Applied artificial intelligence for global child health: Addressing biases and barriers.

Given the potential benefits of artificial intelligence and machine learning (AI/ML) within healthcare, it is critical to consider how these technologies can be deployed in pediatric research and practice. Currently, healthcare AI/ML has not yet adapted to the specific technical considerations related to pediatric data nor adequately addressed the specific vulnerabilities of children and young people (CYP) in relation to AI. While the greatest burden of disease in CYP is firmly concentrated in lower and middle-income countries (LMICs), existing applied pediatric AI/ML efforts are concentrated in a small number of high-income countries (HICs). In LMICs, use-cases remain primarily in the proof-of-concept stage. This narrative review identifies a number of intersecting challenges that pose barriers to effective AI/ML for CYP globally and explores the shifts needed to make progress across multiple domains. Child-specific technical considerations throughout the AI/ML lifecycle have been largely overlooked thus far, yet these can be critical to model effectiveness. Governance concerns are paramount, with suitable national and international frameworks and guidance required to enable the safe and responsible deployment of advanced technologies impacting the care of CYP and using their data. An ambitious vision for child health demands that the potential benefits of AI/Ml are realized universally through greater international collaboration, capacity building, strong oversight, and ultimately diffusing the AI/ML locus of power to empower researchers and clinicians globally. In order that AI/ML systems that do not exacerbate inequalities in pediatric care, teams researching and developing these technologies in LMICs must ensure that AI/ML research is inclusive of the needs and concerns of CYP and their caregivers. A broad, interdisciplinary, and human-centered approach to AI/ML is essential for developing tools for healthcare workers delivering care, such that the creation and deployment of ML is grounded in local systems, cultures, and clinical practice. Decisions to invest in developing and testing pediatric AI/ML in resource-constrained settings must always be part of a broader evaluation of the overall needs of a healthcare system, considering the critical building blocks underpinning effective, sustainable, and cost-efficient healthcare delivery for CYP.

Validation of the Melanoma Institute of Australia's Sentinel Lymph Node Biopsy Risk Prediction Tool for Cutaneous Melanoma.

BACKGROUND: For patients with cutaneous melanoma, sentinel lymph node biopsy (SLNB) is used to stage regional lymph nodes pathologically and inform prognosis, treatment, and surveillance. To reduce unnecessary surgeries, predictive tools aim to identify those at lowest risk for node-positive disease. The Melanoma Institute of Australia (MIA)'s Prediction Tool for Sentinel Node Metastasis Risk estimates risk of a positive SLNB using patient age and primary melanoma Breslow depth, histologic subtype, ulceration, mitotic rate, and lymphovascular invasion. METHODS: A single-institution validation was performed of the MIA Calculator with 982 cutaneous melanoma patients that included all relevant clinicopathologic factors and SLNB pathology outcomes. The study evaluated discrimination via receiver operating characteristic (ROC) curves, calibration via calibration plots, and clinical utility via decision curve analysis of the MIA model in various subgroups. The data were fit to MIA model parameters via a generalized linear model to assess the odds ratio of parameters in our dataset. RESULTS: The Calculator demonstrated limited discrimination based on ROC curves (C-statistic, 0.709) and consistently underestimated risk of SLN positivity. It did not provide a net benefit over SLNB performed on all patients or reduce unnecessary procedures in the risk domain of 0% to 16%. Compared with the original development and validation cohorts, the current study cohort had thinner tumors and a larger proportion of acral melanomas. CONCLUSIONS: The Calculator generally underestimated SLN positivity risk, including assessment in patients who would be counseled to forego SLNB based on a predicted risk lower than 5%. Recognition of the tool's current limitations emphasizes the need to refine it further for use in medical decision-making.

Best Practices for Research in Virtual and Augmented Reality in Dermatology.

Virtual reality (VR) and augmented reality (AR) technologies have advanced rapidly in recent years. These cutting-edge technologies provide dermatology researchers, educators, proceduralists, and patients with opportunities in new scientific horizons. VR is a technology that facilitates immersive human experiences by allowing users to connect with various simulated environments through natural head and hand movements, whereas AR supplements a user's perception of their real environment with virtual elements. Despite technological advancements, there is limited literature on the methodological steps for conducting rigorous VR and AR research in dermatology. Effective storyboarding, user-driven design, and interdisciplinary teamwork play a central role in ensuring that VR/AR applications meet the specific needs of dermatology clinical and research teams. We present a step-by-step approach for their design, team composition, and evaluation in dermatology research, medical education, procedures, and habit formation strategies. We also discuss current VR and AR dermatology applications and the importance of ethical and safety considerations in deploying this new technology.

Principles, applications, and future of artificial intelligence in dermatology.

This paper provides an overview of artificial-intelligence (AI), as applied to dermatology. We focus our discussion on methodology, AI applications for various skin diseases, limitations, and future opportunities. We review how the current image-based models are being implemented in dermatology across disease subsets, and highlight the challenges facing widespread adoption. Additionally, we discuss how the future of AI in dermatology might evolve and the emerging paradigm of large language, and multi-modal models to emphasize the importance of developing responsible, fair, and equitable models in dermatology.

Best Practices for Clinical Skin Image Acquisition in Translational Artificial Intelligence Research.

Recent advances in artificial intelligence research have led to an increase in the development of algorithms for detecting malignancies from clinical and dermoscopic images of skin diseases. These methods are dependent on the collection of training and testing data. There are important considerations when acquiring skin images and data for translational artificial intelligence research. In this paper, we discuss the best practices and challenges for light photography image data collection, covering ethics, image acquisition, labeling, curation, and storage. The purpose of this work is to improve artificial intelligence for malignancy detection by supporting intentional data collection and collaboration between subject matter experts, such as dermatologists and data scientists.

Melanoma awareness and prevention among latinx and non-latinx white adults in urban and rural California: A qualitative exploration.

BACKGROUND: Melanoma mortality rates in the US are highest among older men, individuals of lower socioeconomic status (SES), and people of color. To better understand these inequities, a qualitative exploratory study was conducted in Northern and Southern California to generate knowledge about barriers and facilitators of awareness, prevention, and early detection of melanoma in lower SES Latinx and non-Latinx White (NLW) individuals living in urban and semi-rural areas. METHODS: Nineteen focus groups were conducted (N = 176 adult participants), stratified by race/ethnicity (Latinx, low-income NLW), geography (semi-rural, urban), and language (English and Spanish). Inductive and deductive thematic analysis was conducted, and the findings were organized using the socioecological model framework: individual, interpersonal, community, and health system/policy levels. RESULTS: Four socioecological themes describe how key factors affect knowledge, perceived risk, preventive behaviors, and melanoma screening. Individual level findings revealed that many participants were not familiar with melanoma, yet were willing to learn through trusted sources. Having brown or darker skin tone was perceived as being associated with lower risk for skin cancer. Interpersonally, social relationships were important influences for skin cancer prevention practice. However, for several Latinx and semi-rural participants, conversations about melanoma prevention did not occur with family and peers. At the community level, semi-rural participants reported distance or lack of transportation to a clinic as challenges for accessing dermatology care. Healthcare systems barriers included burdens of additional healthcare costs for dermatology visits and obtaining referral. CONCLUSIONS: Varying factors influence the awareness levels, beliefs, and behaviors associated with knowledge, prevention, and early detection of melanoma among low-income Latinx and NLW individuals and in semi-rural areas. Results have implications for health education interventions. Navigation strategies that target individuals, families, and health care settings can promote improved prevention and early detection of melanoma in these communities.

Acne Vulgaris in Skin of Color: A Systematic Review of the Effectiveness and Tolerability of Current Treatments.

Acne vulgaris is a common dermatosis frequently encountered in general dermatology and presents significant health-related quality of life and psychological challenges. Clinical studies on acne vulgaris in skin of color are limited; thus, it is likely that treatment recommendations to patients with darker skin types are drawn from trial data based on Caucasian skin. The aim of this study was to systematically review the effectiveness and tolerability of treatments used to treat acne vulgaris in patients with skin of color. A literature search was performed in the PubMed, Embase, and Scopus bibliographic databases, with a total of 1,477 retrieved articles, of which 1,316 were excluded after initial screening. Of the 93 studies assessed, 55 studies met our inclusion criteria (28 randomized controlled trials, 4 cohort studies, 6 post-hoc analyses, and 12 other interventional trials). The studies reported a total of 21,202 patients. Most studies explored topical therapies (23 studies) and photodynamic therapy (13 studies). Other treatments included laser/light therapy, systemic therapy, chemical peels, and radiofrequency and microneedling. In general, the different treatment modalities offered an improvement in lesion count and were well tolerated, with no report of major adverse events. However, due to limited evidence, we were unable to draw firm conclusions from the results of this review to guide decisions in practice, particularly with respect to long-term outcomes, in patients with skin of color and acne vulgaris.

Physical and psychological impacts of handwashing and personal protective equipment usage in the COVID-19 pandemic: A UK based cross-sectional analysis of healthcare workers.

The COVID-19 pandemic has necessitated intensified handwashing and mask usage for healthcare staff. A retrospective cross-sectional study was performed primarily to investigate the potential skin damage and secondary impacts on wellbeing of staff resulting from these practices. Additionally the availability and uptake of occupational health services and moisturisers in the work place was also assessed. The survey was distributed to NHS staff between April and May 2020 and asked questions regarding skin damage, impact on wellbeing and availability and utilisation of occupational health input and moisturisers. Of the 211 responders, 167 washed their hands more than ten times per shift. Three quarters of these reported cracks or fissures in one or more regions of their hands, most frequently to the back of the hands or web spaces. Amongst the 157 staff who wore FFP3 masks, redness of the nasal area was most frequently reported with 8% reporting facial blisters. 36% of staff reported a substantial impact on one or more aspects of their wellbeing. Only 7% of respondents had received specialist advice, yet a quarter (26%) had made or anticipated needing changes to their occupational duties. The majority (63%) felt they required no specialist input, despite 38% of these reporting a substantial detriment to their wellbeing. Handwashing and face mask use is resulting in skin damage amongst healthcare workers during the COVID-19 pandemic, with associated detriment to wellbeing. Healthcare services need to take action to implement measures to prevent, reduce and treat damage including promotion of available specialist support.

Real life data on the biopsychosocial effects of Adalimumab in the management of hidradenitis suppurativa: A multicenter cross sectional analysis and consideration of a multisystem monitoring approach to follow up.

Hidradenitis suppurativa (HS) is a chronic relapsing, remitting disease which results in the formation of inflammatory nodules and pustules in intertriginous areas. HS is a complex disease with known psychosocial impact. Adalimumab is a biologic, used for treatment resistant HS, which working by inactivating TNF-alpha. Our primary objective was to determine the effects of adalimumab on HS-PGA and DLQI scores in patients with HS that had been on the treatment for at least 6 months. Our secondary objective was to note and assess the significance of adverse effects and impacts on wider health, namely occupational and social. A retrospective cross-sectional study was performed using clinic notes from routine follow ups in biologic clinics in three specialist HS centers. About 77% (n = 78/101) patients demonstrated improvements in their HS-PGA scores. Significant improvements in the DLQI scores of the patient cohort (P = .0001, 95% CI -12.8 to -5.9) have also been demonstrated. A total of 31.7% (32/101) patients experienced adverse effects spanning multiple organ systems, with 27.7% (28/101) requiring treatment cessation. Three of these patients stopped due to the worsening of preexisting mental health symptoms. Adalimumab is effective in reducing HS-PGA and DLQI scores, but patients still complain of systemic effects necessitating drug cessation in some instances. A holistic and multisystemic approach to follow up is required, and there is scope for further studies examining temporal causality in the context of adalimumab and its multisystemic physical and psychological effects.