ABSTRACT
Background: Despite recent advancements, medical technology has not yet reached its peak. Precision medicine is growing rapidly, thanks to machine learning breakthroughs powered by increased computational capabilities. This article explores a deep learning application for computer-aided diagnosis in dermatology. Methods: Using a custom model based on EfficientNetB3 and deep learning, we propose an approach for skin lesion classification that offers superior results with smaller, cheaper, and faster inference times compared to other models. The skin images dataset used for this research includes 8222 files selected from the authors' collection and the ISIC 2019 archive, covering six dermatological conditions. Results: The model achieved 95.4% validation accuracy in four categories-melanoma, basal cell carcinoma, benign keratosis-like lesions, and melanocytic nevi-using an average of 1600 images per category. Adding two categories with fewer images (about 700 each)-squamous cell carcinoma and actinic keratoses-reduced the validation accuracy to 88.8%. The model maintained accuracy on new clinical test images taken under the same conditions as the training dataset. Conclusions: The custom model demonstrated excellent performance on the diverse skin lesions dataset, with significant potential for further enhancements.
ABSTRACT
Hybrid trials are a new trend in dermatological research that leverage mobile health technologies to decentralize a subset of clinical trial elements and thereby reduce the number of in-clinic visits. In a Phase I/IIa randomized controlled hybrid trial, the safety and efficacy of an anti-proliferative and anti-inflammatory drug inhibiting cytosolic phospholipase A2 (AVX001) was tested using 1%, 3% or vehicle gel in 60 patients with actinic keratosis (AK) and assessed in-clinic as well as remotely. Over the course of 12 weeks, patients were assessed in-clinic at baseline, end of treatment (EOT) and end of study (EOS), as well as 9 times remotely on a weekly to biweekly basis. Safety outcomes comprising local skin reactions (LSR; 0-5), adverse events (AE) and cosmesis, were graded in-clinic and remotely using patient-obtained smartphone photographs (PSPs) and questionnaires; efficacy was assessed in-clinic based on clinically visible clearance of AK target area of >50%. A total of 55 participants (91.7%) completed the treatment course. The average submission rate of PSPs was high (≥85%), of which 93% were of sufficient quality. No serious AE were reported and only two experienced temporary LSR >2 (scale 0-4) and cosmesis remained stable throughout the study. Based on the mild AE and LSR profile, daily application of AVX001 gel for 1 month appears safe, tolerable, and cosmetically acceptable for use in patients with AK. At EOT, AVX001 achieved a subtle treatment response with clearance of AK target area of >50% in 18% of patients. Remote and in-clinic assessments of LSRs were in high agreement, suggesting that the use of mobile health technologies in early-phase hybrid studies of AK does not compromise patient safety.
Subject(s)
Keratosis, Actinic , Telemedicine , Humans , Blood Proteins , Keratosis, Actinic/drug therapy , SkinABSTRACT
Background: Patient recruitment is a major cause of delays in randomized controlled trials (RCT). Online recruitment is evolving into an alternative to conventional in-clinic recruitment for RCT. The objective of this study was to test the effectiveness of online patient recruitment for an RCT on actinic keratosis (AK). Methods: In this proof-of-concept study, adults with AK were recruited for a Phase I/IIa RCT (NCT05164393) via social media using targeted advertising Interested users were directed to a landing page to learn about the study, respond to questionnaires, and upload self-obtained smartphone pictures of potential AK. Facebook Analytics was used to track the number of advertisement views, individual users exposed to the advertisement, and advertisement clicks. Following eligibility-review by remote dermatologists, candidates were contacted for an in-clinic visit. A review of pertinent RCTs on AK (2012-2022) was conducted to compare recruitment metrics. Results: The online campaign served 886,670 views, reached 309,000 users, and generated 27,814 clicks. A total of 556 users underwent eligibility review, leading to 140 pre-evaluated potential study subjects. The RCT's enrollment target of 60 patients (68.8 ± 7.1 years, 43.3 % female) was reached in 53 days after screening 90 participants in-clinic, corresponding to a screen failure rate of 33.3 %. The total cost of this online recruitment campaign was 14,285 USD i.e. 238 USD per randomized patient. Compared to the existing literature (44 RCTs), our online approach resulted in 9 times more time-efficient recruitment per site. Conclusion: Using targeted advertisements, 60 patients with AK were recruited for a single-center Phase I/IIa RCT in 53 days. Social media appears to be an efficient platform for online recruitment of patients with low-grade AK for RCT.
ABSTRACT
Background: Remote monitoring was used to assess and manage skin diseases. Objective: To investigate to what extent smartphone photographs along with a self-reported body region (BR) score can be used to evaluate psoriasis severity. Methods: Psoriasis severity was assessed in the clinic using the psoriasis area and severity index and the physician's global assessment. On the same day, the patients took a photograph of a representative lesion from 4 BR (head/neck, upper limbs, trunk, and lower limbs) and completed a questionnaire about BR score. The photographs were rated by 5 dermatologists. Intraclass correlation coefficients with 95% CIs were calculated. Results: Overall, 32 were included, of which 6% had almost clear, 69% had mild, and 25% had moderate psoriasis. Perfect agreement between the self-reported and the doctors' BR score was observed for 59%, and near-perfect agreement (deviation of maximum 1 score) was 92%. The intraclass correlation coefficient between clinical and photographic psoriasis area and severity index was 0.78 (95% CI, 0.55-0.90), and for physician's global assessment, perfect agreement was 53%. Conclusions: The agreement between psoriasis severity assessed clinically and by photographs was good in a study setting. This gives the opportunity to remotely assess psoriasis severity by combining photographs with self-reported BR scores.
ABSTRACT
INTRODUCTION: Actinic keratosis (AK) is the most common precancerous skin condition caused by long-term UV exposure. Given the high recurrence rate of 15%-53%, identifying safe and effective treatment options is warranted. AVX001, a cytosolic phospholipase A2α (cPLA2α) enzyme inhibitor, is a novel anti-inflammatory drug for field-directed, self-administered, topical therapy of AK. METHODS AND ANALYSIS: This study is a single-centre, randomised, vehicle-controlled, double-blind, parallel-group hybrid clinical trial in adults with multiple AK lesions Olsen grade 1 or 2. The hybrid design combines decentralised participant tasks and assessments with conventional in-clinic visits. Recruitment using targeted advertising on social media and eligibility prescreening are conducted via the Studies&Me online recruitment platform. Participants (n=60) are randomly assigned to 1 of 3 treatment arms: AVX001 gel 1%, AVX001 gel 3% or vehicle gel. The trial consists of a 4-week treatment period with daily field-directed topical application of the gel and an 8-week follow-up period. Participants attend in-clinic visits at baseline, week 4 and week 12. The remote participant trial tasks include questionnaires and upload of smartphone-obtained photos of the treated skin area using a study-specific web-based app. Both remote and in-clinic assessments of safety and efficacy will be performed. The primary objective is to evaluate the local tolerability of daily application of AVX001 gel (1% or 3%) compared with vehicle gel. Secondary objectives include safety, efficacy, dose-response efficacy relationship, treatment satisfaction and cosmetic outcome. Exploratory objectives include evaluations of tolerability and efficacy assessed by dermatologists using smartphone photos uploaded by participants, comparisons of in-clinic and remote assessments and assessment of AK-related skin changes by non-invasive optical imaging. ETHICS AND DISSEMINATION: Approved by the Ethics Committee of the Capital Region of Denmark (H-21018064) and the Danish Medicines Agency (2021032485). Results will be submitted for publication in peer-reviewed scientific journals. TRIAL REGISTRATION NUMBERS: 2021-000934-32; NCT05164393.
Subject(s)
Fatty Acids, Omega-3 , Keratosis, Actinic , Phospholipase A2 Inhibitors , Adult , Clinical Trials, Phase I as Topic , Clinical Trials, Phase II as Topic , Fatty Acids, Omega-3/adverse effects , Humans , Keratosis, Actinic/drug therapy , Phospholipase A2 Inhibitors/adverse effects , Randomized Controlled Trials as Topic , Treatment OutcomeABSTRACT
BACKGROUND: The use of photographs to diagnose and monitor skin diseases is gaining ground. OBJECTIVES: To investigate the validity and reliability of photographic assessments of atopic dermatitis (AD) severity. METHODS: AD severity was evaluated in the clinic by two assessors using the Eczema Area and Severity Index (EASI), SCOring Atopic Dermatitis (SCORAD), and Investigator's Global Assessment (IGA). Participants photographed the lesions with their own smartphone and completed a questionnaire about the extent of eczema the same day from home. The photographs were assessed twice with an 8 weeks interval by five dermatologists experienced in photographic evaluations. Intraclass correlation coefficients (ICC) with 95% confidence interval (CI) were applied. RESULTS: Seventy-nine participants were enrolled. The ICC between clinical EASI and photographic EASI was 0.88 (95% CI 0.81-0.93), and 0.86 (0.70-0.93) between clinical SCORAD and photographic SCORAD. Perfect agreement between clinical IGA and photograph IGA was observed for 62%, with the difference between the two never deviating with more than 1 score. The inter-rater ICC for photographic EASI and photographic SCORAD, respectively, was 0.90 (0.85-0.94), and 0.96 (0.91-0.98). The intra-rater agreements between the first and second assessments varied from 0.95 to 0.98 for photographic EASI, and from 0.86 to 0.94 for photographic SCORAD. CONCLUSION: There was high agreement between mild to moderate AD severity assessed clinically and based on smartphone photographs. Further, the photographic assessments can be reproduced with high reliability.
Subject(s)
Dermatitis, Atopic , Eczema , Dermatitis, Atopic/diagnostic imaging , Dermatitis, Atopic/pathology , Humans , Reproducibility of Results , Severity of Illness Index , SmartphoneABSTRACT
BACKGROUND: Digital imaging of dermatological patients is a novel approach to remote assessment and has recently become more relevant since telehealth and remote decentralized clinical trials are gaining ground. OBJECTIVE: We aimed to investigate whether photographs taken by a smartphone are of adequate quality to allow severity assessments to be made and to explore the usefulness of an established atopic dermatitis severity assessment instrument on photograph evaluation. METHODS: During scheduled visits in a previously published study, the investigating doctor evaluated the severity of atopic dermatitis using the Scoring AD (SCORAD) index and took photographs of the most representative lesions (target lesions) with both a smartphone and a digital single-lens reflex camera (DSLR). The photographs were then assessed by 5 dermatologists using the intensity items of the SCORAD (iSCORAD), which consists of erythema, oedema/papulation, excoriations, lichenification, oozing/crusts, and dryness (scale 0-3, maximum score 18). The mean iSCORAD of the photographs was calculated and compared with in-person assessments using Pearson correlation and Bland-Altman plots. Intraclass correlation coefficients were used for interrater reliability. RESULTS: A total of 942 photographs from 95 patients were assessed. The iSCORAD based on smartphone photographs correlated strongly with the evaluations performed in person (iSCORAD: r=0.78, P<.001; objective SCORAD: r=0.81, P<.001; and total SCORAD: r=0.78, P<.001). For iSCORAD specifically, a Bland-Altman plot showed a difference in mean score of 1.31 for in-person and remote iSCORAD. In addition, the interrater agreement between the 5 rating dermatologists was 0.93 (95% CI 0.911-0.939). A total of 170 lesions were photographed, and the difference in mean scores was 1.32, 1.13, and 1.43 between in-person and remote evaluations based on photographs taken by a DSLR camera, a smartphone without flash, and a smartphone with flash, respectively. CONCLUSIONS: In terms of quality, remote atopic dermatitis severity assessments based on photographs are comparable to in-person assessments, and smartphone photos can be used to assess atopic dermatitis severity to a similar degree as photographs from a DSLR camera. Further, the variation in how the dermatologists in this study rated the iSCORAD based on the photographs was very low.
ABSTRACT
BACKGROUND: Workers in the healthcare sector are at high risk of developing occupational hand eczema mainly due to frequent exposure to irritants and/or allergens. Amongst workers in healthcare, nurses are at higher risk of developing hand dermatitis. OBJECTIVES: To evaluate the effectiveness of a short educational intervention program in preventing occupational hand eczema in nurse apprentices, using two objective tools, namely TEWL and EH, and the HECSI score. METHODS: Data regarding professions, wet work exposure, activities performed during working hours, self-reported eczema were collected from 230 nurse students, divided in two study groups: the intervention and the control group (CG). The intervention group (IG) was given education about risks and proper skin care and was provided with cosmeceuticals to be used for skin care during hospital activity. The evaluation of skin properties was performed using questionnaires, HECSI score, measurement of transepidermal water loss (TEWL) and epidermal hydration (EH). RESULTS: A number of 139 apprentice nurses completed the study. Of those participants who completed the study, 19.1% from CG and 19.6% from IG reported, at T1, hand eczema in the last 3 months, while at T2 (3 months later), 59.52 % of the CG and only 11.34 % from the IG stated having eczema in the last 3 months. In the IG, results showed an improvement of CM with 17% and of TEWL with 16%, with only a 0.5% improvement of CM in CG and a marked impairment of TEWL by 33%. CONCLUSION: Hand eczema is a common occupational dermatosis affecting the medical staff, even during apprenticeship. Early preventive training programs are effective in reducing the burden of occupational contact dermatitis.
Subject(s)
Dermatitis, Occupational , Eczema , Hand Dermatoses , Occupational Exposure , Dermatitis, Occupational/prevention & control , Eczema/prevention & control , Hand , Hand Dermatoses/prevention & control , HumansABSTRACT
Primary cutaneous CD30-positive lymphoproliferative disorders represent the second most common subgroup of cutaneous T-cell lymphomas and include lymphomatoid papulosis, primary cutaneous anaplastic large cell lymphoma, and borderline lesions. Primary cutaneous anaplastic large cell lymphoma is characterized by the presence of solitary or localized nodules or tumors located on the extremities or the cephalic or cervical region. Large plaque parapsoriasis is a chronic inflammatory disorder that associates a high risk of progression to mycosis fungoides. We report a case of CD30+ primary cutaneous anaplastic large cell lymphoma in a patient with a long history of large plaque parapsoriasis.