Results of a pilot optional e-triage teledermatology advice and guidance pathway for equivocal lesions as an alternative to 2-week wait referrals in two large general practitioner networks in a city

In our hospital we receive about 200 skin 2-week wait (2WW) referrals weekly. This is a huge burden on local services. Many of these patients are discharged at the first appointment, and, for a significant proportion of referrals, the 'level of cancer concern' on the general practitioner (GP)-provided 'suspected skin cancer referral form' is rated: 'I'm unsure, it might well be cancer but there are other equally plausible explanations'. In collaboration with secondary care and community stakeholders, an innovative pilot using an optional teledermatology advice and guidance process (A&G) was implemented as a complementary pathway for patients in two large GP practice networks. Conventional 2WW faceto- face referrals could be initiated as normal;however, at the GP's discretion an alternative teledermatology e-triage A&G pathway was introduced for lesions equivocal for malignancy. A model where healthcare assistants (HCAs) maintained a weekly clinic in each of the practices was designed and implemented. The HCA received training and undertook a lesion history via proforma and macroscopic and dermatoscopic photographs, which were subsequently uploaded to the National Health Service e-referral service. A consultant dermatologist reviewed the A&G e-triage request within 72 h and either provided advice or recommended 2WW referral, which was then actioned via the outpatient appointment centre, without further need for GP action. The pilot commenced in November 2021. Over 2 months (November-December 2021 inclusive) 101 e-triage A&G requests were made and 212 conventional 2WW face-to-face referrals. Of the A&G e-triage requests 70 (69.3%) were returned with advice and the patient did not require onward referral. In total 70/313 (22.4%) of the skin lesion episodes were retained in primary care with advice. Since the initiation of the pilot, there are signs that A&G requests and 2WW referrals are changing, with increased uptake in A&G e-triage. Comparing the referral behaviours of the two practice networks before and after the pilot is a challenge given the short period of the pilot and the event of COVID-19 on referral patterns. However, in November- December 2019 (pre-community COVID-19 in the UK), the two practices sent 201 2WW referrals juxtaposed with 212 intrapilot (November-December 2021). This demonstrates a more sustainable number of 2WW referrals and in keeping with previous levels at a period when locally skin 2WW referrals are increasing. Fiscally, given that many of the A&G e-triage requests would have resulted in a face-to-face 2WW referral a cost saving has been made. Our interim data demonstrate the development and implementation of an optional A&G e-triage pathway as an alternative approach for equivocal lesions and it has resulted in retention of 22.4% of would-be 2WW referrals in primary care. Community stakeholders and engagement has been crucial for the project. Our 6-month pilot data will be presented.

Deep learning-based voice screening technique for cystic fibrosis related diabetes

Background: Cystic fibrosis-related diabetes (CFRD) is a unique type of diabetes that is associated with significantly increased morbidity and mortality in both children and adults with cystic fibrosis (CF). The prevalence of CFRD progressively increases with age such that more than half of adults with CF develop CFRD. Early diagnosis and treatment are associated with improvements in body weight and pulmonary function, reduction in the frequency of pulmonary exacerbations, and improved overall survival. Since patients with CFRD may present with no symptoms, screening is recommended starting from the age of 10 years with an annual oral glucose tolerance test (OGTT). Especially during the COVID-19 pandemic, requiring an in-person clinic visit can be challenging, which may lead to a delayed diagnosis of CFRD. Objectives: The purpose of this project was to develop a state-of-the-art technique to detect changes in glucose levels of patients with CF by developing a deep learning-based audio classification tool. Preliminary work by our group suggested that voice characteristics could distinguish between patients with CFRD patients and patients with CF but without CFRD. We hypothesize that high blood glucose levels may cause laryngeal soft tissue swelling leading to changes in voice characteristics. Methods: We performed a prospective cross-sectional study in adult patients with CF recruited from Emory CF Clinic from March to December 2021. We recorded 5-second voice samples of a sustained /a/ vowel via a portable digital microphone. The spectrogram was extracted via the Mel frequency cepstral coefficient. The training to test the dataset ratio was 80: 20. 20% of the training dataset were randomly selected to serve as a validation dataset. We designed a convolutional neural network (CNN) architecture for CFRD patients’ voice classification. Results: There were a total of 100 subjects consisting of 43 patients with CFRD and 57 patients with CF without diabetes. The male to female ratio was approximately 60: 40 in both groups. Patients with CFRD had similar mean age and mean BMI to patients without CFRD. There was a significantly higher point of care glucose level in CFRD patients. The mean duration of a CFRD diagnosis was 9 years and the mean HbA1c level was 7.26 in the CFRD group. The performance of the VGG model CNN classifier achieved 98.7% and 94.92% accuracy on training and validation datasets, respectively. On the test dataset, the model achieved 73.53% sensitivity 69.77% specificity and 71.43% accuracy. Conclusions: We found a deep learning-based audio screening tool for CFRD could be potentially used as an alternative tool for screening in the CF community. A convolutional neural network algorithm demonstrated high sensitivity and specificity to adequately differentiate between patients with and without CFRD. Larger prospective studies are required to test this technology in patients with every form of diabetes.Presentation: Sunday, June 12, 2022 12:15 p.m. - 12:30 p.m.

Case Report: Acute Abdominal Pain as Presentation of Pneumonia and Acute Pancreatitis in a Pediatric Patient With COVID-19.

Abdominal pain, nausea, and vomiting are known gastrointestinal symptoms of symptomatic SARS-CoV-2 infection (COVID-19 disease) in pediatric patients.1 There is little literature regarding pancreatitis in COVID-19. We describe a 16-year-old male diagnosed with acute pancreatitis in the setting of a SARS-COV-2 infection and associated fluid balance considerations.

Severe SARS-CoV-2 disease in the context of a NF-κB2 loss-of-function pathogenic variant.

BACKGROUND: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a novel coronavirus that emerged recently and has created a global pandemic. Symptomatic SARS-CoV-2 infection, termed coronavirus disease 2019 (COVID-19), has been associated with a host of symptoms affecting numerous organ systems, including the lungs, cardiovascular system, kidney, central nervous system, gastrointestinal tract, and skin, among others. OBJECTIVE: Although several risk factors have been identified as related to complications from and severity of COVID-19, much about the virus remains unknown. The host immune response appears to affect the outcome of disease. It is not surprising that patients with intrinsic or secondary immune compromise might be particularly susceptible to complications from SARS-CoV-2 infection. Pathogenic loss-of-function or gain-of-function heterozygous variants in nuclear factor-κB2 have been reported to be associated with either a combined immunodeficiency or common variable immunodeficiency phenotype. METHODS: We evaluated the functional consequence and immunologic phenotype of a novel NFKB2 loss of function variant in a 17-year-old male patient and describe the clinical management of SARS-CoV-2 infection in this context. RESULTS: This patient required a 2-week hospitalization for SARS-CoV-2 infection, including 7 days of mechanical ventilation. We used biologic therapies to avert potentially fatal acute respiratory distress syndrome and treat hyperinflammatory responses. The patient had an immunologic phenotype of B-cell dysregulation with decreased switched memory B cells. Despite the underlying immune dysfunction, he recovered from the infection with intense management. CONCLUSIONS: This clinical case exemplifies some of the practical challenges in management of patients with SARS-CoV-2 infection, especially in the context of underlying immune dysregulation.

Streamlining patient referrals and clearing the dermatology non-2-week-wait waiting list using trainee-led teledermatology

Amidst the COVID-19 pandemic, the National Health Service (NHS) faced unprecedented changes to patient care, with specialties having to adapt using technology. At the outset of the pandemic our dermatology department already had a waiting list of > 800 new patient referrals [excluding 2-week-wait (2WW) patients], owing to the impending release of a new electronic patient record ('MyCare') platform. By redesigning pathways and reallocating surgical resources to remote consultation clinics we observed a paradoxical explosion in efficiency. Within 10 weeks of the onset of 'lockdown' we had virtually cleared the waiting list to 18 patients (which had peaked at 950 patients), using a combination of teledermatology, telephone clinics and video consultations. A solution was devised by consensus in the department. Urgent cases and possible [non-basal cell carcinoma (BCC)] cancers were still seen face to face. However, all other appointments became virtual, using telephone consultations and emailing photographs in a patient-directed store-and-forward approach. Where surgical lists for non-urgent BCC surgery had been cancelled, clinicians were allocated remote-consultation clinics, with temporal and geographical flexibility for delivery within their current job plans. Patients were invited to send skin photographs to a shared departmental NHS.net account that was initiated by trainees, to supplement telephone consultations where required. Quality was assisted by explaining simple photography techniques in a default email signature (https://www.bad.org.uk/shared/get-file.as#x?itemtype=document&id =5818). The issue of consent was managed practically for the majority;the act of sending a photograph inherently implied consent. Where necessary, patients had the option of signing a bespoke teledermatology consent form sent as an email attachment, enabling images to be saved to their medical record if required. Additional resources of benefit include Attend Anywhere video consultations, and M-modal digital dictation. Furthermore, to manage new patients referred after onset of the pandemic, Consultants are e-triaging all non-2WW referrals through e-RS using a Referral Assessment Service - with e-RS Advice and Guidance being used routinely, too. Teledermatology during the COVID-19 pandemic has not only compensated, but has also highlighted some advantages over traditional patient pathways. Clinicians and patients alike quickly acknowledged that a telephone call could often suffice, if not preferable to meeting in person. With a large catchment area, many patients were pleased to avoid the long journeys. COVID-19 catapulted everyone into unchartered territories, posing innumerable obstacles in delivering good patient care. With simple measures, we emerged having tackled our already inflated pending list. What is more, the delivery of traditional model of care was questioned. Who knew you could see a dermatologist over the phone?