-
Cancers Sep 2023Melanoma, the deadliest form of skin cancer, poses a significant public health challenge worldwide. Early detection is crucial for improved patient outcomes.... (Review)
Review
BACKGROUND
Melanoma, the deadliest form of skin cancer, poses a significant public health challenge worldwide. Early detection is crucial for improved patient outcomes. Non-invasive skin imaging techniques allow for improved diagnostic accuracy; however, their use is often limited due to the need for skilled practitioners trained to interpret images in a standardized fashion. Recent innovations in artificial intelligence (AI)-based techniques for skin lesion image interpretation show potential for the use of AI in the early detection of melanoma.
OBJECTIVE
The aim of this study was to evaluate the current state of AI-based techniques used in combination with non-invasive diagnostic imaging modalities including reflectance confocal microscopy (RCM), optical coherence tomography (OCT), and dermoscopy. We also aimed to determine whether the application of AI-based techniques can lead to improved diagnostic accuracy of melanoma.
METHODS
A systematic search was conducted via the Medline/PubMed, Cochrane, and Embase databases for eligible publications between 2018 and 2022. Screening methods adhered to the 2020 version of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Included studies utilized AI-based algorithms for melanoma detection and directly addressed the review objectives.
RESULTS
We retrieved 40 papers amongst the three databases. All studies directly comparing the performance of AI-based techniques with dermatologists reported the superior or equivalent performance of AI-based techniques in improving the detection of melanoma. In studies directly comparing algorithm performance on dermoscopy images to dermatologists, AI-based algorithms achieved a higher ROC (>80%) in the detection of melanoma. In these comparative studies using dermoscopic images, the mean algorithm sensitivity was 83.01% and the mean algorithm specificity was 85.58%. Studies evaluating machine learning in conjunction with OCT boasted accuracy of 95%, while studies evaluating RCM reported a mean accuracy rate of 82.72%.
CONCLUSIONS
Our results demonstrate the robust potential of AI-based techniques to improve diagnostic accuracy and patient outcomes through the early identification of melanoma. Further studies are needed to assess the generalizability of these AI-based techniques across different populations and skin types, improve standardization in image processing, and further compare the performance of AI-based techniques with board-certified dermatologists to evaluate clinical applicability.
PubMed: 37835388
DOI: 10.3390/cancers15194694 -
Journal of Drugs in Dermatology : JDD Mar 2024Atopic dermatitis (AD) typically starts in infancy and early childhood. The chronic skin disorder is associated with recurrent flares, pruritus, and genetic...
Attenuation of Atopic Dermatitis in Newborns, Infants, and Children With Prescription Treatment and Ceramide-Containing Skin Care: A Systematic Literature Review and Consensus.
BACKGROUND
Atopic dermatitis (AD) typically starts in infancy and early childhood. The chronic skin disorder is associated with recurrent flares, pruritus, and genetic predisposition. Daily use of moisturizers that contain lipids, such as ceramides, reduces the rate of AD flares and the need for topical steroid treatment. We aimed to provide insights on AD attenuation to tailor AD prescription therapy, skin care, and maintenance treatment to improve pediatric patients with AD and families.
METHODS
A panel of 6 pediatric dermatologists and dermatologists who treat neonates, infants, and children developed a consensus paper on AD attenuation for pediatric patients. The modified Delphi process comprised a face-to-face panel meeting and online follow-up to discuss the systematic literature search results and draw from clinical experience and opinion of the panel to adopt and agree on 5 statements. Results: Understanding the functional properties of newborn and infant skin, discussing skincare product use with parents, and recommending tailored prescription and skincare routines can improve newborn, infant, and children’s skin health. Studies on the prophylactic application of moisturizers initiated in early infancy suggest moisturizers may delay rather than prevent AD, especially in high-risk populations and when used continuously. Increasingly there is evidence that moisturizer application reduces the severity of AD and extends the time to flares, which may help attenuate the atopic march. The protective effect of skin care for AD has been observed in studies where its daily use is ongoing; these beneficial effects may be lost in less than 1year after cessation. It is therefore important to emphasize that skin care should be routinely used when counseling patients and caregivers. Conclusion: Healthcare providers can improve patient outcomes in atopic-prone infants and children by providing instructions regarding the daily benefits of applying skin care with gentle cleansers and moisturizers. Using gentle cleansers and moisturizers containing barrier lipids from birth onward may delay AD occurrence and mitigate severity in predisposed infants.J Drugs Dermatol. 2024;23(3): doi:10.36849/JDD.7894.
Topics: Infant, Newborn; Infant; Humans; Child, Preschool; Child; Dermatitis, Atopic; Consensus; Skin Care; Skin; Ceramides
PubMed: 38443125
DOI: 10.36849/jdd.7894 -
Skin Health and Disease Aug 2023Cutaneous and systemic signs of acute and chronic arsenic poisoning may be vague. Thus, an awareness of these signs is crucial to prevent late or missed diagnoses. This... (Review)
Review
Cutaneous and systemic signs of acute and chronic arsenic poisoning may be vague. Thus, an awareness of these signs is crucial to prevent late or missed diagnoses. This is especially true in non-endemic countries where individuals may present decades after exposure, or may still be ingesting arsenic via a non-classical exposure. Existing literature emphasizes several well-known cutaneous presentations of arsenic toxicity while ignoring the complete clinical spectrum, including several rare tumours of relevance to the dermatologist. This study aims to review the existing literature on dermatological presentations of arsenic toxicity and their management in adults.
PubMed: 37538334
DOI: 10.1002/ski2.231 -
NPJ Digital Medicine May 2024Scientific research of artificial intelligence (AI) in dermatology has increased exponentially. The objective of this study was to perform a systematic review and... (Review)
Review
Scientific research of artificial intelligence (AI) in dermatology has increased exponentially. The objective of this study was to perform a systematic review and meta-analysis to evaluate the performance of AI algorithms for skin cancer classification in comparison to clinicians with different levels of expertise. Based on PRISMA guidelines, 3 electronic databases (PubMed, Embase, and Cochrane Library) were screened for relevant articles up to August 2022. The quality of the studies was assessed using QUADAS-2. A meta-analysis of sensitivity and specificity was performed for the accuracy of AI and clinicians. Fifty-three studies were included in the systematic review, and 19 met the inclusion criteria for the meta-analysis. Considering all studies and all subgroups of clinicians, we found a sensitivity (Sn) and specificity (Sp) of 87.0% and 77.1% for AI algorithms, respectively, and a Sn of 79.78% and Sp of 73.6% for all clinicians (overall); differences were statistically significant for both Sn and Sp. The difference between AI performance (Sn 92.5%, Sp 66.5%) vs. generalists (Sn 64.6%, Sp 72.8%), was greater, when compared with expert clinicians. Performance between AI algorithms (Sn 86.3%, Sp 78.4%) vs expert dermatologists (Sn 84.2%, Sp 74.4%) was clinically comparable. Limitations of AI algorithms in clinical practice should be considered, and future studies should focus on real-world settings, and towards AI-assistance.
PubMed: 38744955
DOI: 10.1038/s41746-024-01103-x -
Journal of Cosmetic Dermatology May 2024To provide dermatologists with more clinical experience in treating androgenetic alopecia, we evaluated the effect and safety of combined microneedling therapy for... (Meta-Analysis)
Meta-Analysis
OBJECTIVE
To provide dermatologists with more clinical experience in treating androgenetic alopecia, we evaluated the effect and safety of combined microneedling therapy for androgenetic alopecia.
METHODS
Studies on combined microneedling for hair loss were comprehensively searched by us in PubMed, Excerpta Medica Database, and the Cochrane Library Database. The literature search spanned the period from 2012 to 2022. Inclusion and exclusion criteria were developed, and the literature was screened according to this criteria. The Cochrane Risk of Bias Tool was used to assess the quality of the studies. The researcher applied Revman 5.3 and Stata 15.1 software to analyze the data after extracting information from the data.
RESULTS
Finally, 13 RCTs involving 696 AGA patients were included to compare the clinical effectiveness and adverse events of combined MN therapy with single MN therapy or single drug therapy for AGA. The results of meta-analysis showed as follows: (1) Hair density and diameter changes: The combined MN group was significantly better than any single treatment group, and the differences were statistically significant (MD = 13.36, 95% CI = [8.55, 18.16], Z = 5.45, p < 0.00001; MD = 18.11, 95% CI = [13.70, 22.52], Z = 8.04, p < 0.00001; MD = 13.36, 95% CI = [8.55, 18.16], Z = 5.45, p < 0.00001; MD = 2.50, 95% CI = [0.99, 4.02], Z = 3.23, p = 0.001); (2) the evaluation of satisfaction for efficacy: The doctor satisfaction rating of the combined MN group was significantly higher than that of any single treatment group, with statistical difference (RR = 2.03, 95% CI = [1.62, 2.53], Z = 6.24, p < 0.00001). The difference between the two groups regarding patients satisfaction was not significant (RR = 3.44, 95% CI = [0.67, 17.59], Z = 1.49, p = 0.14). (3) Safety: There was no statistical difference in the incidence of adverse reactions between combination therapy and monotherapy (RR = 0.83, 95% CI = [0.62, 1.12], Z = 1.22, p = 0.22).
CONCLUSION
The combined MN group showed statistically significant improvement in hair density and diameter, and good safety compared with monotherapy.
Topics: Humans; Alopecia; Combined Modality Therapy; Cosmetic Techniques; Dry Needling; Hair; Needles; Patient Satisfaction; Percutaneous Collagen Induction; Treatment Outcome
PubMed: 38239003
DOI: 10.1111/jocd.16186 -
Sensors (Basel, Switzerland) Oct 2023Skin cancer is considered a dangerous type of cancer with a high global mortality rate. Manual skin cancer diagnosis is a challenging and time-consuming method due to... (Review)
Review
Skin cancer is considered a dangerous type of cancer with a high global mortality rate. Manual skin cancer diagnosis is a challenging and time-consuming method due to the complexity of the disease. Recently, deep learning and transfer learning have been the most effective methods for diagnosing this deadly cancer. To aid dermatologists and other healthcare professionals in classifying images into melanoma and nonmelanoma cancer and enabling the treatment of patients at an early stage, this systematic literature review (SLR) presents various federated learning (FL) and transfer learning (TL) techniques that have been widely applied. This study explores the FL and TL classifiers by evaluating them in terms of the performance metrics reported in research studies, which include true positive rate (TPR), true negative rate (TNR), area under the curve (AUC), and accuracy (ACC). This study was assembled and systemized by reviewing well-reputed studies published in eminent fora between January 2018 and July 2023. The existing literature was compiled through a systematic search of seven well-reputed databases. A total of 86 articles were included in this SLR. This SLR contains the most recent research on FL and TL algorithms for classifying malignant skin cancer. In addition, a taxonomy is presented that summarizes the many malignant and non-malignant cancer classes. The results of this SLR highlight the limitations and challenges of recent research. Consequently, the future direction of work and opportunities for interested researchers are established that help them in the automated classification of melanoma and nonmelanoma skin cancers.
Topics: Humans; Prospective Studies; Skin Neoplasms; Melanoma; Skin; Machine Learning
PubMed: 37896548
DOI: 10.3390/s23208457 -
Frontiers in Endocrinology 2023The aim of the study was to identify available polycystic ovary syndrome (PCOS) models of care (MoCs) and describe their characteristics and alignment with the...
INTRODUCTION
The aim of the study was to identify available polycystic ovary syndrome (PCOS) models of care (MoCs) and describe their characteristics and alignment with the international PCOS guideline.
METHODS
Ovid MEDLINE, All EBM, PsycINFO, Embase, and CINAHL were searched from inception until 11 July 2022. Any study with a description of a PCOS MoC was included. Non-evidence-based guidelines, abstracts, study protocols, and clinical trial registrations were excluded. We also excluded MoCs delivered in research settings to minimize care bias. Meta-analysis was not performed due to heterogeneity across MoCs. We describe and evaluate each MoC based on the recommendations made by the international evidence-based guideline for assessing and managing PCOS.
RESULTS
Of 3,671 articles, six articles describing five MoCs were included in our systematic review. All MoCs described a multidisciplinary approach, including an endocrinologist, dietitian, gynecologist, psychologist, dermatologist, etc. Three MoCs described all aspects of PCOS care aligned with the international guideline recommendations. These include providing education on long-term risks, lifestyle interventions, screening and management of emotional well-being, cardiometabolic diseases, and the dermatological and reproductive elements of PCOS. Three MoCs evaluated patients' and healthcare professionals' satisfaction, with generally positive findings. Only one MoC explored the impact of their service on patients' health outcomes and showed improvement in BMI.
CONCLUSION
There is limited literature describing PCOS MoCs in routine practice. Future research should explore developing cost-effective co-created multidisciplinary PCOS MoCs globally. This may be facilitated by the exchange of best practices between institutions with an established MoC and those who are interested in setting one up.
SYSTEMATIC REVIEW REGISTRATION
https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=346539, identifier CRD42022346539.
Topics: Female; Humans; Developing Countries; Educational Status; Emotions; Endocrinologists; Polycystic Ovary Syndrome
PubMed: 37614710
DOI: 10.3389/fendo.2023.1217468 -
NPJ Digital Medicine Apr 2024The development of diagnostic tools for skin cancer based on artificial intelligence (AI) is increasing rapidly and will likely soon be widely implemented in clinical... (Review)
Review
The development of diagnostic tools for skin cancer based on artificial intelligence (AI) is increasing rapidly and will likely soon be widely implemented in clinical use. Even though the performance of these algorithms is promising in theory, there is limited evidence on the impact of AI assistance on human diagnostic decisions. Therefore, the aim of this systematic review and meta-analysis was to study the effect of AI assistance on the accuracy of skin cancer diagnosis. We searched PubMed, Embase, IEE Xplore, Scopus and conference proceedings for articles from 1/1/2017 to 11/8/2022. We included studies comparing the performance of clinicians diagnosing at least one skin cancer with and without deep learning-based AI assistance. Summary estimates of sensitivity and specificity of diagnostic accuracy with versus without AI assistance were computed using a bivariate random effects model. We identified 2983 studies, of which ten were eligible for meta-analysis. For clinicians without AI assistance, pooled sensitivity was 74.8% (95% CI 68.6-80.1) and specificity was 81.5% (95% CI 73.9-87.3). For AI-assisted clinicians, the overall sensitivity was 81.1% (95% CI 74.4-86.5) and specificity was 86.1% (95% CI 79.2-90.9). AI benefitted medical professionals of all experience levels in subgroup analyses, with the largest improvement among non-dermatologists. No publication bias was detected, and sensitivity analysis revealed that the findings were robust. AI in the hands of clinicians has the potential to improve diagnostic accuracy in skin cancer diagnosis. Given that most studies were conducted in experimental settings, we encourage future studies to further investigate these potential benefits in real-life settings.
PubMed: 38594408
DOI: 10.1038/s41746-024-01031-w -
JMIR Dermatology Dec 2023Dermatological conditions, especially when severe, can lead to sleep disturbances that affect a patient's quality of life. However, limited research exists on the... (Review)
Review
BACKGROUND
Dermatological conditions, especially when severe, can lead to sleep disturbances that affect a patient's quality of life. However, limited research exists on the efficacy of treatments for improving sleep parameters in skin conditions.
OBJECTIVE
The objective was to perform a systematic review of the literature on dermatological conditions and the treatments available for improving sleep parameters.
METHODS
A literature review was performed using the PubMed, Ovid MEDLINE, Embase, Cochrane, and ClinicalTrials.gov databases from 1945 to 2021. After filtering based on our exclusion criteria, studies were graded using the SORT (Strength of Recommendation Taxonomy) algorithm, and only those receiving a grade of "2" or better were included.
RESULTS
In total, 25 treatment studies (n=11,025) assessing sleep parameters related to dermatological conditions were found. Dupilumab appeared to be the best-supported and most effective treatment for improving sleep in atopic dermatitis (AD) but had frequent adverse effects. Topical treatments for AD were mostly ineffective, but procedural treatments showed some promise. Treatments for other conditions appeared efficacious.
CONCLUSIONS
The evaluation of sleep parameter changes in dermatological treatments is predominantly restricted to AD. Systemic interventions such as dupilumab and procedural interventions were the most efficacious. Sleep changes in other dermatoses were limited by a paucity of available studies. The inclusion of a sleep assessment component to a broader range of dermatological treatment studies is warranted.
PubMed: 38090791
DOI: 10.2196/48713 -
Archives of Dermatological Research Jun 2024Steven Johnson Syndrome (SJS) and Toxic Epidermal Necrolysis (TEN), grouped together under the terminology of epidermal necrolysis (EN), are a spectrum of... (Review)
Review
Steven Johnson Syndrome (SJS) and Toxic Epidermal Necrolysis (TEN), grouped together under the terminology of epidermal necrolysis (EN), are a spectrum of life-threatening dermatologic conditions. A lack of standardization and validation for existing endpoints has been identified as a key barrier to the comparison of these therapies and development of evidenced-based treatment. Following PRISMA guidelines, we conducted a systematic review of prospective studies involving systemic or topical treatments for EN, including dressing and ocular treatments. Outcomes were separated into mortality assessment, cutaneous outcomes, non-cutaneous clinical outcomes, and mucosal outcomes. The COSMIN Risk of Bias tool was used to assess the quality of studies on reliability and measurement error of outcome measurement instruments. Outcomes across studies assessing treatment in the acute phase of EN were varied. Most data came from prospective case reports and cohort studies representing the lack of available randomized clinical trial data available in EN. Our search did not reveal any EN-specific validated measures or scoring tools used to assess disease progression and outcomes. Less than half of included studies were considered "adequate" for COSMIN risk of bias in reliability and measurement error of outcome measurement instruments. With little consensus about management and treatment of EN, consistency and validation of measured outcomes is of the upmost importance for future studies to compare outcomes across treatments and identify the most effective means of combating the disease with the highest mortality managed by dermatologists.
Topics: Humans; Stevens-Johnson Syndrome; Reproducibility of Results; Outcome Assessment, Health Care; Treatment Outcome; Bandages
PubMed: 38878166
DOI: 10.1007/s00403-024-03062-5