ABSTRACT
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.
ABSTRACT
Cutaneous tuberculosis represents 1-1.5% of extrapulmonary tuberculosis, including a variety of clinical conditions. Scrofuloderma and lupus vulgaris are the most common forms. We report a 49-year-old woman who sought medical attention through tele-dermatology concerning a cervical nodule associated with suppuration and cutaneous involvement. The diagnoses of scrofuloderma and pulmonary tuberculosis were confirmed, and during her evolution she presented a coinfection with SARS-CoV-2. The possible associations between tuberculosis and COVID-19 were reviewed.
Subject(s)
COVID-19 , Tuberculosis, Cutaneous , Tuberculosis, Pulmonary , COVID-19/complications , Female , Humans , Middle Aged , Tuberculosis, Cutaneous/complications , Tuberculosis, Cutaneous/diagnosis , Tuberculosis, Pulmonary/complications , Tuberculosis, Pulmonary/diagnosisABSTRACT
Cutaneous tuberculosis represents 1-1.5% of extrapulmonary tuberculosis, including a variety of clinical conditions. Scrofuloderma and lupus vulgaris are the most common forms. We report a 49-year-old woman who sought medical attention through tele-dermatology concerning a cervical nodule associated with suppuration and cutaneous involvement. The diagnoses of scrofuloderma and pulmonary tuberculosis were confirmed, and during her evolution she presented a coinfection with SARS-CoV-2. The possible associations between tuberculosis and COVID-19 were reviewed.
Subject(s)
Humans , Female , Middle Aged , Tuberculosis, Cutaneous/complications , Tuberculosis, Cutaneous/diagnosis , Tuberculosis, Pulmonary/complications , Tuberculosis, Pulmonary/diagnosis , COVID-19/complicationsABSTRACT
Background: Stevens-Johnson Syndrome (SSJ) and Toxic Epidermal Necrolysis (NET) are infrequent and life-threatening mucocutaneous diseases, which occur predominantly as adverse drug reactions. Aim: To describe the frequency of SSJ and NET diagnoses at a national level, estimate their incidence and describe their distribution among the different regions of the country. Material and Methods: Analysis of hospital discharge databases available at the website of the Chilean Ministry of Health searching for the tenth version of the International Classification of Diseases (ICD 10) codes for SSJ or NET, between 2001 and 2015. Results: We analyzed 24,521,796 hospital discharges nationwide. SSJ caused 855 discharges, with a lethality of 2%. NET caused 128 discharges with a lethality of 16%. The global cumulative incidence was 3.87 cases per million inhabitants per year nationwide, with a trend line to increase incidence towards the regions of higher latitude. Conclusions: SSJ and NET are dermatological emergencies with high mortality. The increase in incidence towards regions at higher latitudes may suggest an association between these conditions and lower levels of vitamin D, correlated with latitude and exposure to UV radiation.
Subject(s)
Humans , Patient Discharge/statistics & numerical data , Stevens-Johnson Syndrome/epidemiology , Chile/epidemiology , Databases, Factual , Hospital Information SystemsABSTRACT
BACKGROUND: Stevens-Johnson Syndrome (SSJ) and Toxic Epidermal Necrolysis (NET) are infrequent and life-threatening mucocutaneous diseases, which occur predominantly as adverse drug reactions. AIM: To describe the frequency of SSJ and NET diagnoses at a national level, estimate their incidence and describe their distribution among the different regions of the country. MATERIAL AND METHODS: Analysis of hospital discharge databases available at the website of the Chilean Ministry of Health searching for the tenth version of the International Classification of Diseases (ICD 10) codes for SSJ or NET, between 2001 and 2015. RESULTS: We analyzed 24,521,796 hospital discharges nationwide. SSJ caused 855 discharges, with a lethality of 2%. NET caused 128 discharges with a lethality of 16%. The global cumulative incidence was 3.87 cases per million inhabitants per year nationwide, with a trend line to increase incidence towards the regions of higher latitude. CONCLUSIONS: SSJ and NET are dermatological emergencies with high mortality. The increase in incidence towards regions at higher latitudes may suggest an association between these conditions and lower levels of vitamin D, correlated with latitude and exposure to UV radiation.