Comparison of Three Deep Learning Models in Accurate Classification of 770 Dermoscopy Skin Lesion Images.

Accurately determining and classifying different types of skin cancers is critical for early diagnosis. In this work, we propose a novel use of deep learning for classification of benign and malignant skin lesions using dermoscopy images. We obtained 770 de-identified dermoscopy images from the University of Missouri (MU) Healthcare. We created three unique image datasets that contained the original images and images obtained after applying a hair removal algorithm. We trained three popular deep learning models, namely, ResNet50, DenseNet121, and Inception-V3. We evaluated the accuracy and the area under the curve (AUC) receiver operating characteristic (ROC) for each model and dataset. DenseNet121 achieved the best accuracy (80.52%) and AUC ROC score (0.81) on the third dataset. For this dataset, the sensitivity and specificity were 0.80 and 0.81, respectively. We also present the SHAP (SHapley Additive exPlanations) values for the predictions made by different models to understand their interpretability.

Claims data analysis of provider-to-provider tele-mentoring program impact on opioid prescribing in Missouri.

OBJECTIVE: The objective of this study was to assess opioid prescribing patterns of primary care providers (PCPs) participating in a virtual tele-mentoring program for patients with chronic pain as compared to nonparticipants. DESIGN: We utilized Missouri Medicaid claims from 2013 to 2021 to compare opioid prescription dosages and daily supply of opioids prescribed by PCPs. Participants and nonparticipants were matched using propensity score matching. SETTING: Missouri Medicaid data were received through partnership with the Center for Health Policy's MO HealthNet Data Project, the state's leading provider of Medicaid data. PARTICIPANTS: Missouri-based prescribers. INTERVENTION: Show-Me Project Extension for Community Healthcare Outcomes (ECHO), an evidence-based provider-to-provider telehealth intervention that connects PCPs with a team of specialists. MAIN OUTCOME MEASURES: We compared the rate of prescription opioid >50 morphine milligram equivalents (MMEs), mean MMEs/day, and mean number of daily supply to understand the impact of the ECHO model on providers' opioid prescribing. RESULTS: Patients treated by ECHO providers have 33 percent lower odds of being prescribed opioid dose >50 MME/day (p < 0.001) compared to non-ECHO providers. There is also a 14 percent reduction in the average opioid dose prescribed to patients of ECHO providers (p < 0.001). We observed a 3 percent (p < 0.001) reduction in average daily supply of opioids among patients of ECHO providers compared to the comparison group. CONCLUSIONS: Pain Management ECHO supports PCPs with needed education and skills to provide specialty care in the management of pain conditions and safe prescribing of opioid medications.

Closing the gap: Enhancing quality pediatric dermatologic care through project Extension for Community Healthcare Outcomes (ECHO).

This study focused on evaluating Extension for Community Healthcare Outcomes (ECHO) participating primary care clinician's (PCC's) diagnostic and treatment accuracy of pediatric dermatologic conditions. To evaluate this, pediatric cases presented to Dermatology ECHO by PCCs with questions regarding diagnosis, treatment regimen, or both were analyzed. After PCC case presentation, the hub team of dermatologists facilitated case-based discussion and provided the presenter with mentorship and guidance regarding diagnosis and treatment of their patient.

Improving Access to Care for Vulnerable Missourians: The Hotspot Project.

Context: Many rural areas across the country are considered "health and technology desserts." They lack access to healthcare facilities and broadband connectivity for telehealth services. With the emergence of the COVID-19 pandemic and social distancing requirements, rural residents have become even more vulnerable. Purpose: To evaluate the utility of distribution of internet hotspots to rural and underserved Missourians for telehealth access. Methods: Mobile wi-fi devices (hotspots) were distributed to Federally Qualified Healthcare Centers and Community Mental Health Centers to be used by clinics and patients for telemedicine visits through the Missouri Telehealth Network project. We analyzed six sets of surveys from clinic administrators, collected between January and June 2021, to assess usage, technical utility of hotspots, and satisfaction with the project. Findings: A total of 163 (71.5%) survey responses were received. Seventy-seven percent (7,981) of the 10,345 ordered hotspots were distributed. Hotspots were used for video visits, with an average of 5,915.66 monthly visits (range: 3,449 - 8,420). Seven facilities reported technical issues. Open-ended survey responses reported overall satisfaction with the project. The project allowed convenient access to telehealth services for both routine and specialty care, while decreasing patient and staff exposure to COVID-19. Hot-spot service enabled patient access to educational opportunities and providers noticed a decrease in no-shows. Conclusion: The importance of internet connectivity in enabling access and means to care for rural, underserved communities cannot be overemphasized. The hotspot distribution project helped the most vulnerable Missourians access needed care during the public health emergency.

It's Not Always Easy: Cancer Survivorship Care in Primary Care Settings.

By 2040, an anticipated 26.1 million people with a history of cancer will be part of the healthcare system. The purpose of this study was to explore Missouri-based non-oncology clinicians' perspectives on caring for patients with a history of cancer to identify needs of rural-based clinicians to optimize their patients' survivorship care. Using an interpretive qualitative descriptive approach, we conducted semi-structured interviews with 17 non-oncology clinicians. We encouraged clinicians to discuss their approach to caring for patients with a history of cancer and invited them to talk about what might help them increase their knowledge of survivorship care best practices. Through interpretive qualitative descriptive analysis methods including first level coding and constant comparison, we found there is consensus that cancer survivorship care is important; however, training that now guides our clinicians occurred mostly during residency, if at all. Clinicians relied on previous patient encounters and oncology notes combined with their patients' personal account of treatment history to inform the best next steps. Clinicians expressed strong interest in having a simple protocol of their patient's treatment with prompts of known long-term cancer treatment-related effects and a patient-centric follow-up monitoring schedule (mandatory vs recommended vs optional). Clinicians expressed interest in educational opportunities about cancer care and ability for curbside consults with oncologists. They consistently noted the limited resources available in rural areas and that rural patients may have different preferences and approaches to cancer survivorship. There is a clear opportunity to improve non-oncology clinicians' knowledge of the needs of people with a history of cancer as well as their own knowledge base and self-efficacy, especially in rural settings.

Bugs, Bumps, and Bacteria: The Role of Virtual Collaborative Learning Network in Pediatric Dermatology.

Patients in rural and underserved areas face significant barriers in accessing specialty care due to unavailability of services, geographic isolation, travel burden, and other cultural and socioeconomic factors.1 Pediatric dermatology is among the top three subspecialties that provides routine care for pediatric patients, however, shortage and maldistribution of pediatric dermatologists have remained a major hurdle for those living in remote and isolated areas.2 Pediatric dermatologists cluster in urban areas with high-patient volume and estimated wait times for new patients that often exceed 13 weeks, making access one of the major drivers of inequity for rural patients.2-4.

Diagnostic and treatment concordance in primary care participants and dermatologists utilizing Extension for Community Health Outcomes (ECHO).

INTRODUCTION: Suboptimal access to dermatologic care is dependent on patient location and insurance type. Although there have been attempts to address access issues, barriers to providing excellent dermatologic care to all patients at the right time still exist. The objective of this study was to investigate the clinical impact of Dermatology Extension for Community Healthcare Outcomes (ECHO) project participation on primary care providers' diagnostic and treatment tendencies and accuracy. METHODS: This was a retrospective cohort study constructed using Dermatology Extension for Community Healthcare Outcomes case and recommendation data from November 2015 to June 2021. The University of Missouri-based Dermatology Extension for Community Healthcare Outcomes specialty hub team offers regularly scheduled live interactive tele-mentoring sessions for primary care providers who practice in rural and underserved areas. 524 patient cases presented by 25 primary care providers were included in the analysis. Of those, 449 cases were included in diagnostic concordance, and 451 in treatment concordance analysis. RESULTS: Less than 40% of all diagnoses were fully concordant with an expert panel. Over 33% of patients were misdiagnosed, and over 26% received partially correct diagnosis. Only 16% of all treatment recommendations were fully concordant with an expert panel. DISCUSSION: Diagnostic and treatment accuracy of participants is low, and Dermatology Extension for Community Healthcare Outcomes platform ensured patients received correct diagnosis and treatment quickly. Although tele-dermatology models are effective, they continue to be underutilized. Dermatologists in practice and training should be encouraged to adopt innovative clinical educational models, like Dermatology ECHO, to expand access to dermatologic expertise for the most marginalized populations.

Community Case Study: The Role of Live-Interactive Learning Network in Addressing Community Wide Information Needs Through Show-Me COVID-19 ECHO.

After the COVID-19 pandemic reached Missouri, the Show-Me ECHO (Extension for Community Healthcare Outcomes) project initiated COVID-19 ECHO virtual knowledge-sharing networking sessions. These live-interactive weekly sessions inform participants about up-to-date evidence-based recommendations and guidelines through expert didactic lectures followed by real-life case discussions. We conducted a qualitative analysis of pre-session surveys and questions asked during sessions to learn about information needs of community members during first months of public health emergency. This was a pilot project using qualitative analysis of registration questions regarding anticipated COVID-19 community information needs, and participants' questions asked during sessions collected from March 23 until May 4, 2020. We also analyzed participants' satisfaction surveys collected in December 2020. A total of 761 unique participants attended COVID-19 ECHO during the study period. Survey was completed by 692 respondents. Participants asked 315 questions resulting in 797 identified community information needs. Five thematic categories were recognized: patient care, information seeking, minimizing exposure, financial themes, and general comments. Most attendees rated content quality, logistics, and technical operations as good or excellent on a five-point Likert scale. The COVID-19 ECHO model was responsive to the needs of participants by sharing and discussing up-to-date recommendations and guidelines regarding COVID-19. Sessions were well-attended, and the didactic presenters were invited to deliver same or similar presentations at Boone County Medical Society (BCMS) weekly seminars, suggesting the value of the project to healthcare providers and other community members caring for or working with the most vulnerable populations.

Melanoma Extension for Community Healthcare Outcomes: A Feasibility Study of Melanoma Screening Implementation in Primary Care Settings.

Introduction Melanoma incidence rates are rising faster than the rates of any other malignancy. As a major global public health concern, melanoma can be identified by a visual exam not requiring expensive invasive procedures. However, non-dermatologists lack specialized training and skills to identify high-risk patients and implement melanoma skin screenings during regular exams. Most patients from rural and underserved areas have inadequate access to specialty dermatologic care, which can potentially lead to later-stage melanomas and poor patient outcomes. The objective of this study was to identify facilitators and barriers to the implementation of risk surveys and melanoma skin screenings in primary care settings through live interactive education and the telementoring project - Melanoma ECHO (Extension for Community Healthcare Outcomes).  Methods This cross-sectional study was designed with theoretical concepts from dissemination and implementation research. Monthly Melanoma ECHO sessions were integrated into an ongoing Dermatology ECHO at the University of Missouri, Columbia, Missouri, USA, from April 2018 to February 2019. Ten primary care providers, medical doctors/doctors of osteopathic medicine (MDs/DOs), nurse practitioners (NPs), and physician assistants (PAs), from across Missouri participated. Eleven virtual monthly melanoma-related didactics and case-based discussions were provided to participants. Information regarding risk factors, risk surveys, and screening techniques was provided. Ongoing telementoring and guidance were also provided for de-identified real-life patient cases. The main outcomes and measures of the study were to identify the facilitators and barriers of risk survey and melanoma skin screenings in primary care settings and to quantify the number of high-risk patients identified by participating providers and the number of new melanomas detected by visual exams during the study period. Results The primary reason why six out of 10 providers reported participation in Melanoma ECHO was that implementing melanoma skin screenings in their practice was made easier as it increased their confidence. Nine providers reported increased knowledge, and eight cited professional networking as other facilitators. The main perceived barrier to melanoma skin screening was lack of administrative and nursing support, and six providers indicated that lack of time to incorporate skin exams was also a barrier. Combined, ten participants reported identifying 976 high-risk patients during the study period and detecting 36 new melanomas. Discussion and conclusion Our findings indicate that primary care providers may benefit from attending regularly scheduled and focused specialized telementoring sessions, such as Melanoma ECHO. Ongoing support from specialists may help providers practicing in rural and isolated areas with the successful integration of risk surveys and melanoma skin screenings in primary care settings. Further Melanoma ECHO sessions with a more diverse group of primary care providers are needed to better understand the generalizability of the results.

Patient and Provider Satisfaction With Pediatric Urology Telemedicine Clinic.

The use of telemedicine continues to grow as more patients are receptive to this innovative way of providing health care. Multiple publications in telemedicine indicated high satisfaction for this service. This study focuses on the use of telemedicine in a pediatric urology clinic and examines 3 research questions: (1) How did patients' parents/guardians feel about their video appointments? (2) What were the experiences of novice telemedicine providers conducting postsurgical appointments via video? and (3) How did novice telemedicine providers' experiences compare to those of expert telemedicine providers?

Similarities and Differences Between Rural and Urban Telemedicine Utilization.

Telemedicine has traditionally been used in rural areas, but the recent development of mHealth solutions has led to a growth in urban telemedicine services. The aim of this study was to determine whether urban and rural patients in a large academic medical center use telemedicine to access different healthcare specialties at different rates. This retrospective cohort study examined all telemedicine visits dated 2008-2017 at a large academic medical center. Visits were classified by clinical specialty. Teledermatology, child telepsychiatry, and adult telepsychiatry made up 97 percent of telemedicine visits. Rural patients were more likely to have multiple telehealth visits. A significant difference was observed between rural and urban use of telemedicine, both in terms of specialties and demographics. This suggests that health systems should consider adjusting resources and training to meet the different needs of these two populations. In particular, telemedicine may offer help for the nationwide maldistribution of adolescent psychiatry providers.

Utility of Dermatology Extension for Community Healthcare Outcomes (ECHO) sessions in the adult and paediatric population.

INTRODUCTION: Primary care provider (PCP) competency in dermatology is inadequate despite the high volume of patients with skin conditions. Better education and access to dermatology expertise is vital to improve patient care. We present a comprehensive case-based evaluation of Dermatology Extension for Community Healthcare Outcomes (ECHO) sessions, an innovative videoconferencing educational model, by determining the diagnostic and treatment accuracy of dermatological conditions by PCPs over a 2-year period. METHODS: This is a retrospective cross-sectional study evaluating the use and impact of Dermatology ECHO over a 2-year period. Outcomes assessed include patient demographics, PCPs' diagnostic accuracy, and expert treatment impact. Results were analysed using summary statistics and Pearson's chi-square test to describe the adult and paediatric populations. RESULTS: One hundred and sixty-seven adult cases and 56 paediatric cases were presented in 2016-2017. Among the 223 cases, 137 adult and 44 paediatric cases were complete and eligible for analysis. The mean lesion duration was 3.3 years in adults and 2.9 years in children prior to presentation. Upon case presentation, almost half (43.8%) of the adult cases were incorrectly diagnosed by their PCP with 18.8% receiving a partially correct diagnosis. PCPs had greater diagnostic accuracy in children (45% correct diagnosis, 27.5% partially correct, 27.5% incorrect). Expert treatment recommendations benefited 83.6% of adult cases and 72.5% of paediatric cases. DISCUSSION: This study highlights the need for better dermatology access and teaching opportunities among PCPs in Missouri. Dermatology ECHO provides a platform for didactic learning and case presentations to improve dermatology competency among PCPs.

ECHO Autism: Evaluation of Participants' Perceptions of Collaborative Telementoring Network.

Introduction: Primary care clinicians report inadequate training and lack of support regarding identification of early signs of Autism Spectrum Disorder (ASD), resulting in later diagnosis and poor outcomes. The objective of this study was to evaluate the perception of participants in ECHO Autism project regarding the value of the virtual collaborative as a mentoring tool. Methods: We completed a retrospective cross-sectional study of post-virtual clinic surveys of all participants who attended Autism ECHO from September 2, 2015 to June 5, 2019. Results: There were 87 Autism ECHO sessions held, with 83 didactic presentations. A total of 92 de-identified patient cases were discussed with 490 unique learners in attendance. Participants reported increase in self-efficacy in identifying ASD symptoms in children, assessing medical comorbidities, and learning new information. Discussion: Continuing education platforms in healthcare professions are increasingly embracing virtual live-interactive conferences. They provide opportunities to connect with experts, but also hear from peers regarding real-life case examples. During COVID-19 pandemic ECHO Autism was a lifeline for rural providers and will likely continue to increase in participation.

The Influence of Telehealth for Better Health Across Communities.

Rapid spread of coronavirus disease 2019 (COVID-19) forced an abrupt shift in the traditional US health care delivery model to meet the needs of patients, staff, and communities. Through federal policy changes on telehealth, patient care shifted from in-person to telephone or video visits, and health care providers reached out to patients most at risk for exacerbation of chronic disease symptoms. ECHO (Extension for Community Healthcare Outcomes), a videoconferencing peer learning application, engaged health care providers across Missouri in the treatment and management of complex COVID-19-positive patients. Re-envisioning health care in the digital age includes robust utilization of telehealth to enhance care for all.

Accelerating Care Through ECHO: Case Examples from the Field.

In this article, we describe three life-changing patient cases demonstrating high-quality and timely care they received in their communities, thanks to the Show-Me ECHO project. Early autism diagnosis, a potentially deadly tumor manifesting as a benign-looking rash, a recalcitrant case of hepatitis C: rural and underserved Missourians now have access to state-of-the-art care through their local providers receiving interdisciplinary telementoring on evidence based practices.

Assessing Impact of Show-Me ECHO on the Health of Missourians: Two Examples.

Show Me ECHO is a model for interprofessional collaboration that utilizes telehealth technologies to share evidence-based medical knowledge to improve patient outcomes and minimize variation in care for underserved populations. To measure ECHO outcomes, Show Me ECHO develops both an evaluation of clinical outcomes for patients as well as assessing learner outcomes on the Kirkpatrick Typology of Evaluation. This paper describes evaluation models for Dermatology and Childhood Asthma ECHOs.

Telehealth and Telemedicine in Missouri.

Missouri is a national leader in telemedicine, and the Missouri Telehealth Network has led operational, legal and regulatory, and research and evaluation efforts since 1994. Telehealth and telemedicine have the potential to increase access to and efficiency of healthcare delivery, improve quality, and improve patient outcomes. Coverage and reimbursement rules vary by regulator, and Missouri enjoys a broad statutory definition of telehealth coverage and reimbursement parity (no distinction between in-person and telehealth services).

Evaluation of Patient Perceptions With Orthopedic Oncology Telehealth: A Pilot Project.

Telehealth has been used for decades to improve access to care for rural and underserved patients. The adoption of telehealth in orthopedic oncology is novel and expected to positively impact patient access and compliance. However, no previous evaluation has been published of this expected impact. The objective of this pilot project was to evaluate patients' perceptions regarding orthopedic oncology telehealth services. A 13-question satisfaction survey was distributed to patients who used tele-orthopedic oncology. Fifteen respondents (a response rate of 42%) reported satisfaction with services at 9.7 of 10. Median travel distance to the nearest in-person orthopedic oncologist was greater than 150 miles (241 km). These results are consistent with the previous findings of high satisfaction with telehealth in other specialties. Health care organizations are likely to benefit from offering telehealth to orthopedic oncology patients with limited access.