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.
During the first year of the COVID-19 pandemic, unauthorized drugs were widely used. Ivermectin and hydroxychloroquine are drugs that inhibit viral replication in vitro and that have been used in several medical centers. This clinical trial analyzes their efficacy in hospitalized patients with moderate COVID-19. Methods: This a controlled, clinical, randomized, double-blind trial that included hospitalized patients with COVID-19-induced pneumonia, without severe respiratory failure. Patients were randomized to one of three groups: Group 1—hydroxychloroquine, 400 mg every 12 h on the first day and, subsequently, 200 mg every 12 h for 4 days; Group 2—ivermectin, 12 mg or 18 mg, according to patient weight; and Group 3—placebo. At inclusion, blood samples for arterial blood gases and biochemical markers were obtained. The primary outcome was established as the length of stay due to patient improvement and the rate of respiratory deterioration or death. Results: During the month of August 2020, the admission of patients requiring hospitalization mostly encompassed cases with severe respiratory failure, so we ended the recruitment process and analyzed the data that was available at the time. One hundred and six (106) patients with an average age of 53 yrs (±16.9) were included, with a greater proportion of males (n = 66, 62.2%). Seventy-two percent (72%) (n = 76) had an associated comorbidity. Ninety percent (90%) of patients were discharged due to improvement (n = 96). The average duration of hospitalization was 6 days (IQR, 3–10). No difference in hospitalization duration was found between the treatment groups (Group1: 7 vs. Group 2: 6 vs. Group 3: 5, p = 0.43) nor in respiratory deterioration or death (Group 1: 18% vs. Group 2: 22.2% vs. Group 3: 24.3%, p = 0.83). Conclusions: In non-critical hospitalized patients with COVID-19 pneumonia, neither ivermectin nor hydroxychloroquine decreases the number of in-hospital days, respiratory deterioration, or deaths.
Background End-stage renal failure of unknown origin (ESRD-UO) is a public health problem in Mexico and many regions of the world. The prevalence of ESRD-UO in Aguascalientes Mexico is one of the highest worldwide, particularly in adults between 20 and 40 years of age. Aim To screen adolescents for chronic kidney disease (CKD), identify risk factors, and histologically characterize adolescents with persistent albuminuria (pACR). Methodology This is a cross-sectional, observational, and comparative study of adolescents in whom serum creatinine and the albumin creatinine ratio (ACR) were determined when screening for CKD. A clinical evaluation and risk factor survey were conducted. Patients with an abnormal ACR (≥ 30 mg/gr) or a low glomerular filtration rate (GFR) (≤75 ml/min/1.73 m2) were reevaluated and a renal ultrasound was obtained (rUS). A kidney biopsy was performed in patients with pACR. Results Five-hundred and thirteen (513) students were included, 19 had pACR and 494 were controls. The prevalence of pACR was 3.7% (95%CI 2.1 – 5.3). Only one patient had a decreased GRF. None of the patients with pACR had anatomical abnormalities of the urinary tract by rUS. Patients with pACR had a decreased total renal volume in comparison with the control group (150 vs 195 ml/m2, p <0.01). Eighteen (18) kidney biopsies were performed, 72% had glomerulomegaly, and only one patient had mild fibrosis. Podocyte abnormalities were evident on electron microscopy: partial fusion (100%), microvillous degeneration (80%), and increased organelles (60%). Risk factors for pACR were: homestead proximity to maize crops, the use of pesticides at the father´s workplace, a family history of CKD, and blood pressure abnormalities. The body mass index and breastfeeding were protective factors. Conclusions The prevalence of pACR in adolescents in Aguascalientes is high, and histologic compromise is characterized by podocyte injury in the absence of fibrosis. The renal volume of pACR patients was decreased, suggesting oligonephronia. Exposure to environmental toxins such as pesticides, even prenatally, may be responsible for this pathological entity. Screening programs in adolescents by determining ACR are necessary in our milieu.
BACKGROUND The lethality rate of COVID-19 in Mexico is one of the highest worldwide, but in-hospital factors associated with this increased rate have yet to be explored. This study aims to evaluate those factors that could be associated with mortality at 28 days in critically ill COVID-19 patients in Mexico. METHODS This is a retrospective post hoc analysis of the clinical trial (NCT04381858) comparing the safety and efficacy of administering convalescent plasma from COVID-19 patients or human immunoglobulin. The primary outcome, death at 28 days, was analyzed. Results Between May and October 2020, 196 predominantly male patients (n=122, 62.2%) with an average of 58.1 years (plus-or-minus sign 15.5), were included in the cohort. Mortality at 28 days was 44.3 % (n = 84). Patients included in the second trimester had a greater mortality rate when compared with those recruited in the first trimester (54.1 vs 32.1, p < 0.01). On multivariate analysis, the detected protective factors were the use of fentanyl HR 0.51 (95%CI 0.31 - 0.85, p=0.01), the use of antibiotics HR 0.22 (95% CI 0.13 - 0.36, p < 0.01), and a previously healthy state (no comorbidities other than obesity) HR 0.58 (95%CI 0.35 - 0.94, p = 0.03); risk factors were severe kidney injury (AKIN3) HR 1.74 (95%CI 1.04 - 2.9, p=0.035), elevated D-Dimer levels HR 1.02 (95%CI 1.007 - 1.04, p=0.005), shock OR 5.8 (2.4 - 13.8, p < 0.01), and recruitment in the second trimester OR 2.3 (95%CI 1.1 - 4.8, p=0.02). Conclusion In-hospital mortality in critically ill COVID-19 patients has increased in our center. The appropriate use of antibiotics, the type of sedation, and AKIN3 are modifiable factors directly related to this increased mortality. The increase in mortality observed in the second trimester is explained by hospital overcrowding that began in August 2020.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.