Presentations to emergency departments in Melbourne, Australia diagnosed as allergic contact dermatitis.

BACKGROUND: This study investigated cases diagnosed as allergic contact dermatitis (ACD) in emergency departments (EDs) and management. METHODS: A multisite retrospective study of patients attending EDs in metropolitan Melbourne between July 2017 and June 2018 was performed. Using International Statistical Classification of Disease-10 (ICD-10) codes, the Victorian Agency for Health Information generated a list of cases of contact dermatitis (CD). Demographic and clinical data were analysed. RESULTS: Two hundred twenty-eighty patients from 14 different sites were diagnosed with ACD. Hair dyes caused the most cases, and one such case was admitted to hospital. It was apparent from the specified causes that cases of irritant CD were misdiagnosed as ACD. There were significant differences in management with dermatology input, with dermatologists more often advising oral corticosteroids (33.3% vs. 14.5%, P = 0.004) topical corticosteroids (92.9% vs. 38.7%, P < 0.01), emollients (38.1% vs. 20.4%, P = 0.01) and less often advising antihistamines (16.7% vs. 44.6%, P < 0.001). With dermatology input, potent or very potent steroids were more likely to be prescribed (69.3% vs. 11.1%, P < 0.001); without, a mild potency steroid was more likely to be prescribed (63.9% vs. 4%, P = 0.01). CONCLUSION: Improved understanding, diagnosis and management of CD are needed in EDs.

Improving Skin cancer Management with ARTificial Intelligence (SMARTI): protocol for a preintervention/postintervention trial of an artificial intelligence system used as a diagnostic aid for skin cancer management in a specialist dermatology setting.

INTRODUCTION: Convolutional neural networks (CNNs) can diagnose skin cancers with impressive accuracy in experimental settings, however, their performance in the real-world clinical setting, including comparison to teledermatology services, has not been validated in prospective clinical studies. METHODS AND ANALYSIS: Participants will be recruited from dermatology clinics at the Alfred Hospital and Skin Health Institute, Melbourne. Skin lesions will be imaged using a proprietary dermoscopic camera. The artificial intelligence (AI) algorithm, a CNN developed by MoleMap Ltd and Monash eResearch, classifies lesions as benign, malignant or uncertain. This is a preintervention/postintervention study. In the preintervention period, treating doctors are blinded to AI lesion assessment. In the postintervention period, treating doctors review the AI lesion assessment in real time, and have the opportunity to then change their diagnosis and management. Any skin lesions of concern and at least two benign lesions will be selected for imaging. Each participant's lesions will be examined by a registrar, the treating consultant dermatologist and later by a teledermatologist. At the conclusion of the preintervention period, the safety of the AI algorithm will be evaluated in a primary analysis by measuring its sensitivity, specificity and agreement with histopathology where available, or the treating consultant dermatologists' classification. At trial completion, AI classifications will be compared with those of the teledermatologist, registrar, treating dermatologist and histopathology. The impact of the AI algorithm on diagnostic and management decisions will be evaluated by: (1) comparing the initial management decision of the registrar with their AI-assisted decision and (2) comparing the benign to malignant ratio (for lesions biopsied) between the preintervention and postintervention periods. ETHICS AND DISSEMINATION: Human Research Ethics Committee (HREC) approval received from the Alfred Hospital Ethics Committee on 14 February 2019 (HREC/48865/Alfred-2018). Findings from this study will be disseminated through peer-reviewed publications, non-peer reviewed media and conferences. TRIAL REGISTRATION NUMBER: NCT04040114.

Dermatological services; patient profiling in a rural tertiary hospital.

BACKGROUND/OBJECTIVES: There is a paucity of research available regarding the epidemiology of patients attending dermatology outpatient services in Australia. Our objective was to analyse who was attending public dermatology outpatient clinics in a Northern Territory tertiary hospital, with a particular focus on Indigenous and rural patients. METHODS: This is a retrospective cohort study of patients who attended dermatology outpatient clinics between 1 January 2016 and 31 December 2016. Outcome measures included patient demographics (age, gender, ethnicity and postcode) and referrer details. RESULTS: Over the 12 month study period, 923 appointments were scheduled for 500 patients. Of the appointments scheduled, 667 were attended. Twelve per cent of patients were Indigenous, and of the total appointment attendances, 10% were by Indigenous patients. Of the 923 appointments, 28% were not attended, with a higher non-attendance rate for Indigenous patients at 36%. The majority of patients seen were adults, for both groups, but a larger proportion of Indigenous children were seen. Nine per cent of patients with a recorded address were from a remote region. CONCLUSION: Dermatology outpatient services are likely under-utilised by Indigenous, and remote patients. If we are to improve skin health in Australia, barriers such as limited access to dermatological services in remote regions must be addressed.

The Importance of Incorporating Human Factors in the Design and Implementation of Artificial Intelligence for Skin Cancer Diagnosis in the Real World.

Artificial intelligence (AI) algorithms have been shown to diagnose skin lesions with impressive accuracy in experimental settings. The majority of the literature to date has compared AI and dermatologists as opponents in skin cancer diagnosis. However, in the real-world clinical setting, the clinician will work in collaboration with AI. Existing evidence regarding the integration of such AI diagnostic tools into clinical practice is limited. Human factors, such as cognitive style, personality, experience, preferences, and attitudes may influence clinicians' use of AI. In this review, we consider these human factors and the potential cognitive errors, biases, and unintended consequences that could arise when using an AI skin cancer diagnostic tool in the real world. Integrating this knowledge in the design and implementation of AI technology will assist in ensuring that the end product can be used effectively. Dermatologist leadership in the development of these tools will further improve their clinical relevance and safety.

Overdiagnosis of scabies and overprescribing of scabies treatment in a scabies-endemic region.

OBJECTIVE: To assess the objective evidence upon which diagnosis of scabies and subsequent prescription of permethrin cream or oral ivermectin is based at a tertiary referral hospital in the Northern Territory. DESIGN, SETTING AND PARTICIPANTS: A retrospective cohort study of inpatients who were prescribed permethrin or ivermectin between July and September 2017 at a single tertiary referral hospital. Eighty-eight inpatient admissions, belonging to 77 unique patients, were included. This list was generated with the hospital's electronic prescribing software. MAIN OUTCOME MEASURES: Age, ethnicity, skin diagnosis on admission, which anti-scabies medications were prescribed, which concurrent medications were prescribed to treat a rash or pruritus, which differential or concurrent skin diagnoses were made, whether the dermatology department had seen the patient during their admission, and what evidence was documented as reason for diagnosis of scabies. RESULTS: In the cases in which scabies treatment was prescribed, less than one quarter had positive skin scrapings for scabies, and few had documentation of burrows, and documentation of a contact history combined with clinical lesions. Most cases met none of these diagnostic criteria. Very few were reviewed by the dermatology department as an inpatient. CONCLUSIONS: There were likely high rates of diagnostic uncertainty among the cases in which scabies treatment was prescribed. It is possible that anti-scabies medications are being prescribed empirically in this hospital.

Allergic contact dermatitis in children and proposal for an Australian Paediatric Baseline Series.

BACKGROUND: Allergic contact dermatitis (ACD) is an increasingly common diagnosis in children. The objectives of this study were to review our experience with ACD in children in tertiary settings, to ascertain the spectrum of allergens in this population and to subsequently propose the first Australian Paediatric Baseline Series for patch testing. METHODS: We conducted a retrospective analysis of patch test data from 1993 to 2017 from two tertiary referral patch-testing centres in Melbourne, Victoria. RESULTS: A total of 511 children were patch tested during the study period. Of these, 58.3% (298/511) of children tested had a positive patch test, and 65.1% (194/298, or 38.0% of the total) had a relevant positive patch test. The most common relevant patch test reactions were fragrance mix, methylchloroisothiazolinone/methylisothiazolinone (MCI/MI) and methylisothiazolinone (MI), Myroxylon pereirae, nickel sulphate, and colophonium. CONCLUSION: Allergic contact dermatitis is not uncommon in children, and patch testing should be considered in children with suspected ACD or with recalcitrant atopic dermatitis. Based on our experience over 25 years, we propose the first Australian Paediatric Baseline Series.

The Vulval Disease Quality of Life Index in women with vulval lichen sclerosus correlates with clinician and symptom scores.

BACKGROUND/OBJECTIVES: The Vulval disease Quality of Life Index (VQLI) is a new tool that assesses the burden of vulval disease on quality of life (QoL). Our objective was to assess the correlation between VQLI score and clinician-rated severity scores, overall patient itch/discomfort, disease duration, sexual activity, and age, in vulval lichen sclerosus (VLS) at a vulval disorders clinic. METHODS: A retrospective case note review, including consecutive women with VLS who attended the clinic between April and October 2018. Outcome measures include the VQLI score, clinician-rated severity score, and patient symptom score. RESULTS: A total of 109 women with VLS were included. On multivariable analysis, there was evidence of a positive relationship between VQLI scores and the total clinician-rated score (mean increase in VQLI score per unit increase in clinician score 1.34, 95% confidence interval [CI] 0.31, 2.38; P = 0.01); the relationship was stronger for the cutaneous component. There was little evidence for relationships of the VQLI with the patient's age, sexual activity or time since onset of symptoms. There was strong evidence for a positive relationship between VQLI score and overall itch/discomfort score (mean increase 2.38, 95% CI 1.88, 2.88; P < 0.001). New and follow-up data were obtained on sequential visits for 12 women, among whom the VQLI score dropped a mean -2.75 points between visits (95% CI -6.05, 0.55; P = 0.094). CONCLUSION: The clinician-rated severity correlates with the impact of VLS on QoL. The VQLI captures information included in a patient itch/discomfort score, which can be easily incorporated into routine assessment.