Current state of machine learning for non-melanoma skin cancer.

BACKGROUND: Machine learning (ML) has been increasingly utilized for skin cancer screening, primarily of melanomas but also of non-melanoma skin cancers (NMSC). OBJECTIVE: This study presents the first quantitative review of the success of these techniques in NMSC screening. METHODS: A primary literature search was conducted using PubMed, MEDLINE, and arXiv, capturing all articles involving ML techniques and NMSC screening. RESULTS: 52 articles were included for quantitative analysis, resulting in a mean sensitivity of 89.2% (n = 52, 95% confidence interval (CI) 87.0-91.3) and a mean specificity of 81.1% (n = 44, 95% CI 74.5-87.8) for ML algorithms in the diagnosis of NMSC. Studies were further grouped by skin cancer type, algorithm type, diagnostic gold standard, data set source, and data set size. CONCLUSION: There is insufficient evidence to conclude that an ML algorithm is superior at NMSC screening than a trained dermatologist utilizing dermoscopy for either BCC or SCC. Given that the studies included in this review were performed in silico, further study in the form of randomized clinical trials are needed to further elucidate the role of NMSC screening algorithms in dermatology.

Relapse of Plasmablastic Lymphoma With Cutaneous Involvement in an Immunocompetent Male.

Plasmablastic lymphoma (PBL) is a rare type of non-Hodgkin lymphoma frequently found in the context of immunosuppression and infection with human immunodeficiency virus (HIV) and/or Epstein-Barr virus (EBV). A 33-year-old immunocompetent male presented with recurrent episodes of epistaxis and a growing intranasal mass. Excisional biopsy of the mass revealed an immunohistochemical profile diagnostic of PBL. Upon completion of chemoradiation, he underwent a transnasal endoscopic mucosal flap tissue rearrangement to restore patency for both functional and surveillance purposes. There was no endoscopic evidence of residual or recurrent disease. However, 8 months later, he was found to have a relapse involving the skin. The nasal cavity is one of the most common sites affected by PBL. Involvement of the nasal cavity may present with symptoms of persistent epistaxis accompanied by an enlarging mass. A plasmablastic immunophenotype in combination with HIV or EBV positivity can aid diagnosis.

Characterizing DRESS syndrome recurrence: a systematic review.

Recurrence of DRESS syndrome is poorly characterized, and dermatologists must be prepared to predict, identify, and manage patients after treatment of the initial presentation. In this study, a primary literature search was conducted using PubMed, capturing all articles recording cases of DRESS syndrome recurrence. Forty-two articles were included for review comprising a total of 60 patients. The average age of patients was 46.3 years and time to recurrence was 123 days. Recurrent episodes presented more frequently with a higher fever and eosinophil absolute peak. Relapse was most often attributed to the introduction of a new medication (n = 18). Of the 17 cases in which outcome data were available, the survival rate of those experiencing recurrence was 71%. Viral reactivation with HHV-6 and organ involvement of the liver were frequently recorded complications. In essence, viral reactivation, severe internal organ involvement, and hematological abnormalities all portended a poorer prognosis in those experiencing DRESS syndrome recurrence. An adequate course of treatment should be maintained until clinical and laboratory parameters normalize, with a slow taper to minimize the likelihood of relapse in those most at risk.

Personal Protective Equipment: Attitudes and Behaviors Among Nurses at a Single University Medical Center.

INTRODUCTION: Healthcare workers are at an increased risk of infectious disease transmission through occupational exposure. Despite this, rates of personal protective equipment (PPE) use vary among healthcare personnel. This cross-sectional study surveyed healthcare workers at a single academic center to determine how the coronavirus disease 2019 (COVID-19) pandemic affected the perceptions and behaviors of PPE usage. METHODS: An anonymous online survey through the SurveyMonkey® tool (Zendesk Inc., San Francisco, California) was sent to the University of California, Irvine, Medical Center department listserv of nurses on March 20, 2021, and was closed on June 20, 2021. RESULTS: Of 311 respondents, 23% admitted to suffering a splash injury to the face during a procedure. When compared to one year ago prior to the COVID-19 pandemic, PPE was more important (93% vs. 80%) and more frequently used (80% vs. 54%) by respondents. The recent COVID-19 pandemic had the strongest impact on increasing respondents' perception of the importance of PPE (44%). CONCLUSION: The COVID-19 pandemic positively impacted rates of PPE usage and perceptions of the importance of PPE among healthcare workers at a single academic institution. Implementing clear and effective education and training programs, ensuring adequate access to protective gear, and promoting a positive safety climate can help improve adherence to safety protocols and appropriate use of PPE.

Retrospective analysis of eFAST ultrasounds performed on trauma activations at an academic level-1 trauma center.

BACKGROUND: Point-of-care ultrasound (POCUS) has become increasingly integrated into the practice of emergency medicine. A common application is the extended focused assessment with sonography in trauma (eFAST) exam. The American College of Emergency Physicians has guidelines regarding the scope of ultrasound in the emergency department and the appropriate documentation. The objective of this study was to conduct a review of performed, documented and billed eFAST ultrasounds on trauma activation patients. METHODS: This was a retrospective review of all trauma activation patients during a 10-month period at an academic level-one trauma center. A list comparing all trauma activations was cross-referenced with a list of all billed eFAST scans. Medical records were reviewed to determine whether an eFAST was indicated, performed, and appropriately documented. RESULTS: We found that 1,507 of 1,597 trauma patients had indications for eFAST, but 396 (27%) of these patients did not have a billed eFAST. Of these 396 patients, 87 (22%) had documentation in the provider note that an eFAST was performed but there was no separate procedure note. The remaining 309 (78%) did not have any documentation of the eFAST in the patient's chart although an eFAST was recorded and reviewed during ultrasound quality assurance. CONCLUSION: A significant proportion of trauma patients had eFAST exams performed but were not documented or billed. Lack of documentation was multifactorial. Emergency ultrasound programs require appropriate reimbursement to support training, credentialing, equipment, quality assurance, and device maintenance. Our study demonstrates a significant absence of adequate documentation leading to potential revenue loss for an emergency ultrasound program.

Predicting DRESS Syndrome Recurrence-The ReDRESS Score.

This cross-sectional study of DRESS syndrome cases creates a model capable of predicting recurrence to identify patients most at risk.

Simplified point-of-care ultrasound protocol to confirm central venous catheter placement: A prospective study.

BACKGROUND: The current standard for confirmation of correct supra-diaphragmatic central venous catheter (CVC) placement is with plain film chest radiography (CXR). We hypothesized that a simple point-of-care ultrasound (POCUS) protocol could effectively confirm placement and reduce time to confirmation. METHODS: We prospectively enrolled a convenience sample of patients in the emergency department and intensive care unit who required CVC placement. Correct positioning was considered if turbulent flow was visualized in the right atrium on sub-xiphoid, parasternal or apical cardiac ultrasound after injecting 5 cc of sterile, non-agitated, normal saline through the CVC. RESULTS: Seventy-eight patients were enrolled. POCUS had a sensitivity of 86.8% (95%CI 77.1%-93.5%) and specificity of 100% (95%CI 15.8%-100.0%) for identifying correct central venous catheter placement. Median POCUS and CXR completion were 16 minutes (IQR 10-29) and 32 minutes (IQR 19-45), respectively. CONCLUSION: Ultrasound may be an effective tool to confirm central venous catheter placement in instances where there is a delay in obtaining a confirmatory CXR.

Simplified point-of-care ultrasound protocol to confirm central venous catheter placement:A prospective study / 世界急诊医学杂志（英文）

@#BACKGROUND: The current standard for confirmation of correct supra-diaphragmatic central venous catheter (CVC) placement is with plain film chest radiography (CXR). We hypothesized that a simple point-of-care ultrasound (POCUS) protocol could effectively confirm placement and reduce time to confirmation. METHODS: We prospectively enrolled a convenience sample of patients in the emergency department and intensive care unit who required CVC placement. Correct positioning was considered if turbulent flow was visualized in the right atrium on sub-xiphoid, parasternal or apical cardiac ultrasound after injecting 5 cc of sterile, non-agitated, normal saline through the CVC. RESULTS: Seventy-eight patients were enrolled. POCUS had a sensitivity of 86.8% (95%CI 77.1%–93.5%) and specificity of 100% (95%CI 15.8%–100.0%) for identifying correct central venous catheter placement. Median POCUS and CXR completion were 16 minutes (IQR 10–29) and 32 minutes (IQR 19–45), respectively. CONCLUSION: Ultrasound may be an effective tool to confirm central venous catheter placement in instances where there is a delay in obtaining a confirmatory CXR.