Telemedicine Journal and E-Health
ISSN / EISSN: 15305627 / 15563669
Published by: Mary Ann Liebert Inc
Total articles ≅ 3,285
Latest articles in this journal
Telemedicine Journal and E-Health; https://doi.org/10.1089/tmj.2022.0405
Background and Objectives: Image quality is a crucial factor in the effectiveness and efficiency of teledermatological consultations. However, up to 50% of images sent by patients have quality issues, thus increasing the time to diagnosis and treatment. An automated, easily deployable, explainable method for assessing image quality is necessary to improve the current teledermatological consultation flow. We introduce ImageQX, a convolutional neural network for image quality assessment with a learning mechanism for identifying the most common poor image quality explanations: bad framing, bad lighting, blur, low resolution, and distance issues. Methods: ImageQX was trained on 26,635 photographs and validated on 9,874 photographs, each annotated with image quality labels and poor image quality explanations by up to 12 board-certified dermatologists. The photographic images were taken between 2017 and 2019 using a mobile skin disease tracking application accessible worldwide. Results: Our method achieves expert-level performance for both image quality assessment and poor image quality explanation. For image quality assessment, ImageQX obtains a macro F1-score of 0.73 ± 0.01, which places it within standard deviation of the pairwise inter-rater F1-score of 0.77 ± 0.07. For poor image quality explanations, our method obtains F1-scores of between 0.37 ± 0.01 and 0.70 ± 0.01, similar to the inter-rater pairwise F1-score of between 0.24 ± 0.15 and 0.83 ± 0.06. Moreover, with a size of only 15 MB, ImageQX is easily deployable on mobile devices. Conclusion: With an image quality detection performance similar to that of dermatologists, incorporating ImageQX into the teledermatology flow can enable a better, faster flow for remote consultations.
Telemedicine Journal and E-Health; https://doi.org/10.1089/tmj.2022.0357
Purpose:Diabetic retinopathy (DR) is a microvascular complication of diabetes mellitus (DM). Standard of care for patients with DM is an annual eye examination or retinal imaging to assess for DR, the latter of which may be completed through telemedicine approaches. One significant issue is poor-quality images that prevent adequate screening and are thus ungradable. We used artificial intelligence to enable point-of-care (at time of imaging) identification of ungradable images in a DR screening program.Methods:Nonmydriatic retinal images were gathered from patients with DM imaged during a primary care or endocrinology visit from September 1, 2017, to June 1, 2021. The Topcon TRC-NW400 retinal camera (Topcon Corp., Tokyo, Japan) was used. Images were interpreted by 5 ophthalmologists for gradeability, presence and stage of DR, and presence of non-DR pathologies. A convolutional neural network with Inception V3 network architecture was trained to assess image gradeability. Images were divided into training and test sets, and 10-fold cross-validation was performed.Results:A total of 1,377 images from 537 patients (56.1% female, median age 58) were analyzed. Ophthalmologists classified 25.9% of images as ungradable. Of gradable images, 18.6% had DR of varying degrees and 26.5% had non-DR pathology. 10 fold cross-validation produced an average area under receiver operating characteristic curve (AUC) of 0.922 (standard deviation: 0.027, range: 0.882 to 0.961). The final model exhibited similar test set performance with an AUC of 0.924.Conclusions:This model accurately assesses gradeability of nonmydriatic retinal images. It could be used for increasing the efficiency of DR screening programs by enabling point-of-care identification of poor-quality images.
Telemedicine Journal and E-Health; https://doi.org/10.1089/tmj.2022.0481
Background: The COVID-19 pandemic demanded rapid development of telemedicine services for pediatric care and highlighted disparities for marginalized communities. Objective: To understand the demographic characteristics of patients with completed and incomplete telemedicine visits at Ann and Robert H. Lurie Children's Hospital of Chicago. Methods: This was a cross-sectional retrospective analysis of telemedicine visits for patients <25 years old scheduled between March 21, 2020, and March 17, 2021. We examined visit outcomes and compared outcomes by race/ethnicity, language, and payer using logistic regression. Geographic information system mapping and linear regression were used to examine the relationship between incomplete visits and broadband access within Cook County. Results: A total of 13,655 eligible video visits were scheduled for children within 147 ZIP codes during the study time frame. Patient characteristics included median age 9 years, 53% female, 42% non-Latinx White, 31% Latinx, 13% non-Latinx Black, 11% non-Latinx other, and 3% declined/unknown. Preferred language was 89% English, 10% Spanish, and 1% other. Payer was 56% private, 43% public, and <1% other/self-pay. Overall, 86% video visits were completed, 7% cancelled, and 7% no-show with significant variation by patient demographic. Odds of incomplete visits were higher for Latinx patients (odds ratio [OR] 1.93) and non-Latinx Black patients (OR 2.33) than for non-Latinx White patients, patients with preferred language other than English (OR 1.53), and patients not privately insured (OR 1.89). Incomplete visit rates and broadband access were inversely related. Conclusion: System and policy solutions are needed to ensure equitable access and address disparities in incomplete telemedicine visits for marginalized populations in urban areas with lower broadband.
Telemedicine Journal and E-Health; https://doi.org/10.1089/tmj.2022.0407
During the COVID-19 pandemic and public health emergency, telehealth programs vastly expanded with strong support from various federal and state agencies. However, the uncertainty regarding future reimbursement policies for telehealth services has resulted in concerns about long-term sustainability of innovative health service delivery models beyond the financial support. Given the limited literature on creating telehealth programs with long-term sustainability in consideration, we have developed a framework for gathering appropriate data during various stages of program implementation to evaluate clinical effectiveness and economic sustainability that is applicable across various settings, with additional attention to health equity. Recognizing the difficulty of sustaining telehealth programs solely through a fee-for-service payment model, we encourage all telehealth stakeholders, especially payers and policymakers, to consider cost-effectiveness of telehealth programs and support alternate payment models for ensuring long-term sustainability.
Telemedicine Journal and E-Health; https://doi.org/10.1089/tmj.2022.0150
Background:The COVID-19 pandemic led to health care practitioners utilizing new technologies to deliver health care, including telemedicine. The purpose of this study was to examine the effect of rapidly proliferative use of video visits on opioid prescribing to orthopedic patients at a large academic health system that had existing procedure-specific opioid prescribing guidelines.Methods:This IRB-exempt study examined 651 opioid prescriptions written to patients who had video (visual and audio), telephone (audio only), or in-person encounters at our institution from March 1 to June 1, 2020 and compared them with 963 prescriptions written during the same months in 2019. Prescriptions were converted into daily milligram morphine equivalents (MMEs) to facilitate direct comparison. Chi-square testing was used to compare categorical data, whereas analysis of variance and Mann–Whitney tests were used to compare numerical data between groups. Statistical significance was set at <0.05.Results:Six hundred fifty-one of 1,614 prescriptions analyzed (40.3%) occurred during the pandemic. Patients prescribed opioids during video visits were prescribed 53.3 ± 37 MME, significantly higher than in-person (p = 0.002) or audio visits (p < 0.001) before or during the pandemic. Prepandemic, significantly higher MME were prescribed for in-person versus audio only visits (41.6 ± 89 vs. 30.2 ± 28 MME; p = 0.026); during the pandemic, there was no difference between these groups (p = 0.91). Significantly higher MME were prescribed by Nurse Practitioners and Physician Associates versus MD or DO prescribers for both time periods (51.3 ± 109 vs. 27.9 ± 42 MME; p < 0.001; 42.9 ± 70 vs. 28.2 ± 42 MME; p < 0.001).Conclusion:During crisis and with new technology, we should be vigilant about prescribing of opioid analgesics. Despite well-established protocols, patients received significantly higher MME through video than for other encounter types, including in-person encounters. In addition, significantly higher MME were prescribed by mid-level prescribers compared with DOs or MDs. Institutions should ensure these prescribers are involved during creation of opioid prescribing protocols after orthopedic surgery.
Telemedicine Journal and E-Health; https://doi.org/10.1089/tmj.2022.0299
Introduction:Data are limited on the effectiveness of remote patient monitoring (RPM) for acute illnesses, including COVID-19. We conducted a study to determine if enrollment in a COVID-19 RPM program was associated with better outcomes.Methods:From March through September 2020, patients with respiratory symptoms and presumptive COVID-19 were referred to the health system's COVID-19 RPM program. We conducted a retrospective cohort study comparing outcomes for patients enrolled in the RPM (n = 4,435) with those who declined enrollment (n = 2,742). Primary outcomes were emergency room, hospital, and intensive care unit admissions, and death. We used logistic regression to adjust for demographic differences and known risk factors for severe COVID-19.Results:Patients enrolled in the RPM were less likely to have risk factors for severe COVID-19. There was a significant decrease in the odds of death for the group enrolled in the RPM (adjusted odds ratio [OR] = 0.50; 95% confidence interval [CI], 0.30–0.83) and a nonsignificant decrease in the odds of the other primary outcomes. Increased number of interactions with the RPM significantly decreased the odds of hospital admission (OR = 0.92; 95% CI, 0.88–0.95).Conclusions:COVID-19 RPM enrollment was associated with decreased odds of death, and the more patients interacted with the RPM, the less likely they were to require hospital admission. RPM is a promising tool that has the potential to improve patient outcomes for acute illness, but controlled trials are necessary to confirm these findings.
Telemedicine Journal and E-Health; https://doi.org/10.1089/tmj.2022.0397
Objective:Older adults are generally less proficient in technology use compared with younger adults. Data on telemedicine use during the COVID-19 pandemic in older persons with type 1 diabetes (T1D) and the association of telemedicine with the use of diabetes-related technology are limited. We evaluated care delivery to older adults compared with younger adults with T1D in a prepandemic and pandemic period.Methods:Data from electronic health records were evaluated for visit types (in-person, phone, and video) from two sequential 12-month intervals: prepandemic (April 2019–March 2020) and pandemic (April 2020–March 2021).Results:Data from 2,832 unique adults with T1D were evaluated in two age cohorts: younger (40–64 years) and older (≥65 years). Half of each group used continuous glucose monitoring (CGM), whereas 54% of the younger and 37% of the older cohort used pump therapy (p < 0.001). During the pandemic compared with the prepandemic period, visit frequency increased in both the younger (0.65 vs. 0.76 visits/patient/quarter; p < 0.01) and older (0.72 vs. 0.80 visits/patient/quarter; p < 0.01) cohorts. During the pandemic, older adults used more phone visits compared with younger adults (48% vs. 32%; p = 0.001). Patients using either pump therapy or CGM were more likely to use video visits compared with phone visits in both younger (41% vs. 24%; p < 0.001) and older cohorts (53% vs. 42%; p < 0.001).Conclusions:Adults using diabetes-related technologies, independent of age, accessed more video visits than those not using devices. Telemedicine visits appeared to maintain continuity of care for younger and older adults with T1D, supporting the future of a hybrid-care model.
Telemedicine Journal and E-Health; https://doi.org/10.1089/tmj.2022.0484
Introduction:A number of reports are available exploring how telehealth use grew during the COVID-19 pandemic and public health emergency. Some have reported variations in telehealth uptake by specialty, but few have explored growth in telehealth utilization by both specialty and state, arguably the most salient combination of regulatory domains.Methods:We extracted telehealth claims from Medicare public use data files in 2019 and 2020. We calculated utilization by state both as raw encounters and as encounters per 10,000 Medicare beneficiaries in each state. We categorized providers into four major groups (primary care, specialty care, nurse practitioners and physician assistants, and behavioral health) to further explore variations in uptake among these groups. We generated tables and maps to display the variations found.Results:Growth in raw telehealth encounter volume was dominated by large states. Growth in telehealth volume per 10,000 beneficiaries was dominated by states in the Northeast and showed four- to fivefold variation between the least and greatest. Growth by state and provider group varied by even wider margins, with some states showing large amounts of growth among some provider groups, but relatively little growth in others. No states showed relatively robust growth in telehealth across all provider groups.Discussion:Growth in telehealth during the public health emergency was generally robust, but varied considerably across states and provider types. Recognizing this variation is important, and further exploring potential sources of variation is an important task for future research.
Telemedicine Journal and E-Health; https://doi.org/10.1089/tmj.2022.0430
Purpose:This study investigated military doctors' and nurses' perceptions of telemedicine and the factors influencing their intention to use it based on the unified theory of acceptance and use of technology.Method:This study adopted a questionnaire-based, cross-sectional descriptive approach. It used a web questionnaire for data collection over a 5-week period, starting in June 2021.Results:A total of 72.6% of participants indicated that telemedicine is required in the military. The intention to use telemedicine was significantly higher among women, younger individuals (<30 years), and military nurses. In addition, factors such as voluntariness of use, performance expectancy, social influence, and facilitating conditions positively affected the intention to use telemedicine.Conclusions:To improve military doctors' and nurses' use and understanding of telemedicine, consensus must be reached regarding its use in military contexts. Discussions that incorporate opposing views should be encouraged as well. Moreover, the voluntariness of use significantly affected respondents' intention to use telemedicine. There is an urgent need, therefore, for in-depth analyses of the various factors associated with voluntariness of use of telemedicine; the resulting insights could be used to encourage military doctors and nurses to adopt telemedicine. Finally, along with promoting the use of smartphones for medical consultation among military personnel, military nurses' role should be extended to include health consultation using smartphones. This could promote the active use of telemedicine in military nursing, which could contribute to health promotion among military personnel.
Telemedicine Journal and E-Health; https://doi.org/10.1089/tmj.2022.0452
Background:The coronavirus disease 2019 pandemic has expanded noncontact health care systems worldwide. Transcranial direct current stimulation (tDCS) is a noninvasive brain stimulation technology that enables treatment monitoring under remote supervision. We investigated the factors affecting patients' decision to participate in telerehabilitation (TR) using tDCS for motor function recovery after suffering a stroke.Materials and Methods:Four medical institutions surveyed 156 patients with poststroke paralysis. The participants were asked whether they would participate in TR therapy using tDCS in the future. We performed logistic regression analysis to examine the factors—demographic data, stroke characteristics, arm function, gait, and cognitive function—that influenced participants' decisions.Results:Of the participants, 66% (103/156) reported that they would participate in TR using tDCS in the future. Participants' monthly salary was a single significant independent factor influencing their decision to participate. Those earning greater than 5 million KRW (4,000 USD) were more likely to engage in TR via tDCS than those earning less than 1 million KRW (800 USD). The most common barriers to participation in telemedicine included the preference for face-to-face treatment and unfamiliarity. The expected medical expenses of TR using tDCS were 46,154 KRW (37 USD) per session.Conclusions:Most participants with poststroke paralysis responded positively to TR using tDCS for hand function recovery. For telemedicine to work effectively in a situation wherein face-to-face rehabilitation is impossible, prior discussion at the governmental level is essential for determining medical finances.