Citations

Abstract Background Neuropathologic evaluation is essential for diagnosing and treating dementia, but definitive diagnoses is only available after post‐mortem brain autopsy. Positron emission tomography (PET) offers a potential in vivo proxy for predicting neuropathology. This study proposes a semi‐supervised learning (SSL) model using a single FDG‐PET image to predict underlying neuropathology. Method The SSL model leverages a self‐organized graph structure based on a patient similarity network (PSN) created from 1,495 FDG‐PET images across the aging and neurodegenerative spectrum. Each patient is represented by a node, with edges indicating image similarity derived from principal component analysis features and cosine similarity weights. The PSN structure connects 20 nearest neighbors. Neuropathologic labels were available for 204 autopsied patients. The Poisson Learning Method was employed to propagate labels from these annotated nodes to unlabeled nodes, guided by the PSN structure. FDG‐PET images were collected from clinical and research participants at the Mayo Clinic and processed using an MRI‐free pipeline. Neuropathologic labels were assigned based on widely accepted diagnostic criteria. Leave‐one‐out cross‐validation (LOOCV) was used to assess model performance. Results The confusion matrix demonstrated high accuracy in predicting Alzheimer's disease, frontotemporal lobar degeneration with tau inclusions, and Lewy body disease pathology. A Sankey diagram and label distribution analysis revealed strong correlations between clinical and predicted neuropathologic labels. Conclusion This study highlights the potential of a graph‐based SSL pipeline to predict neuropathological changes using FDG‐PET imaging data, despite limited pathology labels. The findings underscore the value of SSL in bridging the gap between abundant neuroimaging data and scarce neuropathologic labels, contributing to improved dementia diagnosis and understanding.

Abstract Objective To compare the pathology outcomes of image-guided breast biopsies across a multistate health care enterprise by the method of detection (MOD), including the positive predictive value (PPV3) and histological types. Methods Biopsies from October 31, 2017, to July 6, 2023, across 18 imaging sites in 4 states were extracted. Radiologists prospectively assigned MODs, including symptomatic presentations (self-examination, clinical examination) and imaging modalities (mammogram, tomosynthesis, US, MRI, contrast-enhanced mammogram, molecular breast imaging, other imaging). For each MOD, the rates of malignancy and cancer subtypes were calculated. Univariate and multivariate logistic regression analyses were performed. Results In 26 932 biopsies on 22 582 patients (mean age 57.6 years ± 14.2 [SD]; 22 416 women), 6068 (81.1%) cancers were detected by screening, and 1144 (15.3%) were detected by symptoms. Symptomatic presentation MODs had a higher PPV3 (43.0% vs 25.6%; P < .001), larger cancer lesion sizes (x̄ = 27.5 mm vs x̄ = 17.8 mm; P < 001), and a higher association with invasive carcinoma (96.7% vs 76.8%; P <.001) compared with screening imaging-based MODs. Methods of detection with higher PPV3s also tended to have higher rates of invasive carcinoma (Spearman’s ρ = 0.83). Conclusion Compared with breast cancers detected after symptomatic presentations, those identified via image-based screening were smaller and less often invasive, confirming the value of screening in early detection. Positive predictive value and the rate of invasive carcinoma varied in parallel across MODs.

Abstract Background Percutaneous endoscopic gastrostomy (PEG) and percutaneous radiologic gastrostomy (PRG) are used for gastric drainage, decompression, and feeding. Recent innovations enable bumper and balloon‐type tube placement via transabdominal approach under guidance of fluoroscopy or sonography. Method This is a single‐center retrospective cohort study to evaluate the outcomes of balloon and bumper gastrostomy tube placement under guide of fluoroscopy and ultrasound. The total sample size was 470 consecutive patients. The eligibility criteria included all patients aged ≥18 years who underwent a balloon or bumper‐type gastrostomy tube insertion for nutrition support in both the interventional radiology unit and at the bedside between 2017 and 2022. Result This study revealed no significant differences between the two types of tubes in terms of time to tube replacement or requiring a gastrostomy tube. There was a positive correlation between the time that a patient has a gastrostomy tube and major complications ( P = 0.005) and a positive correlation between number of tubes replaced and minor complications ( P < 0.001). Both types of tubes were associated with low rates of complications. However, patients with a balloon tube were more likely to experience gastric‐tube–related hospitalization/ED visits and require a >24‐h hospital stay postoperation. Conclusion These findings can help healthcare providers make informed decisions when selecting the appropriate type of tube for their patients to have more durability with less complication.

Abstract Purpose The U.S. population is rapidly aging. The supply of surgeons needed to meet this demand should be evaluated. This study evaluated the trends in supply of Medicare surgeons by specialty and by U.S. state and region. Method All surgeons associated with a National Provider Identifier for cardiothoracic surgery, colorectal surgery, general surgery, gynecologic oncology, hand surgery, neurosurgery, obstetrics-gynecology, ophthalmology, oral and maxillofacial surgery, orthopedic surgery, otolaryngology, plastic and reconstructive surgery, surgical oncology, urology, and vascular surgery from 2013 to 2019 on the Centers for Medicare & Medicaid Services website were included. The absolute number of physicians was adjusted per 100,000 Medicare beneficiaries. Annual change was calculated by linear regression model, and the compound annual growth rate (CAGR) was calculated per specialty. Results The absolute number of physicians per 100,000 beneficiaries increased in 6 of 15 specialties during the study period. Vascular surgery had the largest annual increase (+0.23; CAGR, +2.75%), and obstetrics-gynecology had the largest annual decrease (−1.08; CAGR, −1.44%). Surgical oncology showed the largest positive CAGR (+4.20%). Oral and maxillofacial surgery had the largest negative CAGR (−2.86%). The Northeast was above the national average in supply for each specialty. The Midwest had the most specialties with positive CAGRs. The South did not meet the national average for physicians in any specialty. Conclusions This analysis of 15 surgical specialties provides important context to predicted physician shortages to the Medicare population. The study found geographic variation by region across specialty, which has important implications for health care planning from the level of undergraduate medical education to provision of hospital resources. Overall, the supply of surgeons across all specialties may not be sufficient to meet the demand of the rapidly aging U.S. population. Future study is needed to evaluate why surgeons are leaving the Medicare program.

Abstract Objectives The surge in patient portal messages (PPMs) with increasing needs and workloads for efficient PPM triage in healthcare settings has spurred the exploration of AI-driven solutions to streamline the healthcare workflow processes, ensuring timely responses to patients to satisfy their healthcare needs. However, there has been less focus on isolating and understanding patient primary concerns in PPMs—a practice which holds the potential to yield more nuanced insights and enhances the quality of healthcare delivery and patient-centered care. Materials and Methods We propose a fusion framework to leverage pretrained language models (LMs) with different language advantages via a Convolution Neural Network for precise identification of patient primary concerns via multi-class classification. We examined 3 traditional machine learning models, 9 BERT-based language models, 6 fusion models, and 2 ensemble models. Results The outcomes of our experimentation underscore the superior performance achieved by BERT-based models in comparison to traditional machine learning models. Remarkably, our fusion model emerges as the top-performing solution, delivering a notably improved accuracy score of 77.67 ± 2.74% and an F1 score of 74.37 ± 3.70% in macro-average. Discussion This study highlights the feasibility and effectiveness of multi-class classification for patient primary concern detection and the proposed fusion framework for enhancing primary concern detection. Conclusions The use of multi-class classification enhanced by a fusion of multiple pretrained LMs not only improves the accuracy and efficiency of patient primary concern identification in PPMs but also aids in managing the rising volume of PPMs in healthcare, ensuring critical patient communications are addressed promptly and accurately.

Introduction: The COVID-19 pandemic has had major impacts on all healthcare services, including cardiac imaging. In this study, we investigate annual changes in cardiac imaging procedural volume and reimbursement among Medicare Beneficiaries (MB) from 2018 to 2020. Methods: We used the Center of Medicare and Medicaid Services database to identify a 100% sample of MB who underwent cardiac imaging procedures from 2018 to 2020. Using the Current Procedural Terminology (CPT) codes, we identified transthoracic echocardiogram (TTE), transesophageal echocardiogram (TEE), stress echocardiogram, and nuclear stress test procedures. We examined each procedure’s total, inpatient (facility), and outpatient (non-facility) annual volumes per 1,000 MB. We also examined the total annual Medicare reimbursement per imaging type during that period. We compared annual changes in volumes and total reimbursement between two-time intervals: 2018-2019 and 2019-2020. Results: All annual cardiac imaging procedural volumes decreased significantly in 2020 compared to 2019 ( P<0.001 ). The biggest change was observed in TEE, which decreased by 29.20%, followed by stress echocardiography (26.01%), nuclear stress test (22.96%), and TTE (10.68%). The decrease was more evident in the inpatient setting. Inpatient stress echocardiography decreased by 27.04% (vs 23.82% in the outpatient setting), nuclear stress test decreased by 24.82% (vs 20.66%), and TTE decreased by 11.03% (vs 9.58%). There was also a significant reduction in total annual reimbursement for all procedures in 2020 compared to 2019 ( P=0.0015 ). Stress echocardiogram, nuclear stress test, TEE, and TTE reimbursement decreased by 28.08%, 24.00%, 21.11%, and 15.79%, respectively. Conclusions: The COVID-19 pandemic was associated with a significant and abrupt reduction in annual cardiac imaging procedural volumes and total reimbursement among MB in both inpatient and outpatient settings.