Use of Artificial Intelligence as a Predictor of the Response to Treatment in Alopecia Areata

Background Artificial intelligence (AI) has emerged in dermatology with some studies focusing on skin disorders such as skin cancer, atopic dermatitis, psoriasis, and onychomycosis. Alopecia areata (AA) is a dermatological disease whose prevalence is 0.7%-3% in the United States, and is characterized by oval areas of nonscarring hair loss of the scalp or body without evident clinical variables to predict its response to the treatment. Nonetheless, some studies suggest a predictive value of trichoscopic features in the evaluation of treatment responses. Assuming that black dots, broken hairs, exclamation marks, and tapered hairs are markers of negative predictive value of the treatment response, while yellow dots are markers of no response to treatment according to recent studies, the absence of these trichoscopic features could indicate favorable disease evolution without treatment or even predict its response. Nonetheless, no studies have reportedly evaluated the role of AI in AA on the basis of trichoscopic features. Objective This study aimed to develop an AI algorithm to predict, using trichoscopic images, those patients diagnosed with AA with a better disease evolution. Methods In total, 80 trichoscopic images were included and classified in those with or without features of negative prognosis. Using a data augmentation technique, they were multiplied to 179 images to train an AI algorithm, as previously carried out with dermoscopic images of skin tumors with a favorable response. Subsequently, 82 new images of AA were presented to the algorithm, and the algorithm classified these patients as responders and non-responders; this process was reviewed by an expert trichologist observer and presented a concordance higher than 90% with the algorithm identifying structures described previously. Evolution of the cases was followed up to truly determine their response to treatment and, therefore, to assess the predictive value of the algorithm. Results In total, 32 of 40 (80%) images of patients predicted as nonresponders scarcely showed response to the treatment, while 34 of 42 (81%) images of those predicted as responders showed a favorable response to the treatment. Conclusions The development of an AI algorithm or tool could be useful to predict AA evolution and its response to treatment. However, further research is needed, including larger sample images or trained algorithms, by using images previously classified in accordance with the disease evolution and not with trichoscopic features. Conflicts of Interest None declared.

Use of Artificial Intelligence as a Predictor of the Response to Treatment in Alopecia Areata (Preprint)

BACKGROUND Artificial intelligence (AI) has emerged in dermatology with some studies focusing on skin disorders such as skin cancer, atopic dermatitis, psoriasis, and onychomycosis. Alopecia areata (AA) is a dermatological disease whose prevalence is 0.7%-3% in the United States, and is characterized by oval areas of nonscarring hair loss of the scalp or body without evident clinical variables to predict its response to the treatment. Nonetheless, some studies suggest a predictive value of trichoscopic features in the evaluation of treatment responses. Assuming that black dots, broken hairs, exclamation marks, and tapered hairs are markers of negative predictive value of the treatment response, while yellow dots are markers of no response to treatment according to recent studies, the absence of these trichoscopic features could indicate favorable disease evolution without treatment or even predict its response. Nonetheless, no studies have reportedly evaluated the role of AI in AA on the basis of trichoscopic features. OBJECTIVE This study aimed to develop an AI algorithm to predict, using trichoscopic images, those patients diagnosed with AA with a better disease evolution. METHODS In total, 80 trichoscopic images were included and classified in those with or without features of negative prognosis. Using a data augmentation technique, they were multiplied to 179 images to train an AI algorithm, as previously carried out with dermoscopic images of skin tumors with a favorable response. Subsequently, 82 new images of AA were presented to the algorithm, and the algorithm classified these patients as responders and non-responders; this process was reviewed by an expert trichologist observer and presented a concordance higher than 90% with the algorithm identifying structures described previously. Evolution of the cases was followed up to truly determine their response to treatment and, therefore, to assess the predictive value of the algorithm. RESULTS In total, 32 of 40 (80%) images of patients predicted as nonresponders scarcely showed response to the treatment, while 34 of 42 (81%) images of those predicted as responders showed a favorable response to the treatment. CONCLUSIONS The development of an AI algorithm or tool could be useful to predict AA evolution and its response to treatment. However, further research is needed, including larger sample images or trained algorithms, by using images previously classified in accordance with the disease evolution and not with trichoscopic features.

COVID-19 and Psoriasis: A Concise Systematic Review

Introduction: The effects on human health caused by the severe acute respiratory syndrome of coronavirus 2 (SARS-CoV-2) lead to hyperinflammation processes, which can lead to meta-inflammation. This process can aggravate skin diseases, especially psoriasis. This is a chronic inflammatory skin disease associated with significant morbidity. This problem affects about 2-3% of people worldwide. Objective: to demonstrate, through a concise systematic review, the main considerations about the relationship between COVID-19 and psoriasis, showing the possible mechanisms for the worsening of this dermatological disease. Methods: The research was carried out from June 2021 to July 2021 and developed based on Scopus, PubMed, Science Direct, Scielo, and Google Scholar, following the Systematic Review-PRISMA rules. The quality of the studies was based on the GRADE instrument and the risk of bias was analyzed according to the Cochrane instrument. Results: Psoriasis is a common chronic inflammatory skin disease and is autoimmune. Patients with COVID-19 may have features of hyper inflammation and even meta-inflammation. The triggering or exacerbating factor of psoriasis may be medications and, in addition, patients with COVID-19 may have psoriasis exacerbation. Reports indicated that psoriasis patients using biological products were no longer susceptible to COVID-19 and the severe clinical course of the disease. It is envisioned that the use of azithromycin in cases of COVID 19 with pre-existing psoriasis can alleviate psoriatic lesions. Conclusion: The COVID 19 pandemic had a direct impact on dermatological diseases, especially psoriasis. Difficulty in accessing health care services and the stress load caused exacerbations in psoriasis cases. Studies recommend avoiding classic immunosuppressive agents such as methotrexate, cyclosporine, and TNF alpha inhibitors. Reports indicated that psoriasis patients using biological products were no longer susceptible to COVID-19 and the severe clinical course of the disease.

P079 Multi-systemic inflammatory syndrome in children: skin tropism

Background Multisystem inflammatory syndrome in children (MIS-C) is a severe immune-mediated syndrome that occurs after COVID-19 infection. It mainly affects children and presents several clinical aspects. The cutaneous and mucous signs are very much part of the diagnostic criteria. The aimisto describe the clinical and evolutionary aspects of the muco-cutaneous signs during MIS-C Patients and methods It was a descriptive retrospective study conducted over a period of 9 months (March 1, 2020 - December 31, 2020) including children admitted to COVID isolation unit with suspicion of MIS-C syndrome. Results We included 17 patients. The average age was 7 years (1–11 years). The sex ratio was 2.2 (11 boys and 6 girls). There was o history of dermatological disease has been reported. Fever was present in all patients. Mucosal signs were present in 13 patients. Conjunctival hyperemia without purulent secretions was noted in 12 patients. Conjunctivitis was bilateral in 11 cases. A rash was found in 10 cases. It was macular (6 cases), maculopapular (2 cases) and vesicular cluster in one 1 case. It was itchy in 2 cases. It was located in the limbs (7 cases), thorax and/or abdomen (5 cases), pelvis (4 cases), palms and/or soles (3 cases) and the face in one case. Cheilitis was found in 6 cases and stomatitis or glossitis in 5 cases. oEdema of the extremities was present in three patients and oedema of the face was noted in one patient. All children received intravenous immunoglobulin therapy combined with high-dose corticosteroids and acetylsalicylic acid at anti-aggregating doses. The course was marked by the disappearance of the muco-cutaneous signs without recurrence in all cases. Conclusion Mucocutaneous involvement is a characteristic manifestation of multisystem inflammatory syndrome. It is one of the various diagnostic criteria for this syndrome.

The oral manifestations of scurvy in the 21st century

Scurvy is a vitamin deficiency historically associated with pirates and sailors that affects collagen synthesis, leading to hemorrhage, skin, and oral lesions. In the 18th century, the lack of consumption of foods rich in vitamin C was found to cause such a severe condition, whose early diagnosis increases the likelihood of a better prognosis. A 58-year-old female patient complained of fatigue, body pain, and gingival bleeding for nearly 24 months. In 2001, she was diagnosed with lupus, now in remission, and osteoporosis more recently. On clinical examination, gingivitis with spontaneous bleeding was observed, despite the patient’s good hygiene, as well as some petechiae over the body. Due to the hypothesis of a possible autoimmune dermatological disease, the patient was referred to a dermatologist, who requested a series of tests, including vitamin C dosage. The results showed a concentration below 0.25mg / dL (IR, 4 to 2.0 mg / dL), and thus the diagnosis of scurvy was established. The patient was administered vitamin C replacement and in about 3 months, the symptoms started to improve. In some cases, such as this, hospitalization is required for intravenous replacement due to bleeding risks. This case report highlights the importance of the dentist in the early diagnosis and treatment of scurvy. This condition causes oral lesions that are often confused with other more common conditions, such as gingivitis or autoimmune dermatological response. Therefore, we recommend a comprehensive physical examination and anamnesis, including dietary history.

International Dermatology Outcome Measures (IDEOM): Report from the 2020 Annual Meeting

<b><i>Background:</i></b> The International Dermatology Outcome Measures (IDEOM) initiative is a non-profit organization that aims to develop evidence-based outcome measurements to evaluate the impact of treatments for patients with dermatological disease. IDEOM includes all key stakeholders in dermatology (patient, physician, industry, insurer, and government) during the process of developing such outcome measurements. <b><i>Summary:</i></b> Here, we provide an update of IDEOM activities that were presented at the 2020 IDEOM Virtual Annual Meeting (October 23–24, 2020). During the meeting, multiple IDEOM workgroups (psoriasis, psoriatic arthritis, hidradenitis suppurativa, acne, pyoderma gangrenosum, and actinic keratosis) shared their progress to date, as well as future directions in developing and validating Patient-Reported Outcome Measures. Updates on demonstrating efficacy in clinicals trials by the US Food and Drug Administration are also summarized. <b><i>Key Messages:</i></b> In this report, we summarize the work presented by each IDEOM workgroup (psoriasis, psoriatic arthritis, hidradenitis suppurativa, acne, pyoderma gangrenosum, and actinic keratosis) at the 2020 IDEOM Virtual Annual Meeting.