with further information to support decision making when utilizing RPM in this cohort. Conclusion: A clinician-led RPM program for patients with acute COVID-19 infection provided supportive care and screening for deterioration. Similar models should be considered for implementation in COVID-19 cohorts and other conditions at risk of rapid clinical deterioration in the home setting.

Early Identification of COVID-19 Infection Using Remote Cardiorespiratory Monitoring: Three Case Reports.

BackgroundThe adoption of remote patient monitoring (RPM) in routine medical care requires increased understanding of the physiologic changes accompanying disease development and the proactive interventions that will improve outcomes.ObjectiveThe aim of this study is to present three case reports that highlight the capability of RPM to enable early identification of viral infection with COVID-19 in patients with chronic respiratory disease.MethodsPatients at a large pulmonary practice who were enrolled in a respiratory RPM program and who had contracted COVID-19 were identified. The RPM system (Spire Health) contains three components: (1) Health Tags (Spire Health), undergarment waistband-adhered physiologic monitors that include a respiratory rate sensor; (2) an app on a smartphone; and (3) a web dashboard for use by respiratory therapists. The physiologic data of 9 patients with COVID out of 1000 patients who were enrolled for monitoring were retrospectively reviewed, and 3 instances were identified where the RPM system had notified clinicians of physiologic deviation due to the viral infection.ResultsPhysiologic deviations from respective patient baselines occurred during infection onset and, although the infection manifested differently in each case, were identified by the RPM system. In the first case, the patient was symptomatic; in the second case, the patient was presymptomatic; and in the third case, the patient varied from asymptomatic to mildly symptomatic.ConclusionsRPM systems intended for long-term use and that use patient-specific baselines can highlight physiologic changes early in the course of acute disease, such as COVID-19 infection. These cases demonstrate opportunities for earlier diagnosis, treatment, and isolation. This study supports the need for further research into how RPM can be effectively integrated into clinical practice.

Oncology Patients' Perspectives on Remote Patient Monitoring for COVID-19.

Oncology patients are vulnerable to adverse outcomes associated with COVID-19, and clinical deterioration must be identified early. Several institutions launched remote patient monitoring programs (RPMPs) to care for patients with COVID-19. We describe patients' perspectives on a COVID-19 RPMP at a National Comprehensive Cancer Center. Patients who tested positive for COVID-19 were eligible. Enrolled patients received a daily electronic COVID-19 symptom assessment, and a subset of high-risk patients also received a pulse oximeter. Monitoring was provided by a centralized team and was discontinued 14 days after a patient's positive test result and following 3 days without worsening symptoms. Patients who completed at least one assessment and exited the program were sent a patient engagement survey to evaluate the patient's experience with digital monitoring for COVID-19. The survey was distributed to 491 patients, and 257 responded (52% completion rate). The net promoter score was 85%. Most patients agreed that the RPMP was worthwhile, enabled better management of their COVID-19 symptoms, made them feel more connected to their healthcare team, and helped prevent emergency room visits. Identified themes regarding patient-perceived value of a RPMP included (1) security: a clinical safety net; (2) connection: a link to their clinical team during a period of isolation; and (3) empowerment: an education on the virus and symptom management. RPMPs are perceived to be of value to oncology patients with COVID-19. Policymakers should consider how these programs can be reimbursed to keep vulnerable patients at home and out of the acute care setting.

467-P: Immediate and Sustained Trends in Glycemic Control during Remote Patient Monitoring in People with Type 2 Diabetes

Technologies that let patients share diabetes data with care teams can help care teams identify patients with deteriorating glycemic control and facilitate timely and remote-based interventions outside of routine clinic visits. In the current study, we investigated whether people with type 2 diabetes (PWT2D) demonstrate improved glycemia after enrolling in remote patient monitoring (RPM) pilot programs that incorporated remote data syncing and coaching. All program participants were instructed to sync their blood glucose meters with either a mobile app or a computer-based software regularly during program participation. Synced blood glucose data were available to the RPM teams via a web-based dashboard, and remote coaching was administered either regularly and/or as needed. Data from 384 PWT2D (42% female; median age: 50 years) were included in cross-sectional comparisons at baseline and at 3, 6, and 12 months of RPM program participation. Overall trends of immediate (i.e., at 3 months) and sustained (at 6 and 12 months) improvements were observed for mean blood glucose levels (baseline: 178 mg/dL to ~155 mg/dL at 3, 6, 12 months; all Ps <.05), and mean proportion of in-range (70-180 mg/dL; baseline: 60% to ~74% at 3, 6, 12 months; all Ps <.05) and high SMBG readings (>250 mg/dL; baseline: 14% to ~8% at 3, 6, 12 months; all Ps <.05), with no differences in the proportion of low (<70 mg/dL) readings. In summary, glycemic improvements are seen within 3 months of program participation and are sustained with continued engagement. These findings indicate that RPM programs that incorporate remote data sharing and coaching can make a substantial impact on glycemic control for people with type 2 diabetes. Disclosure T. Sheng: Employee; Self; Glooko, Inc. S. Babikian: Employee; Self; Glooko, Inc. V. Singh: Employee; Self; Glooko, Inc. M. A. Clements: Employee; Self; Glooko, Inc., Other Relationship; Self; Glooko, Inc.

Oncology patients’ perspectives on remote patient monitoring for COVID-19.

1504 Background: Oncology patients are particularly vulnerable to adverse outcomes from COVID-19 and require careful monitoring to identify early deterioration and render higher level care when indicated. Several institutions launched remote patient monitoring programs (RPMPs) to care for patients with COVID-19. We describe patients’ perspectives on a COVID-19 RPMP at a National Comprehensive Cancer Center. Methods: Adult patients who had either tested positive for COVID-19 on an outpatient microbiology test or were discharged after hospitalization for the virus were eligible. Patients enrolled in the RPMP received a daily 10-question electronic patient-reported outcome assessment of COVID-19 symptoms and their responses generated alerts to a centralized monitoring team for new or worsening symptoms. A subset of high-risk patients also received a pulse oximeter which alerted when blood oxygen levels dropped below 93%. RPM was discontinued 14 days after a patient’s positive test result and following 3 days without worsening symptoms or fever. Patients who exited the program and had completed at least one assessment were sent a patient engagement survey. The objective of the survey was to evaluate the patient’s experience with digital monitoring and symptom management for COVID-19. The assessment was structured with objective response questions, including a net promoter score, and free text questions to elicit patient perspectives on RPM value. Free text responses were analyzed using grounded theory to identify primary themes regarding perceived value. Results: The survey was distributed to 452 patients; 241 responded as of June 10, 2020 (53% completion rate). The net promoter score was 91%. The table provides responses to objective questions. Qualitative analysis of free text responses identified the primary themes regarding patient perceived value which included: 1) Security: patients appreciated that the RPMP provided a clinical safety net; 2) Connection: patients appreciated the link to their clinical team during a period of isolation; 3) Empowerment: patients appreciated that the RPMP provided education on the virus and symptom management. Conclusions: RPMPs are perceived to be of value to oncology patients with COVID-19. A key barrier to maintaining these programs is cost. Policymakers should consider how these programs can be reimbursed in the future so that they can continue to provide care to vulnerable patients and keep them at home out of the acute care setting.[Table: see text]

Association of use of remote patient monitoring (RPM) with reduced hospitalizations in cancer patients with COVID-19.

1503 Background: Patients with cancer and COVID-19 are at risk for poor clinical outcomes. An established multi-site remote patient monitoring (RPM) service was rapidly adapted to support a novel, interdisciplinary COVID-19 program for outpatient management of patients at high-risk for severe illness. The goal of this study was to assess the impact of the RPM program on clinical outcomes and acute care utilization in cancer patients diagnosed with COVID-19. Methods: This is a cross-sectional analysis following a multi-site prospective observational study performed at Mayo Clinic Cancer Center (MCCC). All adult patients with active cancer – defined as currently receiving cancer-directed therapy or in recent remission on active surveillance – and PCR-confirmed SARS-CoV-2 infection between March 18 and July 31, 2020 were included. RPM was comprised of in-home technology to assess symptoms and physiologic data with centralized nurse and physician oversight. Results: During the study timeframe 224 cancer patients were diagnosed with COVID-19 at MCCC. Initial management included urgent hospitalization (within 48 hours of diagnosis) in 34 patients (15%). Of the remaining 190 patients (85%) initially managed in the outpatient setting, those who did not receive RPM were significantly more likely to experience hospitalization than those receiving RPM (OR 3.6, 95% CI 1.036 to 12.01, P = 0.044). Following balancing of patient characteristics by inverse propensity weighting, rates of hospital admission for RPM and non-RPM patients were 3.1% and 11% respectively, implying that RPM was associated with an 8% reduction in hospital admission rate (-0.077; 95% CI: -0.315 to -0.019, P = 0.009). Use of RPM was also associated with lower rates of prolonged hospitalization, ICU admission, and mortality, though these trends did not reach statistical significance. Conclusions: In the midst of a global pandemic associated with inpatient bed, ventilator, and PPE shortages, the RPM program provided an effective strategy for outpatient clinical management and was associated with decreased rates of hospitalization, ICU admission, and mortality in cancer patients with COVID-19. This care model enabled simultaneous opportunity to mitigate the increased risks of exposure, transmission, and resource utilization associated with conventional care.

A Review on Wearable and Contactless Sensing for COVID-19 With Policy Challenges

The COVID-19 pandemic has affected more than 100 million people worldwide, with around 500,000 cases reported daily. This has led to the overwhelming of healthcare systems even in developed countries such as the US, UK, etc. Remote monitoring of COVID-19 patients with non-serious symptoms can help reduce the burden on healthcare facilities and make them available for high risk groups and the seriously affected. The pandemic has accelerated the demand for the remote patient monitoring (RPM) technologies, and the market is expected to reach 2.14 billion in 2027 from the value of 786.4 million in 2019. In RPM programs, there are two types of sensors that can be used: wearable and contactless. The former, which is currently more widely used, is not only more obtrusive and uncomfortable, but can also lead to cross-infection through patient contact. These two types of technologies are discussed and compared for each vital sign. In the respiratory system, the vital signs are the respiratory rate (RR) and oxygen saturation (SpO2), while for the latter, they are the heart rate/rhythm and the blood pressure (BP). Then, the discussion is broadened to policy level changes needed to expedite the use of such technologies for remote patient monitoring (RPM) in the world. Around 80% of countries' RPM programs are either informal or in a pilot phase, and thus lack policies and an established regulatory framework to implement their programs. The various policies needed to initiate, deliver, and reimburse RPM programs during emergency situations and outbreaks are discussed. Finally, technologies such as contactless systems, robotics, and Internet-of-things (IoT) that will revolutionize healthcare in the future by reducing the interaction between physicians and patients and cross-infection are discussed.

Remote Home Monitoring of Patients With Cancer During the COVID Pandemic: A Pilot Study.

PURPOSE:The COVID-19 pandemic has posed significant challenges in the care of patients with cancer, including how to manage outpatients who are COVID-positive but do not require hospitalization. We explored the use of a remote patient monitoring (RPM) program to care for such outpatients.METHODS:Consecutive patients who were tested for COVID-19 because of symptom onset but were clinically stable were offered enrollment into a pilot RPM program. Patients were provided equipment for vital sign measurements and a computer tablet to enter results three times per day. The results were monitored centrally by clinical staff. The goal was to closely monitor patients and escalate care as warranted.RESULTS:Between March and June of 2020, 29 patients were approached and 26 were enrolled. The mean age was 57 years old (range, 30-88), 14 were women, and patients remained in the program for an average of 16 days (range, 2-63). Twenty-four patients (83%) were on active anticancer therapy. During that time period, only one patient was admitted to the hospital for worsening respiratory symptoms. The percentage of days during which at least one set of data and all three sets of data were entered was 97.2% and 65.7%, respectively. There was no association between the demographic factors of age, sex, or the reason for being monitored with the level of engagement (P > .05).CONCLUSION:In this pilot study, patients with cancer were readily enrolled in a remote home monitoring program. Monitoring was feasible, and there was a high rate of engagement with the program. The role of RPM should be further tested as the COVID pandemic continues.

Stratification of Arrhythmic Risk Using Remote Patient Monitoring in a Heart Transplant Recipient with Coronary Allograft Vasculopathy

Introduction Criteria for ICD implantation in heart transplant recipients remain poorly defined. During the COVID-19 pandemic, remote patient monitoring (RPM) has been increasingly used to minimize the patient risk of infection. In addition, RPM also offers monitoring of heart rhythm and thus may have a potential to improve arrhythmic risk stratification. We present a case of heart transplant recipient in whom the decision for ICD implantation was based on RPM data. Case Report We performed elective heart transplantation in 66-year old male patient with nonischemic cardiomyopathy. The transplantation procedure was uneventful; however, on the first postoperative day we performed coronary angiography due to hypokinesia of inferior left ventricular wall. We found 1-vessel disease with stenosis of proximal RCA, which was resolved using 1 drug-eluting stent (DES). Discharge echocardiography showed normal graft function without segmental wall motion abnormalities. At the routine 12-month follow-up visit the patient was asymptomatic, but we found an increase in serum troponin and performed coronary angiography, which showed allograft vasculopathy with significant stenosis of mid LAD, which was resolved with 1 DES. As the echocardiography did not show any decline in the graft function and no ventricular arrhythmias were observed, we did not opt for immediate ICD implantation; instead, we enrolled the patient in our institution's heart transplant RPM program. The RPM program allows for remote monitoring of patient's blood pressure, weight, SpO2 and ECG, which are reviewed by heart transplant nurse on daily basis. After 2 months of RPM we first observed premature ventricular complexes with increasingly more frequent trigeminy episodes being recorded in the course of the following 4 weeks. Repeated coronary angiography showed no progression of vasculopathy and graft function was normal. However, considering the high risk for sudden cardiac death in this patient due to the combination of vasculopathy and significant ventricular ectopy we opted for the implantation of ICD. Summary RPM offers relevant and timely medical data that may facilitate the management of heart transplant recipients. Future trials are warranted to investigate whether such approach may also improve the arrhythmic risk stratification in this patient population.

A Scalable Framework for Telehealth: The Mayo Clinic Center for Connected Care Response to the COVID-19 Pandemic.

Background: The Mayo Clinic Center for Connected Care has an established organizational framework for telehealth care delivery. It provides patients, consumers, care teams, and referring providers access to clinical knowledge through technologies and integrated practice models. Central to the framework are teams that support product management and operational functions. They work together across the asynchronous, synchronous video telemedicine, remote patient monitoring (RPM), and mobile core service lines.Methods: The organizational framework of the Center for Connected Care and Mayo Clinic telehealth response to the COVID-19 pandemic is described. Barriers to telehealth delivery that were addressed by the public health emergency are also reported. This report was deemed exempt from full review by the Mayo Clinic IRB.Results: After declaration of the COVID-19 pandemic, there was rapid growth in established telehealth offerings, including patient online services account creation, secure messaging, inpatient eConsults, express care online utilization, and video visits to home. Census for the RPM program for patients with chronic conditions remained stable; however, its framework was rapidly adapted to develop and implement a COVID-19 RPM service. In addition to this, other new telehealth and virtual care services were created to support the unique needs of patients with COVID-19 symptoms or disease and the health care workforce, including a digital COVID-19 self-assessment tool and video telemedicine solutions for ambulances, emergency departments, intensive care units, and designated medical–surgical units.Conclusion: Rapid growth, adoption, and sustainability of telehealth services through the COVID-19 pandemic were made possible by a scalable framework for telehealth and alignment of regulatory and reimbursement models.

Development and implementation of a remote patient monitoring program for heart failure: a single-centre experience.

AimsRemote patient monitoring (RPM) in the management of heart failure (HF), including telemonitoring, thoracic impedance, implantable pulmonary artery pressure (PAP) monitors, and cardiac implantable electronic device (CIED)‐based sensors, has had varying outcomes in single platform studies. Uncertainty remains regarding the development of single‐centre RPM programs; additionally, no studies examine the effectiveness of dual platform RPM programs for HF. This study describes the implementation and outcomes of a dual platform RPM program for HF at a single centre.Methods and resultsAn RPM program was developed to include two platforms (e.g. CardioMEMS™ HF System and HeartLogic™ HF Diagnostic). To examine changes within each participant over time, study‐related outcomes including total hospitalizations (TH), total length of stay (TLOS), cardiac hospitalizations (CH), cardiac LOS (CLOS), and cardiac‐related emergency department (ED) visits were compared in two timeframes: 12 months pre‐enrolment and post‐enrolment into RPM. For 141 participants enrolled, there was a significant reduction in the likelihood of experiencing a CH by 19% (0.77 vs. 0.61 events/patient‐year; HR: 0.81, 95% CI: 0.67–0.97, P = 0.03) and a cardiac‐related ED visit by 28% (0.48 vs. 0.34 events/patient‐year; HR: 0.72, 95% CI: 0.55–0.93, P = 0.01). There was also a 51% decrease (SE = 1.41, 95% CI: 2.79–8.38 days, P < 0.001) and 62% decrease (SE = 1.24, 95% CI: 3.35–8.22 days, P < 0.001) in TLOS and CLOS, respectively.ConclusionsA dual platform RPM program for HF using structured education, RPM‐capable devices, and alert‐specific medication titration reduces the likelihood of experiencing a cardiac hospitalization and cardiac‐related ED visit in this single‐centre study.

The Johns Hopkins Post-Acute COVID-19 Team (PACT): A Multidisciplinary, Collaborative, Ambulatory Framework Supporting COVID-19 Survivors

The Johns Hopkins Post-Acute COVID-19 Team (PACT): A Multidisciplinary, Collaborative, Ambulatory Framework Supporting COVID-19 Survivors

Technique failure in remote patient monitoring program in patients undergoing automated peritoneal dialysis: A retrospective cohort study.

Remote patient monitoring (RPM) programs in automated peritoneal dialysis (APD) allow clinical teams to be aware of many aspects and events of the therapy that occur in the home. The present study evaluated the association between RPM use and APD technique failure. A retrospective, multicentre, observational cohort study of 558 prevalent adult APD patients included between 1 October 2016 and 30 June 2017 with follow-up until 30 June 2018 at Renal Therapy Services network in Colombia. Patients were divided into two cohorts based on the RPM use: APD-RPM (n = 148) and APD-without RPM (n = 410). Sociodemographic and clinical characteristics of all patients were summarized descriptively. A propensity score was used to create a pseudo-population in which the baseline covariates were well balanced. The association of RPM with technique failure was estimated adjusting for the competing events death and kidney transplant. Five hundred fifty-eight patients were analyzed. 26.5% had APD-RPM. In the matched sample comprising 148 APD-RPM and 148 APD-without RPM patients, we observed a lower technique failure rate of 0.08 [0.05-0.15] episodes per patient-year in APD-RPM versus 0.18 [0.12-0.26] in APD-without RPM cohort; incidence rate ratio = 0.45 95% confidence interval: [0.22-0.91], p-value = 0.03. The use of an RPM program in APD patients may be associated with a lower technique failure rate. More extensive and interventional studies are needed to confirm its potential benefits and to measure other patient-centered outcomes.

Remote Patient Monitoring Program for Hospital Discharged COVID-19 Patients.

We deployed a Remote Patient Monitoring (RPM) program to monitor patients with coronavirus disease 2019 (COVID-19) upon hospital discharge. We describe the patient characteristics, program characteristics, and clinical outcomes of patients in our RPM program. We enrolled COVID-19 patients being discharged home from the hospital. Enrolled patients had an app, and were provided with a pulse oximeter and thermometer. Patients self-reported symptoms, O2 saturation, and temperature daily. Abnormal symptoms or vital signs were flagged and assessed by a pool of nurses. Descriptive statistics were used to describe patient and program characteristics. A mixed-effects logistic regression model was used to determine the odds of a combined endpoint of emergency department (ED) or hospital readmission. A total of 295 patients were referred for RPM from five participating hospitals, and 225 patients were enrolled. A majority of enrolled patients (66%) completed the monitoring period without triggering an abnormal alert. Enrollment was associated with a decreased odds of ED or hospital readmission (adjusted odds ratio: 0.54; 95% confidence interval: 0.3-0.97; p = 0.039). Referral without enrollment was not associated with a reduced odds of ED or hospital readmission. RPM for COVID-19 provides a mechanism to monitor patients in their home environment and reduce hospital utilization. Our work suggests that RPM reduces readmissions for patients with COVID-19 and provides scalable remote monitoring capabilities upon hospital discharge. RPM for postdischarge patients with COVID-19 was associated with a decreased risk of readmission to the ED or hospital, and provided a scalable mechanism to monitor patients in their home environment.

Abstract P156: Improvement In Blood Pressure Using Remote Patient Monitoring During COVID19

Introduction: The coronavirus disease 2019 (COVID19) pandemic required strict social distancing to curb transmission. Unfortunately, these measures severely limited healthcare access and chronic disease management. In response, many health organizations rapidly developed or expanded telemedicine to provide care directly to patients at home. Little has been reported about the impact of such interventions on clinical outcomes during COVID19. We examined whether enrollment in a remote patient monitoring (RPM) program for hypertension (HTN) prior to COVID19 was associated with improved blood pressure during the pandemic. Methods: We developed an RPM program that tracked vital signs, medication side effects, and treatment adherence patterns outside of the clinic. Patients were referred by their primary care doctor for uncontrolled HTN or suspected white coat HTN. Patients received a two-way tablet, blood pressure cuff, and virtual nursing support via scheduled video visits. Those referred for uncontrolled HTN who had at least two weeks of data both before and after the onset of COVID19 (defined as the first two weeks of March 2020) were included in the study. A mixed-models analysis that adjusted for serial autocorrelation was used to compare mean systolic blood pressure (SBP) and mean diastolic blood pressure (DBP) in the pre-/post-COVID19 periods. Results: Of 94 patients enrolled in the RPM program to date, 46 had at least two weeks of data both pre-COVID19 and post-COVID19. Mean age was 69.0 ± 10.9 years, 69.6% (32 of 46) were women, 78.3% (36 of 46) were Hispanic, and 63.0% (29 of 46) were Spanish-speaking. Pre-COVID, mean SBP was 132.31 ± 13.99 mmHg, mean DBP was 77.10 ± 9.87 mmHg, and 70% (32 of 46) of patients had uncontrolled BP (&gt;130/80 mmHg per AHA guidelines). Post-COVID, mean SBP was 129.57 ± 13.29 mmHg, mean DBP was 76.00 ± 9.16 mmHg, and 57% (26 of 46) of patients had uncontrolled BP. There was a significant reduction in both mean SBP (β = –2.74, 95% CI –5.21, –0.26, p = 0.03) and mean DBP (β = –1.10, 95% CI –2.22, 0.02, p = 0.05) post-COVID vs. pre-COVID. Discussion: Despite the stress and social isolation associated with COVID19, participation in an RPM program that combines home BP monitoring with virtual nursing support can help maintain and even mildly decrease BP.

Remote Patient Monitoring for the Detection of COPD Exacerbations.

BackgroundCOPD exacerbations occur more frequently with disease progression and are associated with worse prognosis and higher healthcare expenditure.PurposeTo utilize a networked system, optimized with statistical process control (SPC), for remote patient monitoring (RPM) and to identify potential predictors of COPD exacerbations.MethodsSeventeen subjects, mean (SD) age of 69.7 (7.2) years, with moderate to severe COPD received RPM. Over 2618 patient-days (7.17 patient-years) of monitoring, we obtained daily symptom scores, treatment adherence, self-reported activity levels, daily spirometry (SVC, FEV1, FVC, PEF), inspiratory capacity (IC), and oxygenation (SpO2). These data were used to identify predictors of exacerbations defined using Anthonisen and other criteria.ResultsAfter implementation of SPC, concordance analysis showed substantial agreement between FVC (decrease below the 7-day rolling average minus 1.645 SD) and self-reported healthcare utilization events (κ=0.747, P<0.001) as well as between increased use of inhaled short-acting bronchodilators and exacerbations defined by two Anthonisen criteria (κ=0.611, P<0.001) or modified Anthonisen criteria (κ=0.622, P<0.001). There was a moderate agreement between FEV1 (decrease >1.645 SD below the 7-day rolling average) and self-reported healthcare utilization events (κ=0.475, P<0.001) and between SpO2 less than 90% and exacerbations defined by two Anthonisen criteria (κ=0.474, P<0.001) or modified Anthonisen criteria (κ=0.564, P<0.001).ConclusionExacerbations were best predicted by FVC and FEV1 below the one-sided 95% confidence interval derived from SPC but also by increased use of inhaled short-acting bronchodilators and fall in oxygen saturation. An RPM program that captures these parameters may be used to guide appropriate interventions aimed at reducing healthcare utilization in COPD patients.

862-P: A Machine Learning Model Predicts Engagement with a Mobile Health (mHealth)-Based Remote Patient Monitoring (RPM) Program among Persons with Diabetes (PWDs)

We developed a machine learning model that predicts risk of declining engagement (churn) with an mHealth app (Glooko) that supports diabetes self-management. The model uses self-monitored blood glucose (SMBG), demographic, and app engagement data. We selected 7134 PWD using meter and/or insulin pump devices who used the Glooko diabetes management app in a remote (outside of the clinic) setting between 1/1/2019-7/1/2019 (40,349 total weekly predictions). We trained a gradient boosting algorithm to predict risk of churn in the next 28 days. We built features using data from the prior 28 days; features included outcomes (counts of glucose checks, hypo/hyperglycemia occurrences, mean blood glucose), app engagement (counts of app clicks and meter and/or insulin pump uploads, duration of sessions), and demographics (diabetes type, gender, age). The training cohort had median age=22 years (IQR:11-49), 52% female, 60% type 1 diabetes (T1D). We performed out-of-sample validation using 4647 individuals (8646 total weekly predictions). The validation cohort had median age=20 years (IQR:11-49), 52% female, 60.5% T1D. The algorithm predicted individuals at risk of churning with a precision of 0.67 and a recall of 0.8. This correlates to sensitivity=80%, specificity=58%, and positive predictive value=67%. The present model indicates that it is feasible to predict declining engagement with an mHealth app to support diabetes self-management. The ability to predict churn may help clinics design effective mHealth-based RPM programs. These predictions can allow clinicians to proactively reach out to PWDs at risk of program dropout. Future research should examine whether dropout from RPM programs predicts worsening diabetes-related outcomes. Disclosure S. Babikian: Employee; Self; Glooko, Inc. V. Singh: Employee; Self; Glooko, Inc. M.A. Clements: Consultant; Self; Glooko, Inc. Other Relationship; Self; Glooko, Inc.

Racial Disparities in Diabetes Management Outcomes: Evidence from a Remote Patient Monitoring Program for Type 2 Diabetic Patients.

Introduction: Despite growing documentation of the efficacy of telemedicine in diabetes management, racial disparities in telemedicine-facilitated diabetes management remain underexplored. This study examined disparities in diabetes management outcomes between black and white patients with type 2 diabetes (T2D) in a remote monitoring program. Methods: The analysis sample included 914 white T2D patients and 365 black T2D patients in Nebraska who completed a 3-month remote patient monitoring and coaching after hospital discharge from 2014 to 2017. Ordinary least squares regression was estimated to examine racial differences in hemoglobin A1c (HbA1c), and logistic regression was used to determine the odds of HbA1c > 9% at the end of the program, controlling for demographics, baseline health conditions, and patient activation and engagement with the program. Results: The proportion of white patients with HbA1c > 9% was reduced from 16% at the baseline to 7% at program completion, and the corresponding reduction among black patients was from 30% to 18%. After adjusting for the effects of baseline HbA1c and other covariates, the average HbA1c among black patients at the end of the program was 0.23 points higher than that among white patients (p < 0.01), and the adjusted odds of black patients having HbA1c > 9% was 1.68 times that of white patients (95% confidence interval [1.07-2.63]). Discussion: The remote patient monitoring and coaching program reduced the absolute gap between black and white T2D patients. However, substantial racial disparities in HbA1c still remained at the end of the program and warranted further research.