The state of artificial intelligence for systemic dermatoses: Background and applications for psoriasis, systemic sclerosis, and much more

Artificial intelligence (AI) has been steadily integrated into dermatology, with AI platforms already attempting to identify skin cancers and diagnose benign versus malignant lesions. Although not as widely known, AI programs have also been utilized as diagnostic and prognostic tools for dermatologic conditions with systemic or extracutaneous involvement, especially for diseases with autoimmune etiologies. We have provided a primer on commonly used AI platforms and the practical applicability of these algorithms in dealing with psoriasis, systemic sclerosis, and dermatomyositis as a microcosm for future directions in the field. With a rapidly changing landscape in dermatology and medicine as a whole, AI could be a versatile tool to support clinicians and enhance access to care.

Artificial intelligence in psoriasis: Where we are and where we are going

Artificial intelligence (AI) is a field of computer science that involves the development of programs designed to replicate human cognitive processes and the analysis of complex data. In dermatology, which is predominantly a visual-based diagnostic field, AI has become increasingly important in improving professional processes, particularly in the diagnosis of psoriasis. In this review, we summarized current AI applications in psoriasis: (i) diagnosis, including identification, classification, lesion segmentation, lesion severity and area scoring; (ii) treatment, including prediction treatment efficiency and prediction candidate drugs; (iii) management, including e-health and preventive medicine. Key challenges and future aspects of AI in psoriasis were also discussed, in hope of providing potential directions for future studies.

Therapeutic application of machine learning in psoriasis: A Prisma systematic review

Dermatology, being a predominantly visual-based diagnostic field, has found itself to be at the epitome of artificial intelligence (AI)-based advances. Machine learning (ML), a subset of AI, goes a step further by recognizing patterns from data and teaches machines to automatically learn tasks. Although artificial intelligence in dermatology is mostly developed in melanoma and skin cancer diagnosis, advances in AI and ML have gone far ahead and found its application in ulcer assessment, psoriasis, atopic dermatitis, onychomycosis, etc. This article is focused on the application of ML in the therapeutic aspect of psoriasis.

Joint AAD-NPF Guidelines of care for the management and treatment of psoriasis with topical therapy and alternative medicine modalities for psoriasis severity measures

Psoriasis is a chronic, inflammatory, multisystem disease that affects up to 3.2% of the United States population. This guideline addresses important clinical questions that arise in psoriasis management and care and provides recommendations based on the available evidence. The treatment of psoriasis with topical agents and with alternative medicine will be reviewed, emphasizing treatment recommendations and the role of dermatologists in monitoring and educating patients regarding benefits as well as risks that may be associated. This guideline will also address the severity assessment methods of psoriasis in adults.

Measurement of body surface area in atopic dermatitis using specific PC software (ScoradCard)

In skin diseases, evaluation of involved surface area is a crucial factor in grading the degree of severity. We examined the reliability of body surface area assessment and relative inter-observer and intra-observer variability using new software (ScoraCard), specifically designed to evaluate automatically the extension of the involved area in the SCORAD index. Twenty pediatricians, untrained in the evaluation of skin disease, estimated the percentage of surface area involved in photo-tests of two children with artificial well-delimited lesions, at first by sight and then through software. As "gold standard" the exact amount of pixels was counted for the whole body surface of the children, for the different body zones and for the painted artificial lesions, expressed as percentage of the respective zone. For photo 1, gold standard was 38.06% and median percentage was 43.44% (95% CI 40.7-46.21) by sight (p = 0.002) and 37.99% (95% CI 36.04-39.94) by ScoradCard (p = 0.79). For photo 2, gold standard was 27.84%, median percentage was 30.44% (95% CI 28.25-32.63) by sight (p = 0.047) and 27.8% (95% CI 26.55-29.04) by ScoradCard (p = 0.79). The level of agreement (kappa statistic), cumulative for the two photo tests, was 0.38 (fair agreement) by sight method and 0.67 (good agreement) by ScoradCard. Among the 10 pediatricians who repeated the computer aided evaluation 3 months apart, the intra-observer variability was not significantly different: the median percentage was 31.5% (95% CI 27.0-49.4) at time 0 and 29.0% (95% CI 26.7-47.2) 3 months later (p = 0.76). This new software could be a useful tool in evaluating skin lesions extension, minimizing inter- and intra-observer variability, which is an important goal in multi-centre studies.

Clinical measures of disease severity and outcome in psoriasis: a critical appraisal of their quality

In clinical trials, a wide range of outcome measures has been used to evaluate the severity of psoriasis and its response to treatment. Despite their widespread use, many measures have received little attention with regards to their reliability and validity. Selecting an appropriately developed measurement tool is therefore of critical importance. We conducted a literature survey to examine the status of clinical outcome measures used in psoriasis research. The measures most commonly used were individual sign scores, e.g. for erythema, plaque thickness or scaling, and pooled indices, e.g. the Psoriasis Area and Severity Index. None of these, however, systematically fulfilled all the requirements of a validated instrument for disease assessment. Ideally, a core set of reliable and validated outcome measures for use in all psoriasis clinical trials is needed. Objective instrumental methods should minimise observer variation, but unless a simple non-invasive method can be developed, the uptake of such technology will probably be limited by cost and lack of practicality. Moreover, the translation of instrumental readings into clinically relevant measures is always a major problem, and for none of the methods has there been a robust mapping of instrumental readings on to a clinically meaningful scale. Further research is needed to determine the most appropriate and sensitive parameters to use as surrogate measures for capturing the distress which psoriatic patients feel but which is not measured with sufficient sensitivity or precision with current quality of life or distress questionnaires.