Citations

Pulmonary auscultation is essential for detecting abnormal lung sounds during physical assessments, but its reliability depends on the operator. Machine learning (ML) models offer an alternative by automatically classifying lung sounds. ML models require substantial data, and public databases aim to address this limitation. This systematic review compares characteristics, diagnostic accuracy, concerns, and data sources of existing models in the literature. Papers published from five major databases between 1990 and 2022 were assessed. Quality assessment was accomplished with a modified QUADAS-2 tool. The review encompassed 62 studies utilizing ML models and public-access databases for lung sound classification. Artificial neural networks (ANN) and support vector machines (SVM) were frequently employed in the ML classifiers. The accuracy ranged from 49.43% to 100% for discriminating abnormal sound types and 69.40% to 99.62% for disease class classification. Seventeen public databases were identified, with the ICBHI 2017 database being the most used (66%). The majority of studies exhibited a high risk of bias and concerns related to patient selection and reference standards. Summarizing, ML models can effectively classify abnormal lung sounds using publicly available data sources. Nevertheless, inconsistent reporting and methodologies pose limitations to advancing the field, and therefore, public databases should adhere to standardized recording and labeling procedures.

INTRODUCTION: The coronavirus disease 19 (COVID-19) pandemic disrupted endoscopy practices, creating unprecedented decreases in cancer screening and surveillance services. We aimed to assess the impact of the pandemic on the proportion of patients diagnosed with Barrett's esophagus (BE) and BE-related dysplasia and adherence to established quality indicators. METHODS: Data from all esophagogastroduodenoscopies in the GI Quality Improvement Consortium, a national repository of matched endoscopy and pathology data, were analyzed from January 2018 to December 2022. Four cohorts were created based on procedure date and COVID-19 data: pre-pandemic (January 2018 to February 2020), pandemic-phase I (March 2020 to July 2020), pandemic-phase II (August 2020 to May 2021), and pandemic-phase III (June 2021 to December 2022). Observed and expected number of BE and BE-related dysplasia cases per month and adherence to the Seattle biopsy protocol and recommended surveillance intervals for nondysplastic BE (NDBE) were evaluated. RESULTS: Among 2,446,857 esophagogastroduodenoscopies performed during the study period, 104,124 (4.3%) had pathology-confirmed BE. The histologic distribution was 87.4% NDBE, 1.8% low-grade dysplasia, 2.4% indefinite for dysplasia, and 1.4% high-grade dysplasia. The number of monthly BE (−47.9% pandemic-phase I, −21.5% pandemic-phase II, and −19.0% pandemic-phase III) and BE-related dysplasia (high-grade dysplasia: 41.2%, −27.7%, and −19.0%; low-grade dysplasia: 49.1%, −35.3%, and −26.5%; any dysplasia: 46.7%, −32.3%, and −27.9%) diagnoses were significantly reduced during the pandemic phases compared with pre-pandemic data. Adherence rates to the Seattle protocol and recommended surveillance intervals for NDBE did not decline during the pandemic. DISCUSSION: There was a significant decline in the number of BE and BE-related dysplasia diagnoses during the COVID-19 pandemic, with an approximately 50% reduction in the number of cases of dysplasia diagnosed in the early pandemic. The absence of a compensatory increase in diagnoses in the pandemic-phase II and III periods may result in deleterious downstream effects on esophageal adenocarcinoma morbidity and mortality.

Patient education has been transformed using digital media and online repositories which disseminate information with greater efficiency. In dermatology, this transformation has allowed for patients to gain education on common cutaneous conditions and improve health literacy. Xanthelasma palpebrarum is one of the most common cutaneous conditions, yet there is a poor understanding of how digital materials affect health literacy on this condition. Our study aimed to address this paucity of literature utilizing Brief DISCERN, Rothwell’s Classification of Questions, and six readability calculations. The findings of this study indicate a poor-quality profile (Brief DISCERN < 16) regarding digital materials and readability scores which do not meet grade-level recommendations in the United States. This indicates a need to improve the current body of educational materials used by clinicians for diagnosing and managing xanthelasma palpebrarum.

Abstract Introduction Chronic insomnia affects 5% to 10% of the US population, increasing the demand for treatment options and the corresponding research to prove their validity.1 This review compares recommendations from 3 clinical guidelines and summarizes hypnotic medications, including their newly reported side effects not mentioned in the guidelines. In addition, we aim to provide an overview of what pharmacotherapies are available for prescribers and patients. Methods A literature search was conducted for articles published prior to January 10, 2022, and case reports and clinical studies were retrieved from PubMed and Google Scholar. Results Definitive conclusions cannot be drawn regarding the safety and efficacy of medications reviewed; however, trends are apparent. All 3 guidelines included in this review remarked most treatment recommendations as weak except for cognitive behavioral therapy for insomnia, which is effective but not readily available. Furthermore, based on the 15 case reports and 13 clinical studies presented in this review, many of the medications used for treatment of insomnia present safety concerns. Discussion Benzodiazepines and benzodiazepine receptor agonists are commonly used hypnotic agents with the “Z-drugs” having robust data establishing their efficacy for the short-term treatment of chronic insomnia. However, significant adverse effects related to the central nervous system (CNS), including developing tolerance, addiction, CNS depression, and amnesia, remain barriers to their long-term use. In comparison, newer agents present more favorable side-effect profiles although with less established efficacy. Additionally, off-label agents, including antidepressants, antihistamines, and natural supplements, are discussed due to their prominent use.

Background and Objectives: Literature reviews are foundational to understanding medical evidence. With AI tools like ChatGPT, Bing Chat and Bard AI emerging as potential aids in this domain, this study aimed to individually assess their citation accuracy within Nephrology, comparing their performance in providing precise. Materials and Methods: We generated the prompt to solicit 20 references in Vancouver style in each 12 Nephrology topics, using ChatGPT, Bing Chat and Bard. We verified the existence and accuracy of the provided references using PubMed, Google Scholar, and Web of Science. We categorized the validity of the references from the AI chatbot into (1) incomplete, (2) fabricated, (3) inaccurate, and (4) accurate. Results: A total of 199 (83%), 158 (66%) and 112 (47%) unique references were provided from ChatGPT, Bing Chat and Bard, respectively. ChatGPT provided 76 (38%) accurate, 82 (41%) inaccurate, 32 (16%) fabricated and 9 (5%) incomplete references. Bing Chat provided 47 (30%) accurate, 77 (49%) inaccurate, 21 (13%) fabricated and 13 (8%) incomplete references. In contrast, Bard provided 3 (3%) accurate, 26 (23%) inaccurate, 71 (63%) fabricated and 12 (11%) incomplete references. The most common error type across platforms was incorrect DOIs. Conclusions: In the field of medicine, the necessity for faultless adherence to research integrity is highlighted, asserting that even small errors cannot be tolerated. The outcomes of this investigation draw attention to inconsistent citation accuracy across the different AI tools evaluated. Despite some promising results, the discrepancies identified call for a cautious and rigorous vetting of AI-sourced references in medicine. Such chatbots, before becoming standard tools, need substantial refinements to assure unwavering precision in their outputs.

Spinal subependymomas (SE) are rare, often indolent benign tumors presenting most frequently as intramedullary tumors in the cervical spine or cervicothoracic junction. When symptomatic, patients often present with years of sensory changes, weakness, paresthesias, or bowel and bladder dysfunction. Preoperatively, SE are difficult to distinguish radiographically from ependymomas or astrocytomas; however, it is important to make the distinction intraoperatively as complete resection can be curative. Here the authors present a rare case of recurrent, symptomatic cervical subependymoma which underwent gross-total resection and discussion of management strategies and outcomes of all SE at their institution.

Sclerosing meningiomas (SMs) represent a rare histological variant of meningiomas, first described in 1989 as invasive bulking masses of whorling collagen bundles with a minimum percentage of meningothelia-resembling cells, and they are often misdiagnosed. The literature reports only 30 cases of SMs, with only two of them being intramedullary. The authors present the case of a patient with a cervical intramedullary SM who presented with gait disturbances, sensory deficits, weakness in four extremities, and hyperreflexia. The surgery was performed under neurophysiological monitoring and after administration of sodium fluorescein, which allowed us to discriminate the exact myelotomy point. Intramedullary SMs are very rare entities whose correct management may result in a good outcome.