19043 research outputs found
Sort by
Pre-Trained Multimodal Large Language Model Enhances Dermatological Diagnosis Using Skingpt-4
No full textLarge language models (LLMs) are seen to have tremendous potential in advancing medical diagnosis recently, particularly in dermatological diagnosis, which is a very important task as skin and subcutaneous diseases rank high among the leading contributors to the global burden of nonfatal diseases. Here we present SkinGPT-4, which is an interactive dermatology diagnostic system based on multimodal large language models. We have aligned a pre-trained vision transformer with an LLM named Llama-2-13b-chat by collecting an extensive collection of skin disease images (comprising 52,929 publicly available and proprietary images) along with clinical concepts and doctors’ notes, and designing a two-step training strategy. We have quantitatively evaluated SkinGPT-4 on 150 real-life cases with board-certified dermatologists. With SkinGPT-4, users could upload their own skin photos for diagnosis, and the system could autonomously evaluate the images, identify the characteristics and categories of the skin conditions, perform in-depth analysis, and provide interactive treatment recommendations
Response to “Low-Dose Oral Minoxidil for Androgenetic Alopecia Is Not Associated With Clinically Significant Blood-Pressure Changes: A Retrospective Study”
No full textIncidence of Otolaryngological Manifestations in Individuals With Autism Spectrum Disorder: A Special Focus on Auditory Disorders
No full textAutism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by stereotyped and repetitive behavior patterns. In addition to neurological and behavioral problems, individuals with ASD commonly experience otolaryngological comorbidities. Individuals with ASD often have auditory disorders including hearing loss and auditory processing disorders such as central auditory processing disorder (CAPD), as well as both chronic and recurrent otitis media. These challenges negatively impact a person’s ability to effectively communicate and may further impact their neurological functioning, particularly when not appropriately treated. Individuals diagnosed with ASD also have difficulty sleeping which contributes to increased irritability and may further aggravate the core behavioral symptoms of autism. The individuals with ASD also have a higher rate of sinusitis which contributes to the worsening of the autism behavior phenotype. The high prevalence of otolaryngological comorbidities in individuals with ASD warrants a better collaboration between their various healthcare providers and otolaryngologists with expertise in auditory, sleep, and sinus disorders in pursuit of improving the quality of life of affected individuals and their families/caregivers
Underreporting of Acral Lentiginous Melanoma in Studies Informing American Joint Committee on Cancer Staging System Guidelines: A Review of 150 Cited Studies
No full textStrong Association Between Growth Hormone Therapy and Proximal Tibial Physeal Avulsion Fractures in Children and Adolescents: A Case-Control Study
No full textBackground:Published literature describes slipped capital femoral epiphysis as a complication of recombinant human growth hormone (rhGH) therapy that may be related to decreased physeal strength. The purpose of the current investigation was to utilize a case-control study design to determine whether a greater proportion of pediatric patients sustaining physeal avulsion fractures of the proximal tibia were undergoing rhGH therapy at the time of injury compared with a cohort of matched controls.Methods:A case-control design study design was utilized. Patients 4 to 18 years of age with proximal tibial physeal avulsion fractures (cases) or midshaft tibial fractures (controls) at our institution from February 1, 2016, to May 4, 2023, were identified. Cases and controls were matched 1:1 on the basis of age (within 1 year), sex, and body mass index (within 3 kg/m2). A total of 132 patients were included in the analysis (mean age, 13 ± 2 years). rhGH exposure was compared using conditional logistic regression with Firth correction.Results:We found that 11% of the patients with a proximal tibial physeal avulsion fracture were on rhGH therapy at the time of injury compared with 0% of patients with midshaft tibial fractures (odds ratio [OR], 15.0; 95% confidence interval [CI], 1.8 to 1,946.7; p = 0.007). There was no significant difference in the proportion of sports-related injuries between cases (70%) and controls (67%) (OR, 1.15; 95% CI, 0.55 to 2.39; p = 0.85). Among subjects with proximal tibial avulsion fractures, the proportion requiring surgery did not differ significantly between patients receiving and those not receiving rhGH therapy (43% versus 41%, respectively; p = 0.99).Conclusions:This study demonstrates that the proportion of subjects who sustained proximal tibial physeal avulsion fractures and were receiving recombinant human growth hormone therapy at the time of injury was significantly greater than that of an age, sex, and body mass index-matched control group with midshaft tibial fractures (11% versus 0%, respectively, representing 15-times greater odds of exposure). This quantifies a previously unreported serious orthopaedic complication associated with rhGH therapy.Level of Evidence:Prognostic Level III. See Instructions for Authors for a complete description of levels of evidence
The Incremental Risk of Fragility Fractures in Aging Men
No full textIntroduction: While the United States Preventative Services Task Force recommends osteoporosis screening for women 65 years and older, there is no definitive recommendation for routine osteoporosis screening in men. The purpose of this study was to determine the age at which the odds of fragility fractures (FFx) increase in men to help guide future policy discussions evaluating an optimal screening strategy in this population. Methods: Men older than 49 years were identified in the PearlDiver Patient Records Database. Patients were excluded if they had a prior fragility fracture, if they were at high risk for osteoporosis due to comorbidities, or if they carried a diagnosis of and/or were on treatment for osteoporosis. The prevalence of FFx was trended for each age group. A stratum-specific likelihood ratio (SSLR) analysis was conducted to identify data-driven strata that maximize the incremental FFx risk by age for men. Logistic regression analyses controlling for potential confounders were conducted to test these identified strata. Results: The incidence of FFx started to increase after the age of 64 years for men. Further, the identified data-driven age strata associated with a significant and incremental difference in fragility fractures were the following: 50–64, 65–69, 70–72, 73–75, 76–78, 79–80, and 81+. When compared to the youngest age stratum (50–64 years), multivariable regression showed the risk of fragility fracture incrementally increased starting in those aged 70–72 (RR, 1.31; 95% CI. 1.21–1.46; p \u3c 0.001) with the highest risk in those aged 81+ (RR, 5.35; 95% CI, 5.10–5.62; p \u3c 0.001). Conclusion: In men without a pre-existing history of osteoporosis, the risk of fragility fractures starts to increase after the age of 70. Further work building upon these data may help to identify a specific age at which routine bone health screening in males can help to minimize fractures and their associated morbidity and mortality
Frailty as a Predictor of Postoperative Outcomes in Neurosurgery: A Systematic Review
No full textINTRODUCTION: Baseline frailty status has been utilized to predict a wide range of outcomes and guide preoperative decision making in neurosurgery. This systematic review aims to analyze existing literature on the utilization of frailty as a predictor of neurosurgical outcomes. EVIDENCE ACQUISITION: We conducted a systematic review following PRISMA guidelines. Studies that utilized baseline frailty status to predict outcomes after a neurosurgical intervention were included in this systematic review. Studies that utilized sarcopenia as the sole measure of frailty were excluded. PubMed, EMBASE, and Cochrane library was searched from inception to March 1st, 2023, to identify relevant articles. EVIDENCE SYNTHESIS: Overall, 244 studies met the inclusion criteria. The 11-factor modified frailty index (mFI-11) was the most utilized frailty measure (N.=91, 37.2%) followed by the five-factor modified Frailty Index (mFI-5) (N.=80, 32.7%). Spine surgery was the most common subspecialty (N.=131, 53.7%), followed by intracranial tumor resection (N.=57, 23.3%), and post-operative complications were the most reported outcome (N.=130, 53.2%) in neurosurgical frailty studies. The USA and the Bowers author group published the greatest number of articles within the study period (N.=176, 72.1% and N.=37, 15.2%, respectively). CONCLUSIONS: Frailty literature has grown exponentially over the years and has been incorporated into neurosurgical decision making. Although a wide range of frailty indices exist, their utility may vary according to their ability to be incorporated in the outpatient clinical setting
Impact of COVID-19 on Spinal Diagnosis and Procedural Volume in the United States
No full textStudy Design: Retrospective analysis of a national database. Objectives: COVID-19 resulted in the widespread shifting of hospital resources to handle surging COVID-19 cases resulting in the postponement of surgeries, including numerous spine procedures. This study aimed to quantify the impact that COVID-19 had on the number of treated spinal conditions and diagnoses during the pandemic. Methods: Using CPT and ICD-10 codes, TriNetX, a national database, was utilized to quantify spine procedures and diagnoses in patients \u3e18 years of age. The period of March 2020-May 2021 was compared to a reference pre-pandemic period of March 2018-May 2019. Each time period was then stratified into four seasons of the year, and the mean average number of procedures per healthcare organization was compared. Results: In total, 524,394 patient encounters from 53 healthcare organizations were included in the analysis. There were significant decreases in spine procedures and diagnoses during March-May 2020 compared to pre-pandemic levels. Measurable differences were noted for spine procedures during the winter of 2020-2021, including a decrease in lumbar laminectomy and anterior cervical arthrodesis. Comparing the pandemic period to the pre-pandemic period showed significant reductions in most spine procedures and treated diagnoses; however, there was an increase in open repair of thoracic fractures during this period. Conclusions: COVID-19 resulted in a widespread decrease in spinal diagnosis and treated conditions. An inverse relationship was observed between new COVID-19 cases and spine procedural volume. Recent increases in procedural volume from pre-pandemic levels are promising signs that the spine surgery community has narrowed the gap in unmet care produced by the pandemic
Machine Learning Assessment of Background Parenchymal Enhancement in Breast Cancer and Clinical Applications: A Literature Review
No full textBackground Parenchymal Enhancement (BPE) on breast MRI holds promise as an imaging biomarker for breast cancer risk and prognosis. The ability to identify those at greatest risk can inform clinical decisions, promoting early diagnosis and potentially guiding strategies for prevention such as risk-reduction interventions with the use of selective estrogen receptor modulators and aromatase inhibitors. Currently, the standard method of assessing BPE is based on the Breast Imaging-Reporting and Data System (BI-RADS), which involves a radiologist’s qualitative categorization of BPE as minimal, mild, moderate, or marked on contrast-enhanced MRI. This approach can be subjective and prone to inter/intra-observer variability, and compromises accuracy and reproducibility. In addition, this approach limits qualitative assessment to 4 categories. More recently developed methods using machine learning/artificial intelligence (ML/AI) techniques have the potential to quantify BPE more accurately and objectively. This paper will review the current machine learning/AI methods to determine BPE, and the clinical applications of BPE as an imaging biomarker for breast cancer risk prediction and prognosis