Background
The use of artificial intelligence (AI) algorithms for the diagnosis of skin diseases has shown promise in experimental settings but has not been yet tested in real‐life conditions.
Objective
To assess the diagnostic performance and potential clinical utility of a 174‐multiclass AI algorithm in a real‐life telemedicine setting.
Methods
Prospective, diagnostic accuracy study including consecutive patients who submitted images for teledermatology evaluation. The treating dermatologist chose a single image to upload to a web application during teleconsultation. A follow‐up reader study including nine healthcare providers (3 dermatologists, 3 dermatology residents and 3 general practitioners) was performed.
Results
A total of 340 cases from 281 patients met study inclusion criteria. The mean (SD) age of patients was 33.7 (17.5) years; 63% (n = 177) were female. Exposure to the AI algorithm results was considered useful in 11.8% of visits (n = 40) and the teledermatologist correctly modified the real‐time diagnosis in 0.6% (n = 2) of cases. The overall top‐1 accuracy of the algorithm (41.2%) was lower than that of the dermatologists (60.1%), residents (57.8%) and general practitioners (49.3%) (all comparisons P < 0.05, in the reader study). When the analysis was limited to the diagnoses on which the algorithm had been explicitly trained, the balanced top‐1 accuracy of the algorithm (47.6%) was comparable to the dermatologists (49.7%) and residents (47.7%) but superior to the general practitioners (39.7%; P = 0.049). Algorithm performance was associated with patient skin type and image quality.
Conclusions
A 174‐disease class AI algorithm appears to be a promising tool in the triage and evaluation of lesions with patient‐taken photographs via telemedicine.
Objectives
To detect ultrasonographic inflammatory signs in the lacrimal, parotid, and submandibular glands in cosmetic fillers (CFs) users.
Methods
A prospective and cross‐sectional ultrasound study of the glands in cases with CFs was performed. The sample included users of hyaluronic acid, silicone oil, polymethylmethacrylate, polycaprolactone, calcium hydroxyapatite, and polyacrylamide.
Abnormalities of the parenchyma and hypervascularity signs of the glands were compared with a control group (n = 10), evaluated by 2 observers, and correlated with the type, number, and location of the facial CFs. Cohen's kappa test and logistic regression models with odds ratios (OR) adjusted by age with 95% CI were performed.
Results
Sixty‐three patients with CFs met the criteria. Parotid and submandibular glands had the highest percentage of parenchymal involvement: 87.3 and 88.9%, respectively (p <.01). Abnormalities of the echostructure of the parenchyma and hypervascularity of the glands were detected with all kinds of fillers without significant differences per type. A significant substantial interrater kappa (0.61) with an agreement of 90% for all glands among observers was found.
Conclusion
Users of common types of CFs frequently present subclinical ultrasonographic signs of inflammation of the lacrimal, parotid, and submandibular glands. Further research on the topic seems necessary.
Background Detection of activity in morphea is paramount for adequately managing the disease. Subclinical ultrasound involvement on inactive lesions or healthy skin areas adjacent to morphea has not been described to date. Objectives The study aimed to detect morphea’s subclinical activity by Color Doppler ultrasound not identified with the clinical scorings. Materials & methods This cross-sectional retrospective study was done from January 2014 to July 2019 in patients with a clinicopathological diagnosis of morphea. The modified Localized Scleroderma Skin Severity Index (mLoSSI) and The Ultrasound Morphea Activity Score (US-MAS) were used to correlate clinical and subclinical activity. Results A total of 36 patients met the inclusion criteria. 54% of cases presented subclinical activity in areas adjacent to the clinically active lesion, 23% in nonadjacent regions, and 23% demonstrated activity at a clinically inactive lesion site. 100% of patients with morphea “en coup de sabre” involving the frontal region of the face concomitantly presented both subclinical activities of morphea on the frontal facial region and the scalp following the same axis. A positive relationship was observed between the degree of clinical activity measured by mLoSSI and US-MAS scoring. The main limitations of our study were the low number of patients and the inability to detect alterations < 0.1 mm. Conclusions Subclinical activity is frequent in morphea, can extend beyond the lesional areas, including apparently noninvolved adjacent and distant corporal regions, and can be detected by color Doppler ultrasound.
Introducción: La reacción a drogas con eosinofilia y síntomas sistémicos (DRESS) es una enfermedad poco frecuente que puede ser letal. Objetivo: Describir los hallazgos clínicos, de laboratorio e histopatológicosen pacientes con DRESS. Metodología: Estudioretrospectivo de fichas clínicas de pacientes conDRESS entre los años 2007 y 2017 con scoreregiSCAR mayor o igual a caso probable. Resultados: Se estudiaron 24 pacientes: 14 fueron mujeres (58,3%), la edad promedio fue 45,04 años DS 17,2(16-78). Los medicamentos frecuentemente implicados fueron Lamotrigina (33,3%) y Carbamazepina (20,8%).La latencia fue de 28 días DS 17,7 (10-90). La clínica más frecuente fue prurito 87,5%, fiebre 75%, edema facial 62,5% y adenopatías 45,8%. En laboratorio lo más alterado fueron pruebas hepáticas (70,8%) yeosinofilia (45,8%). 11 pacientes (45,8%) presentaroneosinófilos en la histopatología y 21 pacientes (87,5%)fueron tratados con corticoides. La mortalidad fue de11,1% (2 pacientes) por causas distintas a DRESS.Discusión: DRESS es una reacción adversa a medicamentos severa con hallazgos clínicos y de laboratorio muy variados y evolutivos, requiriendo su conocimiento para no retrasar su diagnóstico ytratamiento.
<b><i>Background:</i></b> Pain is not a trivial issue for hidradenitis suppurativa (HS) patients and has been considered a domain in the Core Outcome Set. To date, there is no evidence about pain caused by the ultrasound examinations. <b><i>Objective:</i></b> The aim of the study was to assess the presence of pain generated by the ultrasound examinations of HS patients. <b><i>Methods:</i></b> A multicentric cross-sectional study for detecting pain during the ultrasound examinations of HS patients using a validated verbal questionnaire immediately after the imaging studies. Statistical analysis included demographic data and possible associations with sex, age, location, clinical (Hurley), and ultrasonographic scoring (SOS-HS). The statistical tests were two proportions <i>Z</i> test, χ<sup>2</sup> test, Student’s <i>t</i> test, and ANOVA. A <i>p</i> < 0.05 was considered significant. <b><i>Results:</i></b> 317 patients met the criteria. 77.3% of them did not present pain. Of cases with pain, 59.8% were mild, 16.7% moderate, and 23.6% severe. No significant association was found with sex, age, staging, location, or the number of affected regions. Although nonsignificant, severe pain cases were more frequent in the clinical Hurley III and ultrasonographic SOS-HS III stages. <b><i>Conclusion:</i></b> Pain generated by the ultrasound examination of HS patients is infrequent.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.