Assessing the Utility of Multimodal Large Language Models (GPT-4 Vision and Large Language and Vision Assistant) in Identifying Melanoma Across Different Skin Tones.

The large language models GPT-4 Vision and Large Language and Vision Assistant are capable of understanding and accurately differentiating between benign lesions and melanoma, indicating potential incorporation into dermatologic care, medical research, and education.

Vulval dermatoses: A review of referrals to dermatology.

We undertook a retrospective observational review of patients referred to a tertiary dermatology department with vulval complaints over 12 months. The most common provisional diagnoses made by the referrer and final dermatology diagnoses were lichen sclerosus (54% and 38%), dermatitis (12.7% and 16.5%) and psoriasis (5.1% and 6.3%). Referrers may benefit from further education about skin diseases of the vulva, topical steroids for vulval complaints and the importance of clinical photography.

Using Artificial Intelligence as a Melanoma Screening Tool in Self-Referred Patients.

INTRODUCTION: Early detection of melanoma requires timely access to medical care. In this study, we examined the feasibility of using artificial intelligence (AI) to flag possible melanomas in self-referred patients concerned that a skin lesion might be cancerous. METHODS: Patients were recruited for the study through advertisements in 2 hospitals in Halifax, Nova Scotia, Canada. Lesions of concern were initially examined by a trained medical student and if the study criteria were met, the lesions were then scanned using the FotoFinder System®. The images were analyzed using their proprietary computer software. Macroscopic and dermoscopic images were evaluated by 3 experienced dermatologists and a senior dermatology resident, all blinded to the AI results. Suspicious lesions identified by the AI or any of the 3 dermatologists were then excised. RESULTS: Seventeen confirmed malignancies were found, including 10 melanomas. Six melanomas were not flagged by the AI. These lesions showed ambiguous atypical melanocytic proliferations, and all were diagnostically challenging to the dermatologists and to the dermatopathologists. Eight malignancies were seen in patients with a family history of melanoma. The AI's ability to diagnose malignancy is not inferior to the dermatologists examining dermoscopic images. CONCLUSION: AI, used in this study, may serve as a practical skin cancer screening aid. While it does have technical and diagnostic limitations, its inclusion in a melanoma screening program, directed at those with a concern about a particular lesion would be valuable in providing timely access to the diagnosis of skin cancer.

Timeliness of diagnosis and treatment of cutaneous melanoma with dermatology, general practice, plastics surgery collaboration - are we meeting standards?

Introduction Melanoma is a serious type of skin cancer with a high burden in New Zealand. MelNet Quality Statements (2021) guide the timeliness of investigations and management for melanoma patients, who might experience long delays waiting for treatment. Aim To assess compliance of melanoma diagnosis and treatment timeliness with the MelNet Quality Statements at Waikato Hospital and in primary care for melanoma and melanoma in situ (MIS). Methods This is a retrospective clinical audit of patients referred via the Suspected Skin Cancer (SSC) teledermatology pathway between June 2020 and June 2022, and histologically confirmed as having melanoma or MIS. Time intervals between elements of service were analysed. Results For 43 melanomas and 105 MIS, compliance with MelNet Quality Statements across all melanoma services was poor, except for teledermatology response rates (100% compliance). From referral to first cancer treatment (Statement 2.1.1), compliance was 50% in general practice and 7.7% in Waikato Hospital. From teledermatologist response to biopsy (Statement 2.1.3), compliance was 65.2% in general practice and 7.7% in hospital plastics department. Histopathological reporting delays were also identified. Discussion Long delays for melanoma care in hospital likely reflect system failures (such as inadequate funding and human resources) and the increasing burden of skin cancer. In contrast, primary care provided quicker diagnostic biopsies and surgical treatments for melanoma.

Teledermatology for Enhancing Skin Cancer Diagnosis and Management: Retrospective Chart Review.

BACKGROUND: Skin cancer rates are at all-time highs, but the shortage of dermatologists compels patients to seek medical advice from general practitioners. A new referral pathway called the Suspected Skin Cancer (SSC) service was established to provide general practitioners in Waikato, New Zealand, with rapid diagnosis and treatment advice for lesions suspicious for skin cancer. OBJECTIVE: The aim of this study was to assess the quantity, quality, and characteristics of referrals to the SSC teledermatology service during its first 6 months. METHODS: A retrospective chart review of all referrals sent to the SSC teledermatology service during the first 6 months of its operation was conducted. Time to advice, diagnoses, diagnostic discordance, adherence to advice, and time to treatment were recorded. Diagnostic discordance between general practitioners, dermatologists, and pathologists was calculated. RESULTS: The SSC service received 340 referrals for 402 lesions. Dermatologists diagnosed 256 (63.7%) of these lesions as benign; 56 (13.9%) were histologically confirmed as malignant, including 19 (4.7%) melanomas. The overall discordance between referrer and dermatologist on specific and broad (ie, benign or malignant) diagnoses for 402 lesions was 47% and 26% (κ=0.58, SD 0.07), respectively; 44% and 26% (κ=0.61, SD 0.15) between referrer and pathologist; and 18% and 12% (κ=0.82, SD 0.12) between dermatologist and pathologist. The mean time between referral submission and receiving advice was 1.02 days. The average time to action (eg, excision) was 64.8 days. CONCLUSIONS: An electronic referral system can be an effective form of teledermatology for providing prompt diagnosis and management advice for benign and malignant skin lesions.

Store-and-Forward Teledermatology for Assessing Skin Cancer in 2023: Literature Review.

BACKGROUND: The role of teledermatology for skin lesion assessment has been a recent development, particularly, since the COVID-19 pandemic has impacted the ability to assess patients in person. The growing number of studies relating to this area reflects the evolving interest. OBJECTIVE: This literature review aims to analyze the available research on store-and-forward teledermatology for skin lesion assessment. METHODS: MEDLINE was searched for papers from January 2010 to November 2021. Papers were searched for assessment of time management, effectiveness, and image quality. RESULTS: The reported effectiveness of store-and-forward teledermatology for skin lesion assessment produces heterogeneous results likely due to significant procedure variations. Most studies show high accuracy and diagnostic concordance of teledermatology compared to in-person dermatologist assessment and histopathology. This is improved through the use of teledermoscopy. Most literature shows that teledermatology reduces time to advice and definitive treatment compared to outpatient clinic assessment. CONCLUSIONS: Overall, teledermatology offers a comparable standard of effectiveness to in-person assessment. It can save significant time in expediting advice and management. Image quality and inclusion of dermoscopy have a considerable bearing on the overall effectiveness.

Benign Keratosis: A Useful Term?

INTRODUCTION: Seborrheic keratosis (SK), lichen planus-like keratosis (LPLK), and solar lentigo (SL) are common benign skin lesions. These lesions are frequently seen adjacent to each other or can arise from one another. They can sometimes be difficult to differentiate despite having distinct histopathological features. OBJECTIVES: We evaluated dermoscopic images of 80 skin lesions to confirm the term 'benign keratosis' is useful for an undifferentiated SK/LPLK/SL where there are overlapping clinical and dermoscopic characteristics. METHODS: Clinical and dermoscopic images were sourced from a teledermoscopy service database of 13,000 lesions in 7,000 patients. The database was queried for SK, SL or LPLK in sun-exposed sites. Each lesion was evaluated based on specific dermoscopic criteria and the results analyzed. RESULTS: Lesions were identified with mixed clinical and dermoscopic criteria of SK and SL, and in some, dermoscopic criteria for LPLK were also present. CONCLUSIONS: This study highlights the relationship between these lesions. We confirm the term 'benign keratosis' is useful for mixed lesions or for those that are difficult to classify.

Cutaneous adverse reactions following the Pfizer/BioNTech COVID-19 vaccine.

A growing number of cutaneous adverse reactions have been reported following the administration of a COVID-19 vaccine. We describe a series of twenty patients who developed a variety of cutaneous conditions within two weeks of receiving the Pfizer/ BioNTech BNT162b2 vaccine.

Body site locations of basal cell carcinoma, squamous cell carcinoma and actinic keratosis in patients referred to the Waikato District Health Board teledermoscopy clinic.

Introduction Basal cell carcinoma (BCC), squamous cell carcinoma (SCC) and actinic keratosis (AK) are usually located on sun-exposed areas of the body. Aims Our main aims were to identify the common body site locations of BCC, SCC and AK in patients attending the Waikato District Health Board teledermoscopy clinic, also known as the Waikato Virtual Lesion Clinic, as well as to analyse whether the distribution of location changes with age and sex. Methods This is a retrospective study where the body site location of 3272 keratinocytic lesions was determined and analysed in 1864 patients attending the Waikato District Health Board teledermoscopy clinics between 2010 and 2021. Results All three types of lesion were most commonly located in the head and neck region (40.9% of BCCs, 38% of SCCs, 83.2% of AKs), followed by 26.8% on the trunk for BCC, 32.3% on the lower extremities for SCC, and 11.6% on the upper extremities for AK. Discussion Our findings of body site locations for keratinocytic lesions were consistent with other studies. Patients were commonly diagnosed with multiple keratinocytic lesions.

International eDelphi Study to Reach Consensus on the Methotrexate Dosing Regimen in Patients With Psoriasis.

Importance: A clear dosing regimen for methotrexate in psoriasis is lacking, and this might lead to a suboptimal treatment. Because methotrexate is affordable and globally available, a uniform dosing regimen could potentially optimize the treatment of patients with psoriasis worldwide. Objective: To reach international consensus among psoriasis experts on a uniform dosing regimen for treatment with methotrexate in adult and pediatric patients with psoriasis and identify potential future research topics. Design, Setting, and Participants: Between September 2020 and March 2021, a survey study with a modified eDelphi procedure that was developed and distributed by the Amsterdam University Medical Center and completed by 180 participants worldwide (55 [30.6%] resided in non-Western countries) was conducted in 3 rounds. The proposals on which no consensus was reached were discussed in a conference meeting (June 2021). Participants voted on 21 proposals with a 9-point scale (1-3 disagree, 4-6 neither agree nor disagree, 7-9 agree) and were recruited through the Skin Inflammation and Psoriasis International Network and European Academy of Dermatology and Venereology in June 2020. Apart from being a dermatologist/dermatology resident, there were no specific criteria for participation in the survey. The participants worked mainly at a university hospital (97 [53.9%]) and were experienced in treating patients with psoriasis with methotrexate (163 [91.6%] had more than 10 years of experience). Main Outcomes and Measures: In a survey with eDelphi procedure, we tried to reach consensus on 21 proposals. Consensus was defined as less than 15% voting disagree (1-3). For the consensus meeting, consensus was defined as less than 30% voting disagree. Results: Of 251 participants, 180 (71.7%) completed all 3 survey rounds, and 58 participants (23.1%) joined the conference meeting. Consensus was achieved on 11 proposals in round 1, 3 proposals in round 2, and 2 proposals in round 3. In the consensus meeting, consensus was achieved on 4 proposals. More research is needed, especially for the proposals on folic acid and the dosing of methotrexate for treating subpopulations such as children and vulnerable patients. Conclusions and Relevance: In this eDelphi consensus study, consensus was reached on 20 of 21 proposals involving methotrexate dosing in patients with psoriasis. This consensus may potentially be used to harmonize the treatment with methotrexate in patients with psoriasis.

A 9-Year Teledermoscopy Service in New Zealand: Retrospective Service Review.

BACKGROUND: A teledermoscopy service was established in January 2010 wherein patients attended nurse-led clinics for the imaging of lesions of concern and remote diagnosis by a dermatologist. OBJECTIVE: This study aims to review the number of visits, patient characteristics, the efficiency of the service, and the diagnoses made. METHODS: We evaluated the waiting times and diagnoses of skin lesions for all patient visits from January 1, 2010, to May 31, 2019. The relationships between patient characteristics and the diagnosis of melanoma were specifically analyzed. RESULTS: The teledermoscopy clinic was attended by 6479 patients for 11,005 skin lesions on 8805 occasions. Statistically significant risk factors for the diagnosis of melanoma and melanoma in situ were male sex (P<.001), European ethnicity (P=.001), an age of 65 to 74 years (P=.001), and Fitzpatrick skin type 2 (P=.001). Attendance was maximal during 2015 and 2016. The seasonal variations in visits from 2011 to 2018 revealed a consistent peak at the end of summer and a dip at the end of winter. In the year 2010, a total of 306 patients attended the clinic; 76.1% (233/306) of these patients were discharged to primary care, and 23.9% (73/306) were referred to a hospital for a specialist assessment. For patients who were diagnosed with suspected melanoma by a dermatologist from January 1, 2010, to May 31, 2019, the median waiting time for an imaging appointment was 44.5 (mean 57.9; range 8-218) days. The most common lesions diagnosed were benign naevus (2933/11,005, 26.7%), benign keratosis (2576/11,005, 23.4%), and keratinocytic cancer (1707/11,005, 15.5%); melanoma was suspected in 4.6% (507/11,005) of referred lesions. The positive predictive value of melanoma and melanoma in situ was 61.1% (320 true positives and 203 false positives). The number needed to treat (ie, the ratio of the total number of excisions to the number with a histological diagnosis of melanoma or melanoma in situ) was 2.02. CONCLUSIONS: A teledermoscopy service offered by nurse-led imaging clinics can provide efficient and convenient access to dermatology services by streamlining referrals to secondary care and prioritizing patients with skin cancer for treatment.

PASI vs PO-PASI: Patient-Oriented PASI (PO-PASI) is comparable to clinician score PASI.

This comparative observational study aimed to validate an online Patient-oriented Psoriasis Area and Severity Index (PO-PASI) by comparing it against the Psoriasis Area and Severity Index (PASI), of 97 adult participants with chronic plaque psoriasis. Pearson's correlation coefficient of 0.866 (P-value = 0.0001) showed a strong positive linear correlation, and interclass correlation coefficients [ICC scores = 0.864 [95% confidence intervals (CIs) (0.803 < ICC < 0.907)]] suggest an interrater reliability of 'good' to 'excellent' when comparing PO-PASI to the PASI score. Additionally, we compared PO-PASI and PASI with DLQI and demonstrated an overall stronger positive correlation between PO-PASI and DLQI when compared to PASI.

Virtual lesion clinic - Evaluation of a teledermatology triage system for referrals for suspected melanoma.

INTRODUCTION: The Virtual Lesion Clinic (VLC) of Waitemata District Health Board (WDHB) improves melanoma assessment and treatment using teledermatology. The VLC is reserved for pigmented lesions referred as suspected melanoma from primary care but indeterminate at the initial triage. OBJECTIVES: To assess the efficacy of the VLC diagnosis of melanoma. METHODS: A retrospective audit of suspected melanoma referrals (1 January 2012 to 31 December 2016) was conducted. Lesions were referred to the VLC if diagnostic uncertainty remained at the initial triage. VLC patients attended MoleMap imaging centres, a dermatologist reviewed history and images remotely and suggested a diagnosis and management plan. Post VLC provisional diagnosis of melanoma, all lesions subsequently excised were reviewed. A positive predictive value (PPV) was calculated using concordance between VLC diagnosis of melanoma and histopathological diagnosis of melanoma. Number needed to excise (NNE) for melanoma was derived, as well as an invasive to in-situ melanoma ratio (IM:MIS) and false negative rate (FNR). RESULTS: The VLC received 1874 referrals for 3546 lesions during the 5-year study period. Six hundred and seventy-nine lesions were recommended excision/biopsy or specialist face-to-face assessment, and 504 lesions were subsequently excised. The PPV was 62%, NNE 1.62 and IM:MIS 0.76 for lesions suspected to be melanoma at VLC assessment. The VLC had a melanoma-specific FNR of 7%. CONCLUSIONS: The VLC is effective in early diagnosis of melanoma with a high positive predictive value, low number needed to excise and low false negative rate amongst lesions referred as suspected melanoma.

Remote Skin Cancer Diagnosis: Adding Images to Electronic Referrals Is More Efficient Than Wait-Listing for a Nurse-Led Imaging Clinic.

We undertook a retrospective comparison of two teledermatology pathways that provide diagnostic and management advice for suspected skin cancers, to evaluate the time from referral to diagnosis and its concordance with histology. Primary Care doctors could refer patients to either the Virtual Lesion Clinic (VLC), a nurse-led community teledermoscopy clinic or, more recently, to the Suspected Skin Cancer (SSC) pathway, which requires them to attach regional, close-up, and dermoscopic images. The primary objective of this study was to determine the comparative time course between the SSC pathway and VLC. Secondary objectives included comparative diagnostic concordance, skin lesion classification, and evaluation of missed skin lesions during subsequent follow-up. VLC referrals from July to December 2016 and 2020 were compared to SSC referrals from July to December 2020. 408 patients with 682 lesions in the VLC cohort were compared with 480 patients with 548 lesions from the 2020 SSC cohort, matched for age, sex, and ethnicity, including histology where available. Median time (SD) from referral to receipt of teledermatology advice was four (2.8) days and 50 (43.0) days for the SSC and VLC cohorts, respectively (p < 0.001). Diagnostic concordance between teledermatologist and histopathologist for benign versus malignant lesions was 70% for 114 lesions in the SSC cohort, comparable to the VLC cohort (71% of 122 lesions). Referrals from primary care, where skin lesions were imaged with variable devices and quality resulted in faster specialist advice with similar diagnostic performance compared to high-quality imaging at nurse-led specialist dermoscopy clinics.

A baseline patch test series for New Zealand.

BACKGROUND: Patch testing is the gold standard diagnostic test for allergic contact dermatitis and needs to be relevant to the region and the population being tested. The aim of this study was to develop a specific New Zealand baseline series (NZBS). METHOD: We performed a retrospective case note review of patients attending four regional patch test centres between 2008 and 2020. Demographic and diagnostic information was collected for each patient along with results of patch testing. Using the results of this review, a group of 11 dermatologists with an interest in contact dermatitis agreed on a core group of allergens for inclusion in an NZBS, based on the frequency of positive reactions and allergens of interest. The remaining potential allergens were ranked by each dermatologist using an online questionnaire, with inclusion in the final NZBS by consensus. RESULTS: Results from 2402 patients (67% female, mean age 44 years) from Auckland, Wellington, Palmerston North and Christchurch were collated. The 10 most frequent positive (relevant and non-relevant) allergens were nickel sulfate (22.0%), fragrance mix I (8.6%), cobalt chloride (7.3%), Myroxylon pereirae (5.6%), colophonium (5.1%), p-phenylenediamine (4.9%), methylisothiazolinone/methylchloroisothiazolinone (4.1%), fragrance mix II (3.9%), potassium dichromate (3.5%) and methylisothiazolinone (3.4%). Based on these results, a core series of 30 allergens was developed, with an additional 30 allergens added to form the extended series (total 60 allergens). CONCLUSION: The baseline series of patch test allergens for routine use in New Zealand (NZBS) is based on national patch test data and expert consensus.

Vulval lichen sclerosus: An Australasian management consensus.

BACKGROUND/OBJECTIVES: Vulval lichen sclerosus (VLS) is a chronic inflammatory skin condition predominantly affecting the anogenital region in women and children. To date, there is lack of agreement amongst experts on a severity scale to aid assessment, research and treatment stratification on VLS. Furthermore, literature on best practice for long-term management of VLS is lacking. The aim of this consensus is to provide broad guidelines on the short and long-term management of VLS. METHODS: An initial focus group of Australasian experts in vulval dermatology developed a draft consensus statement for the management of VLS. Based on the results of the draft statement, a consensus panel of 22 Australasian experts, comprised of the initial and additional members, participated in an anonymous four-stage eDelphi process. Round 1 involved generation and voting on statements from the draft consensus statement developed by the focus group. In Rounds 2, 3 & 4, panel members were presented formal feedback from previous rounds and asked to indicate their level of agreement. Consensus was reached if there was ≥70% agreement on the importance of an item in the 4 (agree) to 5 (strongly agree) range. RESULTS: The expert panel, with a total of 504 collective years of experience in the field of VLS, reached consensus on a core set of 51 management statements related to diagnosis, severity, initial and long-term management, follow-up, and complications of VLS. CONCLUSIONS: This study has identified a set of management statements for VLS that may be useful in clinical practice in the Australasian population.

A retrospective review of cutaneous vascular lesions referred to a teledermatology clinic.

INTRODUCTION Most cutaneous vascular lesions are benign and do not require treatment. Many are referred to specialist dermatologists from primary care. AIM This study aimed to investigate the characteristics of cutaneous vascular lesions and the reasons for their referral from primary care. METHODS Lesions diagnosed as cutaneous vascular abnormalities or dermatoses were retrospectively selected from a database of patients attending the Waikato Virtual Lesion Clinic. Demographic data, diagnosis and clinic outcome were recorded for each imaged lesion. Primary care referrals were reviewed to determine the reasons for referral. RESULTS In total, 229 referrals for vascular lesions were received between January 2010 and February 2019. Patient ages ranged from 6 to 95 years and 64.2% of patients were female. Nearly half the lesions (47.2%) were located on the head and neck; 64.1% had a dermatological diagnosis of a vascular tumour and 18.7% had a malformation. The most common reason for referral was pigmentation (45.7%) and bleeding was least common (8.2%). No diagnosis was given in 34.2% of referrals and less than one-quarter had a correct diagnosis. Malignancy was suspected in 40.2% of referrals; however, the dermatologists found that 95.2% of patients did not require further treatment. Half of excisions (n=2) were for bleeding and all were histologically benign. DISCUSSION Diagnostic uncertainty and suspected malignancy commonly result in referral of benign cutaneous vascular lesions to public dermatology services. This study highlights the usefulness of teledermatology in the timely access of specialist input, minimising the need for intervention or excision.

The use of noninvasive imaging techniques in the diagnosis of melanoma: a prospective diagnostic accuracy study.

BACKGROUND: Early detection of melanoma is crucial to improving the detection of thin curable melanomas. Noninvasive, computer-assisted methods have been developed to use at the bedside to aid in diagnoses but have not been compared directly in a clinical setting. OBJECTIVE: We conducted a prospective diagnostic accuracy study comparing a dermatologist's clinical examination at the bedside, teledermatology, and noninvasive imaging techniques (FotoFinder, MelaFind, and Verisante Aura). METHODS: A total of 184 patients were recruited prospectively from an outpatient dermatology clinic, with lesions imaged, assessed, and excised. Skin specimens were assessed by 2 blinded pathologists, providing the gold standard comparison. RESULTS: Fifty-nine lesions from 56 patients had a histopathologic diagnosis of melanoma, whereas 150 lesions from 128 patients were diagnosed as benign. Sensitivities and specificities were, respectively, MelaFind (82.5%, 52.4%), Verisante Aura (21.4%, 86.2%), and FotoFinder Moleanalyzer Pro (88.1%, 78.8%). The sensitivity and specificity of the teledermoscopist (84.5% and 82.6%, respectively) and local dermatologist (96.6% and 32.2%, respectively) were also compared. LIMITATIONS: There are inherent limitations in using pathology as the gold standard to compare sensitivities and specificities. CONCLUSION: This study demonstrates that the highest sensitivity and specificity of the instruments were established with the FotoFinder Moleanalyzer Pro, which could be a valuable tool to assist with, but not replace, clinical decision making.