Lack of Transparency and Potential Bias in Artificial Intelligence Data Sets and Algorithms: A Scoping Review.

IMPORTANCE: Clinical artificial intelligence (AI) algorithms have the potential to improve clinical care, but fair, generalizable algorithms depend on the clinical data on which they are trained and tested. OBJECTIVE: To assess whether data sets used for training diagnostic AI algorithms addressing skin disease are adequately described and to identify potential sources of bias in these data sets. DATA SOURCES: In this scoping review, PubMed was used to search for peer-reviewed research articles published between January 1, 2015, and November 1, 2020, with the following paired search terms: deep learning and dermatology, artificial intelligence and dermatology, deep learning and dermatologist, and artificial intelligence and dermatologist. STUDY SELECTION: Studies that developed or tested an existing deep learning algorithm for triage, diagnosis, or monitoring using clinical or dermoscopic images of skin disease were selected, and the articles were independently reviewed by 2 investigators to verify that they met selection criteria. CONSENSUS PROCESS: Data set audit criteria were determined by consensus of all authors after reviewing existing literature to highlight data set transparency and sources of bias. RESULTS: A total of 70 unique studies were included. Among these studies, 1 065 291 images were used to develop or test AI algorithms, of which only 257 372 (24.2%) were publicly available. Only 14 studies (20.0%) included descriptions of patient ethnicity or race in at least 1 data set used. Only 7 studies (10.0%) included any information about skin tone in at least 1 data set used. Thirty-six of the 56 studies developing new AI algorithms for cutaneous malignant neoplasms (64.3%) met the gold standard criteria for disease labeling. Public data sets were cited more often than private data sets, suggesting that public data sets contribute more to new development and benchmarks. CONCLUSIONS AND RELEVANCE: This scoping review identified 3 issues in data sets that are used to develop and test clinical AI algorithms for skin disease that should be addressed before clinical translation: (1) sparsity of data set characterization and lack of transparency, (2) nonstandard and unverified disease labels, and (3) inability to fully assess patient diversity used for algorithm development and testing.

Beyond the Booth: Excimer Laser for Cutaneous Conditions.

The excimer laser has emerged as an efficacious treatment modality for many dermatologic diseases. The excimer laser is an alternative to standard narrowband ultraviolet B (NBUVB) phototherapy treatment in patients with limited disease. In comparison to standard NBUVB, the excimer laser requires fewer treatment sessions, has reduced treatment duration, requires a lower cumulative UVB dose, and limits UVB exposure to lesional skin. This review addresses the mechanism, safety, application, and efficacy of the excimer laser for the treatment of these conditions.

Tofacitinib in the management of active psoriatic arthritis: patient selection and perspectives.

Tofacitinib is an oral Janus kinase inhibitor approved for the treatment of psoriatic arthritis (PsA). It provides an alternative option for patients who have had an inadequate response and tolerance to other disease modifying antirheumatic drugs (DMARDs). It has demonstrated comparable efficacy to biologics, is effective in the management of treatment resistant disease, and is reported to improve enthesitis, dactylitis, and radiographic progression. Tofacitinib is also associated with an increased risk of serious infections, malignancy, and laboratory abnormalities. There is currently a large armamentarium of therapies for psoriatic arthritis, and choosing among treatments can be challenging. Due to this wide selection, a thorough assessment of psoriatic disease phenotype, patient preference, disease presentation, and comorbidities is critical. This review addresses key considerations in patient selection for the treatment of PsA with tofacitinib.

Anti IL-17 in psoriasis.

Introduction: Psoriasis is a chronic, immune-mediated disease with significant associated comorbidities. Its pathogenesis is likely multifactorial, however, the interleukin-23/T helper 17 pathway has been identified as a critical axis in its pathogenesis. Interleukin-17A is the primary effector of this pathway and overexpression of IL-17A results in epidermal hyperplasia and an overly robust inflammatory response, resulting in the skin plaques and systemic inflammation seen in psoriasis. Targeted anti IL-17 therapies have demonstrated efficacy in the treatment of moderate-to-severe plaque psoriasis.Areas covered: A PubMed search was conducted for relevant literature. Secukinumab, ixekizumab, and brodalumab are anti IL-17 inhibitors currently approved for the treatment of moderate-to-severe plaque psoriasis. The efficacy and safety data from key phase III clinical trials are reviewed here.Expert opinion: By targeting a key mediator of the interleukin-23/T helper 17 pathway, IL-17 antagonists are an effective treatment for plaque psoriasis. It has demonstrated efficacy and a favorable safety profile in key phase III clinical trials. In addition to efficacy, IL-17 antagonists have also shown long-term maintenance of treatment response and a quick onset of action. The efficacy of IL-17 inhibitors in the treatment of moderate-to-severe psoriasis underscores the importance of the IL-23/Th17 pathway in the pathogenesis of psoriasis.

Diagnosis and screening of patients with generalized pustular psoriasis.

Generalized pustular psoriasis (GPP) is a rare and potentially life-threatening variant of psoriasis that is characterized by recurrent, acute onset, widely distributed pustular eruptions on inflamed, erythematous skin. It is important to recognize acute GPP as a subtype of psoriasis associated with high morbidity and mortality so therapy can be initiated without delay. Since GPP was first described in 1910 by Leopold von Zumbusch, it has been inconsistently defined, stratified, and diagnosed in the literature. Multiple definitions and diagnostic criteria have been proposed over the years. Recently, formal consensus guidelines on GPP have been published by international groups. This article reviews the current evidence and understanding in the diagnosis and screening of GPP.