The value of mHealth for managing chronic conditions.

Chronic conditions place a high cost burden on the healthcare system and deplete the quality of life for millions of Americans. Digital innovations such as mobile health (mHealth) technology can be used to provide efficient and effective healthcare. In this research we explore the use of mobile technology to manage chronic conditions such as diabetes and hypertension. There is ample empirical evidence in the healthcare literature showing that patients who use mHealth observe improvement in their health. However, an analytical study that quantifies the benefit of using mHealth is lacking. The benefit of using mHealth depends on many factors such as the current health condition of the patient, pattern of disease progression, frequency of measurement and intervention, the effectiveness of intervention, and the cost of measuring. Stochastic modeling is a suitable approach to take these factors into consideration to evaluate the benefit of mHealth. In this paper, we model the disease progression with the help of a Markov chain and quantify the benefits of measuring and intervention taking into consideration the above-mentioned factors. We compare two different modes for measuring and intervention, mHealth mode and conventional office visit mode, and evaluate the impact of these factors on health outcome.

A randomized trial of telemedicine for migraine management.

OBJECTIVE: To determine whether synchronous video-based telemedicine visits with specialists are feasible and to evaluate clinical effectiveness, patient perceptions, and other benefits of telemedicine visits for follow-up migraine care in a tertiary headache center. DESIGN: A one-year, randomized clinical trial. RESULTS: Fifty patients were screened and 45 entered the study (43 women, two men). Out of 96 scheduled visits, 89 were successfully conducted using telemedicine. Eighteen patients (out of 22) in the telemedicine cohort and 12 patients (out of 23) in the in-office cohort completed the study. In this small study, clinical outcomes, namely improvement in MIDAS, number of headache days, and average severity at 12 months for participants in the telemedicine group, were not different from those in the in-office group. Convenience was rated higher and visit times were shorter in the telemedicine group. CONCLUSIONS: In this cohort of patients with severe migraine-related disability, telemedicine was a feasible mode of treatment and an effective alternative to in-office visits for follow-up migraine care. Physician productivity could be higher with telemedicine, and patients may get better access because of its convenience. TRIAL REGISTRATION: This study is listed on ClinicalTrials.gov (NCT01706003).

Predicting hospital admission from emergency department triage data for patients presenting with fall-related fractures.

PURPOSE: Predict in advance the need for hospitalization of adult patients for fall-related fractures based on information available at the time of triage to help decision-making at the emergency department (ED). METHODS: We developed machine learning models using routinely collected triage data at a regional hospital chain in Pennsylvania to predict admission to an inpatient unit. We considered all patients presenting to the ED for fall-related fractures. Patients who were 18 years or younger, who left the ED against medical advice, left the ED waiting room without being seen by a provider, and left the ED after initial diagnostics were excluded from the analysis. We compared models obtained using triage data (pre-model) with models developed using additional data obtained after physicians' diagnoses (post-model). RESULTS: Our results show good discriminatory power on predicting hospital admissions. Neural network models performed the best (AUC: pre-model = 0.938 [CI 0.920-0.956], post-model = 0.983 [0.974-0.992]). The logistic regression analysis provides additional insights into the data and the relationships between the variables. CONCLUSIONS: Using limited data available at the time of triage, we developed four machine learning models aimed at predicting hospitalization for patients presenting to the ED for fall-related fractures. All the four models were robust and performed well. Neural network method, however, performed the best for both pre- and post-models. Simple, parsimonious machine learning models can provide high accuracy for predicting hospital admission.

Mobile health application usage and quality of care at a hypertension clinic: an observational cohort study.

OBJECTIVE: The aim of this study was to test whether a physician-supervised web-based app, integrated with an electronic medical record, helps in improving blood pressure (BP) management in clinical practice. MATERIALS AND METHODS: An observational study of 1633 patients seen at a hypertension clinic managed by an endocrinologist with two cohorts (726 adopted the app and 907 had not). The app allowed patients and doctors to monitor BP, blood sugar and other vital signs. Patients decided whether to opt in to using the app and how often to upload their readings. The provider could offer feedback and communicate with patients through the app. We evaluated the change in office-based BP measurement before and after app adoption (at least 12 months apart). We performed a difference-in-difference analysis along with matching based on patient-individual characteristics. RESULTS: The difference-in-difference estimates were 6.23 mmHg systolic [95% confidence interval (95% CI) 0.87-11.59] for patients with SBP 150 mmHg or above, 4.01 mmHg systolic (95% CI 1.11-6.91) for patients with SBP 140 mmHg or above, 4.37 mmHg diastolic (95% CI 1.06-7.68) for patients with DBP 90 mmHg or above, 1.89 mmHg systolic (95% CI 0.58-3.2) and 0.87 mmHg diastolic (95% CI 0.17-1.57) overall for an average patient. Higher frequency of app usage was also associated with a greater reduction in BP. CONCLUSION: Use of an mHealth app in a clinical practice, was associated with a significant reduction in BP for average patients as well as high-severity patients. Physician-supervised mHealth apps in a clinical practice could be instrumental in managing patient BP.

Randomized controlled clinical trial of "virtual house calls" for Parkinson disease.

IMPORTANCE: The burden of neurological disorders is increasing, but access to care is limited. Providing specialty care to patients via telemedicine could help alleviate this growing problem. OBJECTIVE: To evaluate the feasibility, effectiveness, and economic benefits of using web-based videoconferencing (telemedicine) to provide specialty care to patients with Parkinson disease in their homes. DESIGN: A 7-month, 2-center, randomized controlled clinical trial. SETTING: Patients' homes and outpatient clinics at 2 academic medical centers. PARTICIPANTS: Twenty patients with Parkinson disease with Internet access at home. INTERVENTION: Care from a specialist delivered remotely at home or in person in the clinic. MAIN OUTCOME MEASURES: The primary outcome variable was feasibility, as measured by the percentage of telemedicine visits completed as scheduled. Secondary outcome measures included clinical benefit, as measured by the 39-item Parkinson Disease Questionnaire, and economic value, as measured by time and travel. RESULTS: Twenty participants enrolled in the study and were randomly assigned to telemedicine (n = 9) or in-person care (n = 11). Of the 27 scheduled telemedicine visits, 25 (93%) were completed, and of the 33 scheduled in-person visits, 30 (91%) were completed (P = .99). In this small study, the change in quality of life did not differ for those randomly assigned to telemedicine compared with those randomly assigned to in-person care (4.0-point improvement vs 6.4-point improvement; P = .61). Compared with in-person visits, each telemedicine visit saved participants, on average, 100 miles of travel and 3 hours of time. CONCLUSION AND RELEVANCE: Using web-based videoconferencing to provide specialty care at home is feasible, provides value to patients, and may offer similar clinical benefit to that of in-person care. Larger studies are needed to determine whether the clinical benefits are indeed comparable to those of in-person care and whether the results observed are generalizable. TRIAL REGISTRATION: clinicaltrials.gov Identifier: NCT01476306.

Telemedicine in Leading US Neurology Departments.

OBJECTIVE: To determine the current practice and plans for telemedicine at leading US neurology departments. DESIGN AND SETTING: An electronic survey was sent to department chairs, administrators, or faculty involved in telemedicine at 47 neurology departments representing the top 50 hospitals as ranked by U.S. News and World Report. MAIN OUTCOME MEASURES: Current use, size, scope, reimbursement, and perceived quality of telemedicine services. RESULTS: A total of 32 individuals from 30 departments responded (64% response rate). The primary respondents were neurology faculty (66%) and department chairs (22%). Of the responding departments, 60% (18 of 30) currently provide telemedicine and most (n = 12) had initiated services within the last 2 years. Two thirds of those not providing telemedicine plan to do so within a year. Departments provide services to patients in state, out of state, and internationally, but only 6 departments had more than 50 consultations in the last year. The principal applications were stroke (n = 14), movement disorders (n = 4), and neurocritical care (n = 3). Most departments (n = 12) received external funding for telemedicine services, but few departments (n = 3) received payment from insurers (eg, Medicare, Medicaid). Reimbursement (n = 21) was the most frequently identified barrier to implementing telemedicine services. The majority of respondents (n = 20) find telemedicine to be equivalent to in-person care. CONCLUSIONS: Over 85% of leading US neurology departments currently use or plan to implement telemedicine within the next year. Addressing reimbursement may allow for its broader application.